==================== Test output for //tensorflow/python/distribute/failure_handling:gce_failure_handler_test (shard 3 of 8): 2023-05-10 05:24:58.799589: I tensorflow/core/util/port.cc:116] Experimental oneDNN custom operations are on. If you experience issues, please turn them off by setting the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. Running tests under Python 3.10.11: /usr/local/bin/python3 [ RUN ] GceFailureHandlingTest.test_basic_run_test_inputarg_checkpoint_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 23708 I0510 05:25:05.386646 281473286435712 test_util.py:3796] Using local port 23708 INFO:tensorflow:Using local port 23434 I0510 05:25:05.387284 281473286435712 test_util.py:3796] Using local port 23434 INFO:tensorflow:Using local port 18260 I0510 05:25:05.387706 281473286435712 test_util.py:3796] Using local port 18260 INFO:tensorflow:Using local port 23641 I0510 05:25:05.388114 281473286435712 test_util.py:3796] Using local port 23641 2023-05-10 05:25:07.107668: I tensorflow/core/util/port.cc:116] Experimental oneDNN custom operations are on. If you experience issues, please turn them off by setting the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2023-05-10 05:25:07.117790: I tensorflow/core/util/port.cc:116] Experimental oneDNN custom operations are on. If you experience issues, please turn them off by setting the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. INFO:tensorflow:Cluster starting. I0510 05:25:09.630074 281473286435712 gce_failure_handler_test.py:317] Cluster starting. [worker-0]: I0510 05:25:09.687593 281473111126912 multi_process_runner.py:840] Subprocess with PID 1718477 (worker, 0) is now being started. [worker-0]: I0510 05:25:09.687953 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23708", "localhost:23434", "localhost:18260", "localhost:23641"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0510 05:25:09.694222 281473111126912 multi_process_runner.py:840] Subprocess with PID 1718502 (worker, 1) is now being started. [worker-1]: I0510 05:25:09.694605 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23708", "localhost:23434", "localhost:18260", "localhost:23641"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:25:09.705501 281473111126912 multi_process_runner.py:840] Subprocess with PID 1718689 (worker, 2) is now being started. [worker-2]: I0510 05:25:09.705882 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23708", "localhost:23434", "localhost:18260", "localhost:23641"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-1]: E0510 05:25:09.775194541 1718502 server_chttp2.cc:40] {"created":"@1683696309.775077124","description":"No address added out of total 1 resolved","file":"external/com_github_grpc_grpc/src/core/ext/transport/chttp2/server/chttp2_server.cc","file_line":395,"referenced_errors":[{"created":"@1683696309.775072458","description":"Failed to add any wildcard listeners","file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_posix.cc","file_line":341,"referenced_errors":[{"created":"@1683696309.775043700","description":"Unable to configure socket","fd":9,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":215,"referenced_errors":[{"created":"@1683696309.775026989","description":"Address already in use","errno":98,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":189,"os_error":"Address already in use","syscall":"bind"}]},{"created":"@1683696309.775071368","description":"Unable to configure socket","fd":9,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":215,"referenced_errors":[{"created":"@1683696309.775062747","description":"Address already in use","errno":98,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":189,"os_error":"Address already in use","syscall":"bind"}]}]}]} [worker-1]: 2023-05-10 05:25:09.775312: E tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:600] UNKNOWN: Could not start gRPC server [worker-1]: 2023-05-10 05:25:09.776945: E tensorflow/core/common_runtime/eager/context_distributed_manager.cc:699] Could not start gRPC server [worker-2]: 2023-05-10 05:25:09.876859: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:18260 [worker-0]: 2023-05-10 05:25:09.919462: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:23708 [worker-0]: 2023-05-10 05:25:09.921954: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 18211276433599916259 [worker-2]: 2023-05-10 05:25:09.936336: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: 2023-05-10 05:25:09.936397: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 9193772063857403895 [worker-0]: 2023-05-10 05:25:09.936768: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: I0510 05:25:09.967621 281473111126912 multi_process_runner.py:840] Subprocess with PID 1718993 (worker, 3) is now being started. [worker-3]: I0510 05:25:09.967991 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23708", "localhost:23434", "localhost:18260", "localhost:23641"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-1]: Process _Process-3: [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap [worker-1]: self.run() [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-1]: return self._actual_run() [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in _run_with_absl [worker-1]: app.run(lambda _: self._run_impl()) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 312, in run [worker-1]: _run_main(main, args) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 258, in _run_main [worker-1]: sys.exit(main(argv)) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in [worker-1]: app.run(lambda _: self._run_impl()) [worker-1]: File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run [worker-1]: self._target(*self._args, **self._kwargs) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 866, in __call__ [worker-1]: six.reraise(*info.exc_info) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise [worker-1]: raise value [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained [worker-1]: return_value = fn(*args, **kwargs) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 134, in worker_fn [worker-1]: strategy = collective_all_reduce_strategy.CollectiveAllReduceStrategy() [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 186, in __init__ [worker-1]: CollectiveAllReduceExtended( [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 339, in __init__ [worker-1]: self._initialize_strategy(self._cluster_resolver, devices=devices) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 358, in _initialize_strategy [worker-1]: self._initialize_multi_worker(cluster_resolver) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 530, in _initialize_multi_worker [worker-1]: context.context().ensure_initialized() [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/eager/context.py", line 610, in ensure_initialized [worker-1]: pywrap_tfe.TFE_EnableCollectiveOps(context_handle, server_def_str) [worker-1]: tensorflow.python.framework.errors_impl.UnknownError: Could not start gRPC server [worker-3]: 2023-05-10 05:25:10.217165: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:23641 [worker-0]: 2023-05-10 05:25:10.228686: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 15785656182227291662 [worker-3]: 2023-05-10 05:25:10.229460: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. INFO:tensorflow:restarting workers I0510 05:25:39.877156 281473286435712 gce_failure_handler_test.py:323] restarting workers INFO:tensorflow:workers restarted I0510 05:25:39.907813 281473286435712 gce_failure_handler_test.py:327] workers restarted [worker-0]: I0510 05:25:39.968122 281473111126912 multi_process_runner.py:840] Subprocess with PID 1775232 (worker, 0) is now being started. [worker-1]: I0510 05:25:39.995601 281473111126912 multi_process_runner.py:840] Subprocess with PID 1775235 (worker, 1) is now being started. [worker-0]: I0510 05:25:39.968499 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23708", "localhost:23434", "localhost:18260", "localhost:23641"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0510 05:25:39.996195 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23708", "localhost:23434", "localhost:18260", "localhost:23641"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:25:40.001947 281473111126912 multi_process_runner.py:840] Subprocess with PID 1775250 (worker, 2) is now being started. [worker-2]: I0510 05:25:40.002520 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23708", "localhost:23434", "localhost:18260", "localhost:23641"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0510 05:25:40.032212 281473111126912 multi_process_runner.py:840] Subprocess with PID 1775266 (worker, 3) is now being started. [worker-3]: I0510 05:25:40.032758 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23708", "localhost:23434", "localhost:18260", "localhost:23641"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: E0510 05:25:40.091324952 1775250 server_chttp2.cc:40] {"created":"@1683696340.091201700","description":"No address added out of total 1 resolved","file":"external/com_github_grpc_grpc/src/core/ext/transport/chttp2/server/chttp2_server.cc","file_line":395,"referenced_errors":[{"created":"@1683696340.091195644","description":"Failed to add any wildcard listeners","file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_posix.cc","file_line":341,"referenced_errors":[{"created":"@1683696340.091162885","description":"Unable to configure socket","fd":9,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":215,"referenced_errors":[{"created":"@1683696340.091144519","description":"Address already in use","errno":98,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":189,"os_error":"Address already in use","syscall":"bind"}]},{"created":"@1683696340.091194499","description":"Unable to configure socket","fd":9,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":215,"referenced_errors":[{"created":"@1683696340.091185198","description":"Address already in use","errno":98,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":189,"os_error":"Address already in use","syscall":"bind"}]}]}]} [worker-2]: 2023-05-10 05:25:40.091485: E tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:600] UNKNOWN: Could not start gRPC server [worker-2]: 2023-05-10 05:25:40.096628: E tensorflow/core/common_runtime/eager/context_distributed_manager.cc:699] Could not start gRPC server [worker-0]: E0510 05:25:40.102390011 1775232 server_chttp2.cc:40] {"created":"@1683696340.102267063","description":"No address added out of total 1 resolved","file":"external/com_github_grpc_grpc/src/core/ext/transport/chttp2/server/chttp2_server.cc","file_line":395,"referenced_errors":[{"created":"@1683696340.102261098","description":"Failed to add any wildcard listeners","file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_posix.cc","file_line":341,"referenced_errors":[{"created":"@1683696340.102227944","description":"Unable to configure socket","fd":9,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":215,"referenced_errors":[{"created":"@1683696340.102208887","description":"Address already in use","errno":98,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":189,"os_error":"Address already in use","syscall":"bind"}]},{"created":"@1683696340.102259708","description":"Unable to configure socket","fd":9,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":215,"referenced_errors":[{"created":"@1683696340.102251057","description":"Address already in use","errno":98,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":189,"os_error":"Address already in use","syscall":"bind"}]}]}]} [worker-0]: 2023-05-10 05:25:40.102544: E tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:600] UNKNOWN: Could not start gRPC server [worker-3]: E0510 05:25:40.165602184 1775266 server_chttp2.cc:40] {"created":"@1683696340.136793623","description":"No address added out of total 1 resolved","file":"external/com_github_grpc_grpc/src/core/ext/transport/chttp2/server/chttp2_server.cc","file_line":395,"referenced_errors":[{"created":"@1683696340.136785742","description":"Failed to add any wildcard listeners","file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_posix.cc","file_line":341,"referenced_errors":[{"created":"@1683696340.136691908","description":"Unable to configure socket","fd":9,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":215,"referenced_errors":[{"created":"@1683696340.056341515","description":"Address already in use","errno":98,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":189,"os_error":"Address already in use","syscall":"bind"}]},{"created":"@1683696340.136784632","description":"Unable to configure socket","fd":9,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":215,"referenced_errors":[{"created":"@1683696340.136771516","description":"Address already in use","errno":98,"file":"external/com_github_grpc_grpc/src/core/lib/iomgr/tcp_server_utils_posix_common.cc","file_line":189,"os_error":"Address already in use","syscall":"bind"}]}]}]} [worker-0]: 2023-05-10 05:25:40.166338: E tensorflow/core/common_runtime/eager/context_distributed_manager.cc:699] Could not start gRPC server [worker-3]: 2023-05-10 05:25:40.165823: E tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:600] UNKNOWN: Could not start gRPC server [worker-3]: 2023-05-10 05:25:40.166998: E tensorflow/core/common_runtime/eager/context_distributed_manager.cc:699] Could not start gRPC server [worker-0]: Process _Process-6: [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap [worker-0]: self.run() [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-0]: return self._actual_run() [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in _run_with_absl [worker-0]: app.run(lambda _: self._run_impl()) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 312, in run [worker-0]: _run_main(main, args) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 258, in _run_main [worker-0]: sys.exit(main(argv)) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in [worker-0]: app.run(lambda _: self._run_impl()) [worker-0]: File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run [worker-0]: self._target(*self._args, **self._kwargs) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 866, in __call__ [worker-0]: six.reraise(*info.exc_info) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise [worker-0]: raise value [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained [worker-0]: return_value = fn(*args, **kwargs) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 134, in worker_fn [worker-0]: strategy = collective_all_reduce_strategy.CollectiveAllReduceStrategy() [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 186, in __init__ [worker-0]: CollectiveAllReduceExtended( [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 339, in __init__ [worker-0]: self._initialize_strategy(self._cluster_resolver, devices=devices) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 358, in _initialize_strategy [worker-2]: Process _Process-8: [worker-0]: self._initialize_multi_worker(cluster_resolver) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 530, in _initialize_multi_worker [worker-0]: context.context().ensure_initialized() [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/eager/context.py", line 610, in ensure_initialized [worker-0]: pywrap_tfe.TFE_EnableCollectiveOps(context_handle, server_def_str) [worker-0]: tensorflow.python.framework.errors_impl.UnknownError: Could not start gRPC server [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap [worker-2]: self.run() [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-2]: return self._actual_run() [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in _run_with_absl [worker-2]: app.run(lambda _: self._run_impl()) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 312, in run [worker-2]: _run_main(main, args) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 258, in _run_main [worker-2]: sys.exit(main(argv)) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in [worker-2]: app.run(lambda _: self._run_impl()) [worker-2]: File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 866, in __call__ [worker-2]: six.reraise(*info.exc_info) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise [worker-2]: raise value [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained [worker-2]: return_value = fn(*args, **kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 134, in worker_fn [worker-2]: strategy = collective_all_reduce_strategy.CollectiveAllReduceStrategy() [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 186, in __init__ [worker-2]: CollectiveAllReduceExtended( [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 339, in __init__ [worker-2]: self._initialize_strategy(self._cluster_resolver, devices=devices) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 358, in _initialize_strategy [worker-2]: self._initialize_multi_worker(cluster_resolver) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 530, in _initialize_multi_worker [worker-2]: context.context().ensure_initialized() [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/eager/context.py", line 610, in ensure_initialized [worker-2]: pywrap_tfe.TFE_EnableCollectiveOps(context_handle, server_def_str) [worker-2]: tensorflow.python.framework.errors_impl.UnknownError: Could not start gRPC server [worker-3]: Process _Process-9: [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap [worker-3]: self.run() [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-3]: return self._actual_run() [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in _run_with_absl [worker-3]: app.run(lambda _: self._run_impl()) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 312, in run [worker-3]: _run_main(main, args) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 258, in _run_main [worker-3]: sys.exit(main(argv)) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in [worker-3]: app.run(lambda _: self._run_impl()) [worker-3]: File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 866, in __call__ [worker-3]: six.reraise(*info.exc_info) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise [worker-3]: raise value [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained [worker-3]: return_value = fn(*args, **kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 134, in worker_fn [worker-3]: strategy = collective_all_reduce_strategy.CollectiveAllReduceStrategy() [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 186, in __init__ [worker-3]: CollectiveAllReduceExtended( [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 339, in __init__ [worker-3]: self._initialize_strategy(self._cluster_resolver, devices=devices) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 358, in _initialize_strategy [worker-3]: self._initialize_multi_worker(cluster_resolver) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/collective_all_reduce_strategy.py", line 530, in _initialize_multi_worker [worker-3]: context.context().ensure_initialized() [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/eager/context.py", line 610, in ensure_initialized [worker-3]: pywrap_tfe.TFE_EnableCollectiveOps(context_handle, server_def_str) [worker-3]: tensorflow.python.framework.errors_impl.UnknownError: Could not start gRPC server [worker-1]: 2023-05-10 05:25:40.538023: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:23434 [worker-0]: 2023-05-10 05:25:40.606313: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 2660229745796522063 [worker-1]: 2023-05-10 05:25:40.607238: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:25:40.618821 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:25:40.620234 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-2]: I0510 05:25:40.637577 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: I0510 05:25:40.627034 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: I0510 05:25:40.691297 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-0]: I0510 05:25:40.691745 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23708', 'localhost:23434', 'localhost:18260', 'localhost:23641']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:25:40.691950 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23708', 'localhost:23434', 'localhost:18260', 'localhost:23641']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:25:40.748979 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:25:40.749420 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23708', 'localhost:23434', 'localhost:18260', 'localhost:23641']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:25:40.749614 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23708', 'localhost:23434', 'localhost:18260', 'localhost:23641']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:25:40.758443 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:25:40.758910 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23708', 'localhost:23434', 'localhost:18260', 'localhost:23641']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0510 05:25:40.759111 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23708', 'localhost:23434', 'localhost:18260', 'localhost:23641']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0510 05:25:40.761971 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: INFO:tensorflow:Check health not enabled. [worker-1]: I0510 05:25:40.762405 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23708', 'localhost:23434', 'localhost:18260', 'localhost:23641']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:25:40.762602 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23708', 'localhost:23434', 'localhost:18260', 'localhost:23641']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0510 05:25:40.902286 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0510 05:25:40.903432 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0510 05:25:40.904983 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:25:40.908665 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:25:40.910480 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: I0510 05:25:40.910630 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0510 05:25:40.911025 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: I0510 05:25:40.911422 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: Instructions for updating: [worker-1]: I0510 05:25:40.911877 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: W0510 05:25:40.911408 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-0]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: W0510 05:25:40.912230 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: INFO:tensorflow:Start training at 0 [worker-1]: Instructions for updating: [worker-0]: I0510 05:25:40.911605 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: INFO:tensorflow:Start training at 0 [worker-1]: I0510 05:25:40.912426 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0510 05:25:40.916831 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: INFO:tensorflow:['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-0]: I0510 05:25:40.918671 281473111126912 gce_failure_handler_test.py:203] ['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-1]: INFO:tensorflow:['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-1]: I0510 05:25:40.918838 281473111126912 gce_failure_handler_test.py:203] ['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0510 05:25:40.926423 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: W0510 05:25:40.927013 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start training at 0 [worker-3]: I0510 05:25:40.927243 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: INFO:tensorflow:['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-3]: I0510 05:25:40.932125 281473111126912 gce_failure_handler_test.py:203] ['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-1]: Process _Process-7: [worker-1]: Traceback (most recent call last): [worker-0]: Process _Process-2: [worker-1]: File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap [worker-1]: self.run() [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-1]: return self._actual_run() [worker-0]: Traceback (most recent call last): [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in _run_with_absl [worker-0]: File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap [worker-1]: app.run(lambda _: self._run_impl()) [worker-0]: self.run() [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 312, in run [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-1]: _run_main(main, args) [worker-0]: return self._actual_run() [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 258, in _run_main [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in _run_with_absl [worker-1]: sys.exit(main(argv)) [worker-0]: app.run(lambda _: self._run_impl()) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 312, in run [worker-1]: app.run(lambda _: self._run_impl()) [worker-0]: _run_main(main, args) [worker-1]: File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 258, in _run_main [worker-1]: self._target(*self._args, **self._kwargs) [worker-0]: sys.exit(main(argv)) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 866, in __call__ [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in [worker-1]: six.reraise(*info.exc_info) [worker-0]: app.run(lambda _: self._run_impl()) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise [worker-0]: File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run [worker-1]: raise value [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained [worker-0]: self._target(*self._args, **self._kwargs) [worker-1]: return_value = fn(*args, **kwargs) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 866, in __call__ [worker-3]: Process _Process-5: [worker-0]: six.reraise(*info.exc_info) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 211, in worker_fn [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise [worker-1]: self.assertNotEmpty(checkpoint_index) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 972, in assertNotEmpty [worker-0]: raise value [worker-1]: self.fail('{!r} has length of 0.'.format(container), msg) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 1814, in fail [worker-1]: return super(TestCase, self).fail(self._formatMessage(prefix, msg)) [worker-1]: File "/usr/lib/python3.10/unittest/case.py", line 675, in fail [worker-0]: return_value = fn(*args, **kwargs) [worker-1]: raise self.failureException(msg) [worker-1]: AssertionError: [] has length of 0. [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 211, in worker_fn [worker-3]: Traceback (most recent call last): [worker-0]: self.assertNotEmpty(checkpoint_index) [worker-3]: File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 972, in assertNotEmpty [worker-3]: self.run() [worker-0]: self.fail('{!r} has length of 0.'.format(container), msg) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 1814, in fail [worker-3]: return self._actual_run() [worker-0]: return super(TestCase, self).fail(self._formatMessage(prefix, msg)) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in _run_with_absl [worker-0]: File "/usr/lib/python3.10/unittest/case.py", line 675, in fail [worker-3]: app.run(lambda _: self._run_impl()) [worker-0]: raise self.failureException(msg) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 312, in run [worker-0]: AssertionError: [] has length of 0. [worker-3]: _run_main(main, args) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 258, in _run_main [worker-3]: sys.exit(main(argv)) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in [worker-3]: app.run(lambda _: self._run_impl()) [worker-3]: File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 866, in __call__ [worker-3]: six.reraise(*info.exc_info) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise [worker-3]: raise value [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained [worker-3]: return_value = fn(*args, **kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 211, in worker_fn [worker-3]: self.assertNotEmpty(checkpoint_index) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 972, in assertNotEmpty [worker-3]: self.fail('{!r} has length of 0.'.format(container), msg) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 1814, in fail [worker-3]: return super(TestCase, self).fail(self._formatMessage(prefix, msg)) [worker-3]: File "/usr/lib/python3.10/unittest/case.py", line 675, in fail [worker-3]: raise self.failureException(msg) [worker-3]: AssertionError: [] has length of 0. [worker-2]: Exception in thread PeerTerminationWatcher-2: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 1229, in _watch_step_to_save_key [worker-2]: step_value = context.context().get_config_key_value(_INITIAL_RUN_COUNT_KEY) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/eager/context.py", line 806, in get_config_key_value [worker-2]: pywrap_tfe.TFE_GetConfigKeyValue(self._context_handle, key, [worker-2]: tensorflow.python.framework.errors_impl.UnavailableError: Socket closed [worker-2]: Additional GRPC error information from remote target /job:worker/replica:0/task:0: [worker-2]: :{"created":"@1683696340.961792646","description":"Error received from peer ipv6:[::1]:23708","file":"external/com_github_grpc_grpc/src/core/lib/surface/call.cc","file_line":1056,"grpc_message":"Socket closed","grpc_status":14} [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0510 05:25:40.964263 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: W0510 05:25:40.964615 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:25:40.964786 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-2]: I0510 05:25:40.967700 281473111126912 gce_failure_handler_test.py:203] ['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-2]: Process _Process-4: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap [worker-2]: self.run() [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-2]: return self._actual_run() [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in _run_with_absl [worker-2]: app.run(lambda _: self._run_impl()) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 312, in run [worker-2]: _run_main(main, args) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/app.py", line 258, in _run_main [worker-2]: sys.exit(main(argv)) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_lib.py", line 54, in [worker-2]: app.run(lambda _: self._run_impl()) [worker-2]: File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 866, in __call__ [worker-2]: six.reraise(*info.exc_info) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise [worker-2]: raise value [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained [worker-2]: return_value = fn(*args, **kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 211, in worker_fn [worker-2]: self.assertNotEmpty(checkpoint_index) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 972, in assertNotEmpty [worker-2]: self.fail('{!r} has length of 0.'.format(container), msg) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 1814, in fail [worker-2]: return super(TestCase, self).fail(self._formatMessage(prefix, msg)) [worker-2]: File "/usr/lib/python3.10/unittest/case.py", line 675, in fail [worker-2]: raise self.failureException(msg) [worker-2]: AssertionError: [] has length of 0. I0510 05:25:41.816287 281473286435712 multi_process_runner.py:646] worker-0 exit code: 1 I0510 05:25:41.816597 281473286435712 multi_process_runner.py:646] worker-1 exit code: 1 I0510 05:25:41.816748 281473286435712 multi_process_runner.py:646] worker-2 exit code: 1 I0510 05:25:41.816879 281473286435712 multi_process_runner.py:646] worker-3 exit code: 1 INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_basic_run_test_inputarg_checkpoint_strategyoption_MWMSmultiworker): 36.53s I0510 05:25:41.913561 281473286435712 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_basic_run_test_inputarg_checkpoint_strategyoption_MWMSmultiworker): 36.53s [ FAILED ] GceFailureHandlingTest.test_basic_run_test_inputarg_checkpoint_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_False_inputarg_checkpoint_strategyoption_MWMSmultiworker INFO:tensorflow:Using MirroredStrategy with devices ('/device:CPU:0',) I0510 05:25:42.163141 281473286435712 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/device:CPU:0',) INFO:tensorflow:Single-worker MultiWorkerMirroredStrategy with local_devices = ('/device:CPU:0',), communication = CommunicationImplementation.AUTO I0510 05:25:42.163670 281473286435712 collective_all_reduce_strategy.py:446] Single-worker MultiWorkerMirroredStrategy with local_devices = ('/device:CPU:0',), communication = CommunicationImplementation.AUTO INFO:tensorflow:Start polling for termination signal. I0510 05:25:42.241611 281473286435712 failure_handling.py:683] Start polling for termination signal. INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. I0510 05:25:42.242185 281473286435712 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. Instructions for updating: Track steps using a tf.Variable saved in checkpoint instead. W0510 05:25:42.242470 281473286435712 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. Instructions for updating: Track steps using a tf.Variable saved in checkpoint instead. INFO:tensorflow:Start training at 0 I0510 05:25:42.242661 281473286435712 gce_failure_handler_test.py:194] Start training at 0 WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xfffeeedfde10> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. W0510 05:25:42.648000 281473286435712 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xfffeeedfde10> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xfffeeedfe5f0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. W0510 05:25:42.675985 281473286435712 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xfffeeedfe5f0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. INFO:tensorflow:epoch 0 finished I0510 05:25:42.676472 281473286435712 gce_failure_handler_test.py:192] epoch 0 finished INFO:tensorflow:epoch 1 finished I0510 05:25:43.017144 281473286435712 gce_failure_handler_test.py:192] epoch 1 finished INFO:tensorflow:epoch 2 finished I0510 05:25:43.177689 281473286435712 gce_failure_handler_test.py:192] epoch 2 finished INFO:tensorflow:epoch 3 finished I0510 05:25:43.418318 281473286435712 gce_failure_handler_test.py:192] epoch 3 finished INFO:tensorflow:epoch 4 finished I0510 05:25:43.630333 281473286435712 gce_failure_handler_test.py:192] epoch 4 finished INFO:tensorflow:Training finished. I0510 05:25:43.630695 281473286435712 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_False_inputarg_checkpoint_strategyoption_MWMSmultiworker): 1.73s I0510 05:25:43.645787 281473286435712 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_False_inputarg_checkpoint_strategyoption_MWMSmultiworker): 1.73s [ OK ] GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_False_inputarg_checkpoint_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_True_inputarg_checkpoint_strategyoption_MWMSmultiworker INFO:tensorflow:Using MirroredStrategy with devices ('/device:CPU:0',) I0510 05:25:43.659377 281473286435712 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/device:CPU:0',) INFO:tensorflow:Single-worker MultiWorkerMirroredStrategy with local_devices = ('/device:CPU:0',), communication = CommunicationImplementation.AUTO I0510 05:25:43.659821 281473286435712 collective_all_reduce_strategy.py:446] Single-worker MultiWorkerMirroredStrategy with local_devices = ('/device:CPU:0',), communication = CommunicationImplementation.AUTO INFO:tensorflow:Start polling for termination signal. I0510 05:25:43.677688 281473286435712 failure_handling.py:683] Start polling for termination signal. INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. I0510 05:25:43.678287 281473286435712 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. INFO:tensorflow:Start training at 0 I0510 05:25:43.678556 281473286435712 gce_failure_handler_test.py:194] Start training at 0 INFO:tensorflow:epoch 0 finished I0510 05:25:43.854469 281473286435712 gce_failure_handler_test.py:192] epoch 0 finished INFO:tensorflow:epoch 1 finished I0510 05:25:44.055441 281473286435712 gce_failure_handler_test.py:192] epoch 1 finished INFO:tensorflow:epoch 2 finished I0510 05:25:44.263842 281473286435712 gce_failure_handler_test.py:192] epoch 2 finished INFO:tensorflow:epoch 3 finished I0510 05:25:44.496697 281473286435712 gce_failure_handler_test.py:192] epoch 3 finished INFO:tensorflow:epoch 4 finished I0510 05:25:44.684642 281473286435712 gce_failure_handler_test.py:192] epoch 4 finished INFO:tensorflow:Training finished. I0510 05:25:44.685042 281473286435712 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_True_inputarg_checkpoint_strategyoption_MWMSmultiworker): 1.04s I0510 05:25:44.691127 281473286435712 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_True_inputarg_checkpoint_strategyoption_MWMSmultiworker): 1.04s [ OK ] GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_True_inputarg_checkpoint_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_0_inputarg_checkpoint_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 20543 I0510 05:25:44.696424 281473286435712 test_util.py:3796] Using local port 20543 INFO:tensorflow:Using local port 24657 I0510 05:25:44.697163 281473286435712 test_util.py:3796] Using local port 24657 INFO:tensorflow:Using local port 16468 I0510 05:25:44.697718 281473286435712 test_util.py:3796] Using local port 16468 INFO:tensorflow:Using local port 16446 I0510 05:25:44.698206 281473286435712 test_util.py:3796] Using local port 16446 INFO:tensorflow:Cluster starting. I0510 05:25:44.897697 281473286435712 gce_failure_handler_test.py:405] Cluster starting. [worker-0]: I0510 05:25:45.016747 281473111126912 multi_process_runner.py:840] Subprocess with PID 1782763 (worker, 0) is now being started. [worker-1]: I0510 05:25:45.018354 281473111126912 multi_process_runner.py:840] Subprocess with PID 1782772 (worker, 1) is now being started. [worker-0]: I0510 05:25:45.017241 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:20543", "localhost:24657", "localhost:16468", "localhost:16446"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0510 05:25:45.018801 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:20543", "localhost:24657", "localhost:16468", "localhost:16446"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:25:45.228072 281473111126912 multi_process_runner.py:840] Subprocess with PID 1782778 (worker, 2) is now being started. [worker-2]: I0510 05:25:45.228549 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:20543", "localhost:24657", "localhost:16468", "localhost:16446"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0510 05:25:45.307683 281473111126912 multi_process_runner.py:840] Subprocess with PID 1782795 (worker, 3) is now being started. [worker-3]: I0510 05:25:45.308139 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:20543", "localhost:24657", "localhost:16468", "localhost:16446"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-0]: 2023-05-10 05:25:45.327053: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:20543 [worker-0]: 2023-05-10 05:25:45.364510: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 8406984705604939634 [worker-0]: 2023-05-10 05:25:45.364821: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-1]: 2023-05-10 05:25:45.446925: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:24657 [worker-0]: 2023-05-10 05:25:45.459817: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 60544514795841224 [worker-1]: 2023-05-10 05:25:45.460751: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: 2023-05-10 05:25:45.489713: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:16468 [worker-0]: 2023-05-10 05:25:45.505847: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 10552456952116294028 [worker-2]: 2023-05-10 05:25:45.513116: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: 2023-05-10 05:25:45.547504: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:16446 [worker-0]: 2023-05-10 05:25:45.566955: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 16220111110755230675 [worker-3]: 2023-05-10 05:25:45.581128: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-3]: I0510 05:25:45.584021 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:25:45.587490 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:25:45.587741 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: I0510 05:25:45.606152 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:25:45.663707 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:25:45.664510 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:25:45.664776 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: I0510 05:25:45.667158 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-0]: I0510 05:25:45.667862 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:25:45.668096 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0510 05:25:45.679062 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: INFO:tensorflow:Check health not enabled. [worker-1]: I0510 05:25:45.679769 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:25:45.679982 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:25:45.711587 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:25:45.712138 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0510 05:25:45.712410 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:25:46.068935 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0510 05:25:46.081441 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0510 05:25:46.096734 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: if self._termination_watcher_fn(): [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0510 05:25:46.116197 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: W0510 05:25:46.116632 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start training at 0 [worker-3]: I0510 05:25:46.116841 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0510 05:25:46.106448 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-2]: I0510 05:25:46.123785 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: self._target(*self._args, **self._kwargs) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0510 05:25:46.126488 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0510 05:25:46.136887 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: I0510 05:25:46.109651 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: W0510 05:25:46.110013 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: INFO:tensorflow:Start training at 0 [worker-0]: I0510 05:25:46.110201 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: if self._termination_watcher_fn(): [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-2]: if self._termination_watcher_fn(): [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0510 05:25:46.166418 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0510 05:25:46.166243 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: W0510 05:25:46.166872 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:25:46.167088 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-1]: self._target(*self._args, **self._kwargs) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: if self._termination_watcher_fn(): [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0510 05:25:46.206345 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: W0510 05:25:46.206765 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: INFO:tensorflow:Start training at 0 [worker-1]: I0510 05:25:46.206949 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:46.339024 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:46.463608 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:46.459199 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:46.535571 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:46.701177 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:46.702104 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:46.711010 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:46.701018 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:46.881139 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:46.881109 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:46.900892 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:46.907207 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:47.070170 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:47.061103 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:47.092830 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:47.137256 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:47.278181 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:47.291043 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:47.281161 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:47.321479 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:25:47.399622 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:25:47.405707 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:25:47.407924 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:25:47.421536 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:47.421279 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:47.430909 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:47.440905 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:47.527201 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:25:47.601822 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:25:47.608681 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:25:47.595107 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:epoch 0 finished [worker-0]: INFO:tensorflow:epoch 0 finished [worker-3]: INFO:tensorflow:epoch 0 finished [worker-1]: I0510 05:25:47.609122 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: I0510 05:25:47.602260 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: I0510 05:25:47.595560 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:25:47.617480 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:epoch 0 finished [worker-2]: I0510 05:25:47.617927 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:47.632512 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:47.631274 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:47.632743 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:47.667113 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:47.750523 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:47.754624 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:47.761408 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:47.751356 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:47.881404 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:47.901335 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:47.901335 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:47.911225 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:48.011004 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:48.020745 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:48.025109 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:48.061182 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:48.181144 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:48.211755 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:48.227186 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:48.247089 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:48.354271 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:48.363703 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:48.373804 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:48.402376 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0510 05:25:48.552762 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0510 05:25:48.560364 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0510 05:25:48.559069 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0510 05:25:48.565997 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:48.569052 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:48.591087 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:48.607468 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:48.607175 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:48.751039 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:48.751003 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:48.761677 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:48.771292 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:48.864741 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:48.864410 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:48.864885 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:48.865397 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:48.962730 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:48.956136 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:48.985329 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:48.991216 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:49.053659 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:49.053659 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:49.060014 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:49.088615 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:49.153209 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:49.171074 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:49.171277 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:49.188170 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 2 finished [worker-3]: I0510 05:25:49.248210 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-0]: I0510 05:25:49.248339 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:epoch 2 finished [worker-3]: I0510 05:25:49.257857 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:49.257831 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0510 05:25:49.266469 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:49.258906 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:49.289474 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:49.293047 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:49.361407 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:49.364889 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:49.368002 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:49.368618 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:49.432117 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:49.453454 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:49.460904 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:49.470901 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:49.542060 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:49.560923 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:49.560936 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:49.555655 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:49.650697 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:49.680569 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:49.680488 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:49.900859 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:50.085067 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:50.112226 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:50.142325 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:50.158000 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:epoch 3 finished [worker-0]: I0510 05:25:50.249865 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0510 05:25:50.256158 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: INFO:tensorflow:epoch 3 finished [worker-3]: I0510 05:25:50.256404 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0510 05:25:50.256727 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:50.359695 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:50.362396 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:50.398307 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:50.398830 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:50.478524 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:50.485670 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:50.489893 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:50.480710 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:50.562490 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:50.579345 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:50.589857 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:50.601039 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:50.673828 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:50.674953 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:50.691585 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:50.708813 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:50.776483 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:50.793546 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:50.776497 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:50.801151 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:50.866605 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:50.866470 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:50.891022 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:50.881101 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 4 finished [worker-3]: I0510 05:25:50.947105 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0510 05:25:50.947454 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-2]: INFO:tensorflow:epoch 4 finished [worker-0]: INFO:tensorflow:epoch 4 finished [worker-0]: I0510 05:25:50.976500 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0510 05:25:50.976869 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: I0510 05:25:50.967931 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0510 05:25:50.968309 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-2]: I0510 05:25:50.969173 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0510 05:25:50.969501 281473111126912 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:restarting workers I0510 05:25:53.036618 281473286435712 gce_failure_handler_test.py:411] restarting workers [worker-0]: I0510 05:25:53.099697 281473111126912 multi_process_runner.py:840] Subprocess with PID 1789942 (worker, 0) is now being started. [worker-0]: I0510 05:25:53.100142 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:20543", "localhost:24657", "localhost:16468", "localhost:16446"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' INFO:tensorflow:workers restarted I0510 05:25:53.151565 281473286435712 gce_failure_handler_test.py:415] workers restarted [worker-1]: I0510 05:25:53.188829 281473111126912 multi_process_runner.py:840] Subprocess with PID 1789951 (worker, 1) is now being started. [worker-1]: I0510 05:25:53.189266 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:20543", "localhost:24657", "localhost:16468", "localhost:16446"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:25:53.210695 281473111126912 multi_process_runner.py:840] Subprocess with PID 1790102 (worker, 2) is now being started. [worker-0]: 2023-05-10 05:25:53.236983: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:20543 [worker-2]: I0510 05:25:53.211138 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:20543", "localhost:24657", "localhost:16468", "localhost:16446"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-10 05:25:53.266174: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:24657 [worker-3]: I0510 05:25:53.273830 281473111126912 multi_process_runner.py:840] Subprocess with PID 1790172 (worker, 3) is now being started. [worker-3]: I0510 05:25:53.274262 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:20543", "localhost:24657", "localhost:16468", "localhost:16446"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-0]: 2023-05-10 05:25:53.387328: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 18148642584605490671 [worker-0]: 2023-05-10 05:25:53.396404: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: 2023-05-10 05:25:53.437926: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 7501905258720518793 [worker-1]: 2023-05-10 05:25:53.439403: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: 2023-05-10 05:25:53.494617: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:16446 [worker-0]: 2023-05-10 05:25:53.547986: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 4683545402158519288 [worker-3]: 2023-05-10 05:25:53.599992: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: 2023-05-10 05:25:53.826824: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:16468 [worker-0]: 2023-05-10 05:25:53.906776: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 9476732968811025784 [worker-2]: 2023-05-10 05:25:53.907735: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:25:53.914941 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-3]: I0510 05:25:53.920768 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:25:53.916664 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: I0510 05:25:53.928519 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:25:53.989446 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:25:53.990134 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:25:53.990341 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0510 05:25:54.011322 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: INFO:tensorflow:Check health not enabled. [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:25:54.006690 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:25:54.007404 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-2]: I0510 05:25:54.007627 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:25:54.012046 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:25:54.012277 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:25:54.016910 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-0]: I0510 05:25:54.018803 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:25:54.019036 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:20543', 'localhost:24657', 'localhost:16468', 'localhost:16446']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0510 05:25:54.168635 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0510 05:25:54.171075 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-2]: if self._termination_watcher_fn(): [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0510 05:25:54.172523 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: W0510 05:25:54.174980 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:25:54.175204 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:25:54.189689 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0510 05:25:54.186594 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0510 05:25:54.193471 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0510 05:25:54.194658 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: self.run() [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-1]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: I0510 05:25:54.196753 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: self._target(*self._args, **self._kwargs) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: if self._termination_watcher_fn(): [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0510 05:25:54.197268 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: W0510 05:25:54.197900 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: INFO:tensorflow:Start training at 0 [worker-1]: I0510 05:25:54.198181 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0510 05:25:54.207533 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-3]: I0510 05:25:54.208367 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: W0510 05:25:54.209063 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start training at 0 [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: I0510 05:25:54.209435 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: if self._termination_watcher_fn(): [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0510 05:25:54.216876 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: W0510 05:25:54.217347 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: INFO:tensorflow:Start training at 0 [worker-0]: I0510 05:25:54.217557 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: self._target(*self._args, **self._kwargs) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-0]: if self._termination_watcher_fn(): [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:54.302909 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:54.307524 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:54.370804 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:54.438764 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:54.536971 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:54.570806 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:54.560791 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:54.570800 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:54.679449 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:54.685738 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:54.687932 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:54.701032 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 INFO:tensorflow:Termination notice available. I0510 05:25:54.765539 281463484183008 gce_failure_handler_test.py:142] Termination notice available. INFO:tensorflow:Member single_worker has received termination notice. I0510 05:25:54.765931 281463484183008 failure_handling.py:701] Member single_worker has received termination notice. Exception ignored in: Traceback (most recent call last): File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 775, in __del__ self._stop_poll_termination_signal_thread() File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 734, in _stop_poll_termination_signal_thread self._poll_termination_signal_thread.join() File "/usr/lib/python3.10/threading.py", line 1093, in join raise RuntimeError("cannot join current thread") RuntimeError: cannot join current thread [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:54.799995 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:54.800196 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:54.820973 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:54.835425 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:54.907056 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:54.913106 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:54.921216 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:54.923142 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:25:55.006557 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:25:55.007064 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:25:55.016418 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:25:55.015473 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:55.031057 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:55.040864 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:55.040862 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:55.041064 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:25:55.154950 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:25:55.155390 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:epoch 0 finished [worker-3]: I0510 05:25:55.155787 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: INFO:tensorflow:epoch 0 finished [worker-0]: I0510 05:25:55.155356 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:25:55.155666 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:epoch 0 finished [worker-1]: I0510 05:25:55.156294 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:25:55.187109 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: INFO:tensorflow:epoch 0 finished [worker-2]: I0510 05:25:55.187501 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:55.180842 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:55.180826 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:55.180899 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:55.251499 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:55.531472 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:55.543093 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:55.550633 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:55.590396 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:55.700649 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:55.720429 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:55.710587 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:55.711375 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:55.829497 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:55.830498 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:55.830376 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:55.830533 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:55.951110 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:55.971446 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:55.992274 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:56.007737 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:56.118178 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:56.132397 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:56.142095 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:56.174713 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0510 05:25:56.334178 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-0]: I0510 05:25:56.337036 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: I0510 05:25:56.342617 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0510 05:25:56.376534 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: I0510 05:25:56.362015 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:56.370979 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:56.380468 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:56.430783 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:56.630478 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:56.640333 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:56.656077 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:56.722927 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:56.960822 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:56.980525 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:57.020398 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:57.027031 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:57.220331 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:57.210317 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:57.210334 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:57.250772 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:57.380617 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:57.400521 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:57.410694 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:57.420642 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:57.690912 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:57.681000 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:57.718379 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:57.721590 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-0]: I0510 05:25:57.883211 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: I0510 05:25:57.890001 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0510 05:25:57.897249 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: I0510 05:25:57.876866 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:57.901734 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:57.907215 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:57.911250 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:57.921526 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:58.055339 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:58.050365 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:58.050143 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:58.071253 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:58.179202 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:58.191429 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:58.196281 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:58.196306 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:58.280055 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:58.286726 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:58.280162 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:58.280145 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:58.411919 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:58.422621 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:58.448652 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:58.457489 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:58.613776 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:58.623785 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:58.623983 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:58.653694 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:epoch 3 finished [worker-0]: I0510 05:25:58.844348 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: INFO:tensorflow:epoch 3 finished [worker-3]: I0510 05:25:58.846459 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0510 05:25:58.851360 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0510 05:25:58.856647 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:59.090981 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:59.098966 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:59.122672 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:59.155446 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:59.261945 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:59.261951 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:59.273099 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:59.317329 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:59.403414 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:59.410881 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:59.433033 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:59.457291 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:59.569207 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:59.577412 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:59.587410 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:59.632080 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:59.801498 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:59.821443 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:25:59.821404 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:59.831510 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:25:59.971702 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:25:59.971701 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:25:59.991690 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:00.002189 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 4 finished [worker-0]: INFO:tensorflow:epoch 4 finished [worker-2]: INFO:tensorflow:epoch 4 finished [worker-1]: INFO:tensorflow:epoch 4 finished [worker-2]: I0510 05:26:00.169369 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: I0510 05:26:00.167354 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-2]: INFO:tensorflow:Training finished. [worker-1]: I0510 05:26:00.167729 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-2]: I0510 05:26:00.169731 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-0]: I0510 05:26:00.167785 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: I0510 05:26:00.166558 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0510 05:26:00.166986 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0510 05:26:00.168154 281473111126912 gce_failure_handler_test.py:244] Training finished. I0510 05:26:01.136831 281473286435712 multi_process_runner.py:646] worker-0 exit code: 0 I0510 05:26:01.137222 281473286435712 multi_process_runner.py:646] worker-1 exit code: 0 I0510 05:26:01.137429 281473286435712 multi_process_runner.py:646] worker-2 exit code: 0 I0510 05:26:01.137623 281473286435712 multi_process_runner.py:646] worker-3 exit code: 0 I0510 05:26:01.151059 281473286435712 multi_process_runner.py:662] Joining log reading threads. I0510 05:26:01.151492 281473286435712 multi_process_runner.py:665] Joined log reading threads. INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_0_inputarg_checkpoint_strategyoption_MWMSmultiworker): 16.72s I0510 05:26:01.412765 281473286435712 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_0_inputarg_checkpoint_strategyoption_MWMSmultiworker): 16.72s [ OK ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_0_inputarg_checkpoint_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_7_inputarg_checkpoint_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 17492 I0510 05:26:01.415165 281473286435712 test_util.py:3796] Using local port 17492 INFO:tensorflow:Using local port 20436 I0510 05:26:01.415862 281473286435712 test_util.py:3796] Using local port 20436 INFO:tensorflow:Using local port 21347 I0510 05:26:01.416505 281473286435712 test_util.py:3796] Using local port 21347 INFO:tensorflow:Using local port 20672 I0510 05:26:01.417126 281473286435712 test_util.py:3796] Using local port 20672 INFO:tensorflow:Cluster starting. I0510 05:26:01.757744 281473286435712 gce_failure_handler_test.py:405] Cluster starting. [worker-0]: I0510 05:26:01.928565 281473111126912 multi_process_runner.py:840] Subprocess with PID 1801586 (worker, 0) is now being started. [worker-1]: I0510 05:26:01.948176 281473111126912 multi_process_runner.py:840] Subprocess with PID 1801598 (worker, 1) is now being started. [worker-0]: I0510 05:26:01.929208 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:17492", "localhost:20436", "localhost:21347", "localhost:20672"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0510 05:26:01.948792 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:17492", "localhost:20436", "localhost:21347", "localhost:20672"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:26:02.135874 281473111126912 multi_process_runner.py:840] Subprocess with PID 1801616 (worker, 2) is now being started. [worker-2]: I0510 05:26:02.136557 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:17492", "localhost:20436", "localhost:21347", "localhost:20672"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0510 05:26:02.225197 281473111126912 multi_process_runner.py:840] Subprocess with PID 1801624 (worker, 3) is now being started. [worker-3]: I0510 05:26:02.225840 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:17492", "localhost:20436", "localhost:21347", "localhost:20672"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: 2023-05-10 05:26:02.290944: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:21347 [worker-3]: 2023-05-10 05:26:02.367490: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:20672 [worker-1]: 2023-05-10 05:26:02.383951: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:20436 [worker-0]: 2023-05-10 05:26:02.396734: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:17492 [worker-0]: 2023-05-10 05:26:02.447761: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 12190489595689826008 [worker-0]: 2023-05-10 05:26:02.451411: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 14069653817293269742 [worker-0]: 2023-05-10 05:26:02.451689: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 7893041504352665176 [worker-2]: 2023-05-10 05:26:02.452151: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: 2023-05-10 05:26:02.452078: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-1]: 2023-05-10 05:26:02.448241: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: 2023-05-10 05:26:02.463781: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 17536176123223847881 [worker-0]: 2023-05-10 05:26:02.464874: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: I0510 05:26:02.469197 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:26:02.468541 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-3]: I0510 05:26:02.486735 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:26:02.507832 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: I0510 05:26:02.549022 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-0]: I0510 05:26:02.549993 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:26:02.550320 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:26:02.549173 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:26:02.550029 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0510 05:26:02.550352 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:26:02.599913 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:26:02.601902 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:26:02.602253 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0510 05:26:02.632212 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: INFO:tensorflow:Check health not enabled. [worker-1]: I0510 05:26:02.632839 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:26:02.633184 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:26:02.767863 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0510 05:26:02.781390 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0510 05:26:02.787229 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0510 05:26:02.800468 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0510 05:26:02.801320 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0510 05:26:02.803610 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0510 05:26:02.811939 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0510 05:26:02.815946 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-0]: Traceback (most recent call last): [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-3]: Traceback (most recent call last): [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-3]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: Traceback (most recent call last): [worker-1]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-1]: self.run() [worker-0]: self._target(*self._args, **self._kwargs) [worker-1]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: self._target(*self._args, **self._kwargs) [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-0]: if self._termination_watcher_fn(): [worker-2]: self.run() [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-1]: if self._termination_watcher_fn(): [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: self._target(*self._args, **self._kwargs) [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0510 05:26:02.825694 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: Instructions for updating: [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: if self._termination_watcher_fn(): [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: W0510 05:26:02.826457 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-0]: I0510 05:26:02.816199 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:Start training at 0 [worker-0]: Instructions for updating: [worker-1]: I0510 05:26:02.826774 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: if self._termination_watcher_fn(): [worker-3]: I0510 05:26:02.824473 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: W0510 05:26:02.816681 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: W0510 05:26:02.825015 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start training at 0 [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: I0510 05:26:02.825294 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: INFO:tensorflow:Start training at 0 [worker-0]: I0510 05:26:02.816944 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0510 05:26:02.828362 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: W0510 05:26:02.828847 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:26:02.829112 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:03.003671 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:03.004173 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:03.050253 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:03.073542 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:03.254114 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:03.262813 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:03.271977 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:03.291515 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:03.457645 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:03.443904 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:03.444186 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:03.444959 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:03.552288 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:03.568133 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:03.571386 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:03.587846 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:03.711640 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:03.719772 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:03.731304 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:03.751557 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:03.872228 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:03.884676 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:03.887377 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:03.888455 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:03.886615 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:03.901042 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:03.899848 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:03.899609 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:03.970106 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:epoch 0 finished [worker-0]: I0510 05:26:03.970649 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:03.970242 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:epoch 0 finished [worker-1]: I0510 05:26:03.970755 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:03.977588 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: INFO:tensorflow:epoch 0 finished [worker-2]: I0510 05:26:03.978107 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:03.983047 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:03.986778 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:epoch 0 finished [worker-3]: I0510 05:26:03.987472 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:03.989804 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:03.997656 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:04.033273 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:04.185320 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:04.185410 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:04.192414 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:04.189866 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:04.322472 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:04.331674 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:04.330583 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:04.352479 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:04.522625 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:04.512972 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:04.531947 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:04.533582 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:04.661949 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:04.671713 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:04.674546 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:04.667380 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:04.860204 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:04.864449 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:04.858989 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:04.886070 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0510 05:26:04.958378 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0510 05:26:04.975686 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: I0510 05:26:04.967431 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:04.983460 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0510 05:26:04.977350 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:04.997018 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:05.008397 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:05.036093 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:05.162095 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:05.157331 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:05.162077 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:05.198589 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:05.322788 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:05.322216 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:05.341310 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:05.337503 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:05.462747 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:05.482994 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:05.492373 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:05.517361 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:05.632699 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:05.651969 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:05.647532 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:05.651896 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:05.791798 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:05.811838 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:05.827253 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:05.852278 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 2 finished [worker-3]: I0510 05:26:06.006566 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-1]: I0510 05:26:06.029743 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: I0510 05:26:06.021348 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0510 05:26:06.036913 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:06.032685 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:06.051363 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:06.051302 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:06.081654 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:06.175819 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:06.203061 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:06.212363 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:06.203059 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:06.381106 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:06.371197 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:06.381047 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:06.391840 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:06.521370 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:06.541357 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:06.586568 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:06.617271 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:06.771657 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:06.771658 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:06.881648 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:06.897381 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:07.046374 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:07.054403 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:07.074563 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:07.054121 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:epoch 3 finished [worker-0]: I0510 05:26:07.166136 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: INFO:tensorflow:epoch 3 finished [worker-3]: I0510 05:26:07.164606 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0510 05:26:07.176096 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0510 05:26:07.183346 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:07.305737 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:07.326636 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:07.363125 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:07.350972 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:07.503077 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:07.511640 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:07.531317 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:07.535711 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:07.681049 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:07.710758 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:07.721396 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:07.710689 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:07.871592 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:07.882005 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:07.891342 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:07.890660 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:08.027614 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:08.036090 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:08.051788 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:08.041064 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:08.154313 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:08.171995 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:08.182181 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:08.197276 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 4 finished [worker-3]: I0510 05:26:08.287898 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0510 05:26:08.288282 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0510 05:26:08.299106 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0510 05:26:08.299479 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:epoch 4 finished [worker-2]: INFO:tensorflow:epoch 4 finished [worker-0]: I0510 05:26:08.297229 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: I0510 05:26:08.317469 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-0]: INFO:tensorflow:Training finished. [worker-2]: I0510 05:26:08.317889 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-0]: I0510 05:26:08.297645 281473111126912 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:restarting workers I0510 05:26:09.956694 281473286435712 gce_failure_handler_test.py:411] restarting workers INFO:tensorflow:workers restarted I0510 05:26:10.096242 281473286435712 gce_failure_handler_test.py:415] workers restarted [worker-0]: I0510 05:26:10.578563 281473111126912 multi_process_runner.py:840] Subprocess with PID 1806563 (worker, 0) is now being started. [worker-1]: I0510 05:26:10.618108 281473111126912 multi_process_runner.py:840] Subprocess with PID 1806583 (worker, 1) is now being started. [worker-0]: I0510 05:26:10.579187 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:17492", "localhost:20436", "localhost:21347", "localhost:20672"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-3]: I0510 05:26:10.668623 281473111126912 multi_process_runner.py:840] Subprocess with PID 1806649 (worker, 3) is now being started. [worker-1]: I0510 05:26:10.618714 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:17492", "localhost:20436", "localhost:21347", "localhost:20672"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-3]: I0510 05:26:10.669245 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:17492", "localhost:20436", "localhost:21347", "localhost:20672"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:26:10.828518 281473111126912 multi_process_runner.py:840] Subprocess with PID 1806643 (worker, 2) is now being started. [worker-2]: I0510 05:26:10.829147 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:17492", "localhost:20436", "localhost:21347", "localhost:20672"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-10 05:26:10.901387: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:20436 [worker-0]: 2023-05-10 05:26:10.962132: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:17492 [worker-3]: 2023-05-10 05:26:11.004761: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:20672 [worker-0]: 2023-05-10 05:26:11.011781: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 1997109362290480759 [worker-3]: 2023-05-10 05:26:11.015857: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: 2023-05-10 05:26:11.058150: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 3789421501198513978 [worker-0]: 2023-05-10 05:26:11.059619: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: 2023-05-10 05:26:11.060432: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 15997497953925608182 [worker-1]: 2023-05-10 05:26:11.063010: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: 2023-05-10 05:26:11.247171: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:21347 [worker-0]: 2023-05-10 05:26:11.266769: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 12081934998179563752 [worker-2]: 2023-05-10 05:26:11.267221: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: I0510 05:26:11.271304 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-3]: I0510 05:26:11.277525 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:26:11.287396 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:26:11.272551 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:26:11.367784 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:26:11.368877 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:26:11.369199 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: I0510 05:26:11.429940 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-0]: I0510 05:26:11.447526 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:26:11.449038 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0510 05:26:11.470973 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: INFO:tensorflow:Check health not enabled. [worker-1]: I0510 05:26:11.471655 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:26:11.472015 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:26:11.539298 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:26:11.540009 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0510 05:26:11.540392 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:17492', 'localhost:20436', 'localhost:21347', 'localhost:20672']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0510 05:26:11.699808 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0510 05:26:11.703021 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:26:11.707385 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0510 05:26:11.710322 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: self._target(*self._args, **self._kwargs) [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-1]: I0510 05:26:11.718371 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: I0510 05:26:11.718926 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: self.run() [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-0]: if self._termination_watcher_fn(): [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-2]: if self._termination_watcher_fn(): [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: I0510 05:26:11.715148 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-2]: I0510 05:26:11.718461 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: W0510 05:26:11.715684 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-2]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: INFO:tensorflow:Start training at 0 [worker-2]: W0510 05:26:11.718978 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: I0510 05:26:11.715993 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0510 05:26:11.736758 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:26:11.719261 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: I0510 05:26:11.737095 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0510 05:26:11.757638 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-1]: self._target(*self._args, **self._kwargs) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: if self._termination_watcher_fn(): [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0510 05:26:11.758645 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: W0510 05:26:11.759182 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: INFO:tensorflow:Start training at 0 [worker-1]: I0510 05:26:11.759477 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: W0510 05:26:11.758319 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start training at 0 [worker-3]: I0510 05:26:11.758615 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: if self._termination_watcher_fn(): [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:11.957504 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:11.977846 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:12.023679 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:12.159215 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:12.341662 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:12.351859 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:12.381745 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:12.372123 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:12.544783 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:12.582862 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:12.603025 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:12.593290 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:12.748887 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:12.803006 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:12.801398 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:12.827579 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:12.990073 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:13.003406 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:13.007194 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:13.009151 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:13.101359 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:13.110185 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:13.112222 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:13.121825 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:13.137063 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:13.143287 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:13.143212 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:13.130055 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:13.251403 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:epoch 0 finished [worker-3]: I0510 05:26:13.252182 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:13.267163 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:13.266784 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:13.264625 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:13.274731 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:epoch 0 finished [worker-1]: INFO:tensorflow:epoch 0 finished [worker-2]: INFO:tensorflow:epoch 0 finished [worker-1]: I0510 05:26:13.275500 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: I0510 05:26:13.265395 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: I0510 05:26:13.267401 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:13.293972 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:13.287924 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:13.293835 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:13.413530 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:13.413892 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:13.413530 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:13.437644 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:13.563028 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:13.593516 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:13.583610 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:13.604591 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:13.711932 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:13.711887 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:13.722275 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:13.741378 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:13.902221 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:13.911619 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:13.911628 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:13.932229 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:14.061722 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:14.095921 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:14.104355 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:14.114257 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0510 05:26:14.210015 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0510 05:26:14.219655 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0510 05:26:14.226693 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0510 05:26:14.236629 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:14.242555 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:14.240011 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:14.259410 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:14.288930 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:14.454382 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:14.463171 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:14.463159 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:14.473276 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:14.587032 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:14.596630 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:14.597750 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:14.614010 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:14.753549 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:14.773558 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:14.755917 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:14.797709 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:15.031711 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:15.033069 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:15.073389 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:15.083400 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:15.177021 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:15.193392 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:15.194512 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:15.194682 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:epoch 2 finished [worker-1]: I0510 05:26:15.291513 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: INFO:tensorflow:epoch 2 finished [worker-3]: I0510 05:26:15.290904 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-2]: I0510 05:26:15.291606 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: I0510 05:26:15.291125 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:15.304587 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:15.305154 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:15.308098 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:15.310402 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:15.419079 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:15.413036 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:15.418410 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:15.423034 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:15.583634 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:15.589897 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:15.586722 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:15.597585 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:15.735557 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:15.736938 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:15.754036 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:15.756775 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:15.870370 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:15.870487 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:15.890288 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:15.907998 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:16.092158 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:16.095686 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:16.147323 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:16.147323 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 3 finished [worker-0]: INFO:tensorflow:epoch 3 finished [worker-3]: I0510 05:26:16.219276 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: I0510 05:26:16.219907 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0510 05:26:16.225253 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0510 05:26:16.226699 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:16.360147 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:16.395868 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:16.387272 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:16.416648 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:16.541457 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:16.532119 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:16.561412 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:16.561419 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:16.711681 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:16.723162 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:16.733319 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:16.723209 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:16.912335 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:16.929034 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:16.942761 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:16.987784 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:17.098757 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:17.121472 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:17.149749 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:17.153309 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:17.269969 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:17.278820 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:17.279190 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:17.294403 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 4 finished [worker-3]: I0510 05:26:17.369353 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0510 05:26:17.369777 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:epoch 4 finished [worker-0]: I0510 05:26:17.375185 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:epoch 4 finished [worker-1]: INFO:tensorflow:epoch 4 finished [worker-2]: I0510 05:26:17.374127 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0510 05:26:17.375549 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: I0510 05:26:17.372717 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0510 05:26:17.374505 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0510 05:26:17.373107 281473111126912 gce_failure_handler_test.py:244] Training finished. I0510 05:26:18.076669 281473286435712 multi_process_runner.py:646] worker-0 exit code: 0 I0510 05:26:18.076922 281473286435712 multi_process_runner.py:646] worker-1 exit code: 0 I0510 05:26:18.077057 281473286435712 multi_process_runner.py:646] worker-2 exit code: 0 I0510 05:26:18.077179 281473286435712 multi_process_runner.py:646] worker-3 exit code: 0 I0510 05:26:18.080652 281473286435712 multi_process_runner.py:662] Joining log reading threads. I0510 05:26:18.080876 281473286435712 multi_process_runner.py:665] Joined log reading threads. INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_7_inputarg_checkpoint_strategyoption_MWMSmultiworker): 16.91s I0510 05:26:18.321180 281473286435712 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_7_inputarg_checkpoint_strategyoption_MWMSmultiworker): 16.91s [ OK ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_7_inputarg_checkpoint_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_0_inputarg_checkpoint_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 23829 I0510 05:26:18.323054 281473286435712 test_util.py:3796] Using local port 23829 INFO:tensorflow:Using local port 21640 I0510 05:26:18.323580 281473286435712 test_util.py:3796] Using local port 21640 INFO:tensorflow:Using local port 24152 I0510 05:26:18.324051 281473286435712 test_util.py:3796] Using local port 24152 INFO:tensorflow:Using local port 18578 I0510 05:26:18.324504 281473286435712 test_util.py:3796] Using local port 18578 INFO:tensorflow:Cluster starting. I0510 05:26:18.405419 281473286435712 gce_failure_handler_test.py:405] Cluster starting. [worker-0]: I0510 05:26:18.509112 281473111126912 multi_process_runner.py:840] Subprocess with PID 1813214 (worker, 0) is now being started. [worker-0]: I0510 05:26:18.509564 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23829", "localhost:21640", "localhost:24152", "localhost:18578"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0510 05:26:18.511442 281473111126912 multi_process_runner.py:840] Subprocess with PID 1813228 (worker, 1) is now being started. [worker-1]: I0510 05:26:18.511886 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23829", "localhost:21640", "localhost:24152", "localhost:18578"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:26:18.522581 281473111126912 multi_process_runner.py:840] Subprocess with PID 1813235 (worker, 2) is now being started. [worker-2]: I0510 05:26:18.523028 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23829", "localhost:21640", "localhost:24152", "localhost:18578"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0510 05:26:18.559721 281473111126912 multi_process_runner.py:840] Subprocess with PID 1813264 (worker, 3) is now being started. [worker-3]: I0510 05:26:18.560145 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23829", "localhost:21640", "localhost:24152", "localhost:18578"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: 2023-05-10 05:26:18.562000: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:24152 [worker-3]: 2023-05-10 05:26:18.666831: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:18578 [worker-0]: 2023-05-10 05:26:18.716717: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:23829 [worker-0]: 2023-05-10 05:26:18.800035: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 5305618418619503357 [worker-2]: 2023-05-10 05:26:18.801540: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: 2023-05-10 05:26:18.802437: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: 2023-05-10 05:26:18.800237: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 13378671914288772126 [worker-0]: 2023-05-10 05:26:18.800368: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 14005017604118667671 [worker-0]: 2023-05-10 05:26:18.801344: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-1]: 2023-05-10 05:26:18.880476: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:21640 [worker-0]: 2023-05-10 05:26:18.892646: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 15375776863511918208 [worker-1]: 2023-05-10 05:26:18.906415: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:26:18.913655 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: I0510 05:26:18.913495 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-3]: I0510 05:26:18.917679 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:26:18.972488 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: I0510 05:26:18.983391 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-0]: I0510 05:26:18.984238 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:26:18.984500 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:26:18.985272 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:26:18.986013 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:26:18.986269 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:26:19.044002 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:26:19.045356 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0510 05:26:19.045617 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0510 05:26:19.068774 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: INFO:tensorflow:Check health not enabled. [worker-1]: I0510 05:26:19.069281 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:26:19.069528 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0510 05:26:19.185494 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0510 05:26:19.187073 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0510 05:26:19.188432 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0510 05:26:19.189451 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: if self._termination_watcher_fn(): [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0510 05:26:19.189982 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: W0510 05:26:19.192471 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start training at 0 [worker-3]: I0510 05:26:19.192682 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:26:19.200930 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: I0510 05:26:19.237760 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-1]: self._target(*self._args, **self._kwargs) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: if self._termination_watcher_fn(): [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0510 05:26:19.248980 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: W0510 05:26:19.249605 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0510 05:26:19.250996 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: Instructions for updating: [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: INFO:tensorflow:Start training at 0 [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: I0510 05:26:19.249817 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: self._target(*self._args, **self._kwargs) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-0]: if self._termination_watcher_fn(): [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0510 05:26:19.257000 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: W0510 05:26:19.257453 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: INFO:tensorflow:Start training at 0 [worker-0]: I0510 05:26:19.257685 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0510 05:26:19.266275 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-2]: if self._termination_watcher_fn(): [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0510 05:26:19.296205 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: W0510 05:26:19.296678 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:26:19.296907 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:19.330445 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:19.378431 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:19.448888 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:19.516915 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:19.697204 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:19.700431 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:19.700431 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:19.700355 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:19.823875 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:19.831037 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:19.843321 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:19.851174 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:19.947897 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:19.958468 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:19.973750 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:19.981052 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:20.079522 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:20.111114 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:20.111113 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:20.120756 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:20.216968 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:20.217136 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:20.227436 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:20.236513 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:20.236513 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:20.251453 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:20.257108 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:20.247796 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:20.336513 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:epoch 0 finished [worker-3]: I0510 05:26:20.336946 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:20.343424 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: INFO:tensorflow:epoch 0 finished [worker-2]: I0510 05:26:20.343811 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:20.356589 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:epoch 0 finished [worker-1]: I0510 05:26:20.356972 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:20.356592 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:epoch 0 finished [worker-0]: I0510 05:26:20.356971 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:20.390326 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:20.390229 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:20.408419 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:20.419995 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:20.534095 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:20.580345 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:20.600385 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:20.620820 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:20.715688 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:20.750240 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:20.740036 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:20.743924 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:20.910299 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:20.901787 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:20.910381 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:20.930552 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:21.041844 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:21.060889 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:21.070929 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:21.060890 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:21.192890 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:21.212869 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:21.212556 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:21.222827 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0510 05:26:21.296829 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0510 05:26:21.307276 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0510 05:26:21.312437 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:21.305490 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0510 05:26:21.316822 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:21.324956 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:21.341161 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:21.360826 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:21.552122 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:21.575137 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:21.580446 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:21.590388 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:21.796445 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:21.821612 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:21.820652 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:21.831690 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:21.902596 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:21.906009 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:21.920734 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:21.907799 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:22.041228 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:22.063211 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:22.080839 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:22.112358 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:22.190011 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:22.193830 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:22.211734 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:22.206557 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 2 finished [worker-3]: I0510 05:26:22.334650 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-0]: I0510 05:26:22.346824 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0510 05:26:22.353085 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:22.350544 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:22.347458 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:22.371792 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:22.381786 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:22.381809 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:22.502629 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:22.502629 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:22.512480 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:22.533829 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:22.653048 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:22.660686 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:22.658083 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:22.658040 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:22.738938 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:22.761177 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:22.752244 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:22.762016 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:22.893707 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:22.888009 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:22.893889 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:22.930713 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:23.044403 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:23.051358 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:23.050994 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:23.080760 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-3]: INFO:tensorflow:epoch 3 finished [worker-0]: I0510 05:26:23.188076 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: I0510 05:26:23.196279 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: I0510 05:26:23.187827 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0510 05:26:23.206983 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:23.310907 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:23.373318 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:23.377909 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:23.395390 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:23.483027 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:23.484323 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:23.480533 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:23.492036 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:23.567580 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:23.569228 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:23.569052 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:23.589676 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:23.704529 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:23.709269 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:23.724891 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:23.710538 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:23.830770 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:23.820054 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:23.845084 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:23.847286 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:23.912660 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:23.908806 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:23.920446 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:23.938952 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:epoch 4 finished [worker-0]: I0510 05:26:23.987707 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0510 05:26:23.988034 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-3]: INFO:tensorflow:epoch 4 finished [worker-3]: I0510 05:26:23.999938 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0510 05:26:24.000517 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0510 05:26:24.000806 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0510 05:26:24.000275 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0510 05:26:24.006614 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0510 05:26:24.006949 281473111126912 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:restarting workers I0510 05:26:25.566749 281473286435712 gce_failure_handler_test.py:411] restarting workers [worker-0]: I0510 05:26:25.625874 281473111126912 multi_process_runner.py:840] Subprocess with PID 1822474 (worker, 0) is now being started. [worker-0]: I0510 05:26:25.626421 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23829", "localhost:21640", "localhost:24152", "localhost:18578"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-0]: 2023-05-10 05:26:25.723763: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:23829 [worker-0]: 2023-05-10 05:26:25.727695: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 5239108368010516572 [worker-0]: 2023-05-10 05:26:25.728046: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. INFO:tensorflow:workers restarted I0510 05:26:25.746376 281473286435712 gce_failure_handler_test.py:415] workers restarted [worker-1]: I0510 05:26:25.767844 281473111126912 multi_process_runner.py:840] Subprocess with PID 1822644 (worker, 1) is now being started. [worker-1]: I0510 05:26:25.768240 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23829", "localhost:21640", "localhost:24152", "localhost:18578"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-10 05:26:25.814520: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:21640 [worker-3]: I0510 05:26:25.817229 281473111126912 multi_process_runner.py:840] Subprocess with PID 1822851 (worker, 3) is now being started. [worker-3]: I0510 05:26:25.817608 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23829", "localhost:21640", "localhost:24152", "localhost:18578"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:26:25.853997 281473111126912 multi_process_runner.py:840] Subprocess with PID 1822847 (worker, 2) is now being started. [worker-2]: I0510 05:26:25.854421 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:23829", "localhost:21640", "localhost:24152", "localhost:18578"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-0]: 2023-05-10 05:26:25.865890: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 14418239982177142993 [worker-1]: 2023-05-10 05:26:25.867917: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: 2023-05-10 05:26:25.883620: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:18578 [worker-2]: 2023-05-10 05:26:25.887449: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:24152 [worker-0]: 2023-05-10 05:26:25.906842: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 2001698376458489649 [worker-3]: 2023-05-10 05:26:25.907857: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: 2023-05-10 05:26:25.906990: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 15484410032172945789 [worker-2]: 2023-05-10 05:26:25.946635: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:26:25.977007 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-3]: I0510 05:26:25.987409 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-2]: I0510 05:26:25.968443 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:26:25.989813 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0510 05:26:26.039484 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: INFO:tensorflow:Check health not enabled. [worker-1]: I0510 05:26:26.040156 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:26:26.040355 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:26:26.048031 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:26:26.049442 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0510 05:26:26.049661 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: I0510 05:26:26.084625 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-0]: I0510 05:26:26.085344 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:26:26.085543 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:26:26.138781 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:26:26.139685 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:26:26.139907 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:23829', 'localhost:21640', 'localhost:24152', 'localhost:18578']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0510 05:26:26.308323 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:26:26.313799 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0510 05:26:26.314625 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-0]: I0510 05:26:26.315089 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Instructions for updating: [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: I0510 05:26:26.316565 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: W0510 05:26:26.315554 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0510 05:26:26.317238 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-0]: Instructions for updating: [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-1]: I0510 05:26:26.317642 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: Traceback (most recent call last): [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-3]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: Traceback (most recent call last): [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: INFO:tensorflow:Start training at 0 [worker-1]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-3]: I0510 05:26:26.318283 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: I0510 05:26:26.315819 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: self.run() [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: I0510 05:26:26.318212 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: Instructions for updating: [worker-0]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: I0510 05:26:26.323306 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: self._target(*self._args, **self._kwargs) [worker-1]: Instructions for updating: [worker-3]: W0510 05:26:26.318706 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: Instructions for updating: [worker-0]: if self._termination_watcher_fn(): [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-3]: INFO:tensorflow:Start training at 0 [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: W0510 05:26:26.318596 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: I0510 05:26:26.324205 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: Instructions for updating: [worker-3]: I0510 05:26:26.318918 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: INFO:tensorflow:Start training at 0 [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: I0510 05:26:26.318802 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: I0510 05:26:26.324909 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: self.run() [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-2]: Instructions for updating: [worker-1]: self._target(*self._args, **self._kwargs) [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-2]: W0510 05:26:26.325319 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: if self._termination_watcher_fn(): [worker-2]: Instructions for updating: [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-3]: self.run() [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:26:26.325497 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: self._target(*self._args, **self._kwargs) [worker-2]: Traceback (most recent call last): [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-3]: if self._termination_watcher_fn(): [worker-2]: self.run() [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: self._target(*self._args, **self._kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: if self._termination_watcher_fn(): [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:26.442077 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:26.478744 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:26.477035 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:26.436739 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:26.710557 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:26.718458 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:26.740613 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:26.748367 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:26.876048 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:26.871183 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:26.882248 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:26.891343 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:26.994358 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:27.009019 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:27.031685 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:27.060956 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:27.201619 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:27.196221 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:27.190982 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:27.215410 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cecc280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:27.286849 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cecc280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:27.292316 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:27.292562 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:27.302016 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:27.302038 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:27.320765 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: W0510 05:26:27.306622 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:27.351737 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cecc700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:27.418775 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cecc700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:epoch 0 finished [worker-3]: I0510 05:26:27.419189 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:27.427208 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:epoch 0 finished [worker-0]: I0510 05:26:27.427719 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:27.434190 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:epoch 0 finished [worker-1]: I0510 05:26:27.434579 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:27.428318 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:27.445150 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: INFO:tensorflow:epoch 0 finished [worker-2]: I0510 05:26:27.445583 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:27.444576 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:27.471244 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:27.457436 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:27.580307 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:27.580835 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:27.585075 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:27.612741 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:27.800728 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:27.800792 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:27.822274 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:27.829600 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:27.951106 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:27.955576 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:27.932062 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:27.968497 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:28.152303 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:28.151242 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:28.170949 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:28.185512 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:28.260729 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:28.269185 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:28.283831 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:28.282734 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0510 05:26:28.345901 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0510 05:26:28.345948 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0510 05:26:28.349742 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0510 05:26:28.349838 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:28.361063 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:28.372272 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:28.371703 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:28.380634 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:28.512590 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:28.517001 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:28.517858 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:28.541324 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:28.605243 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:28.621129 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:28.620890 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:28.626632 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:28.695686 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:28.695955 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:28.700744 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:28.710559 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:28.806471 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:28.821249 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:28.798977 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:28.810915 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:28.911447 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:28.991049 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:28.981790 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:29.001110 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 2 finished [worker-3]: I0510 05:26:29.107113 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-0]: I0510 05:26:29.107501 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:29.115769 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:epoch 2 finished [worker-1]: I0510 05:26:29.107728 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:29.115789 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0510 05:26:29.117526 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:29.118174 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:29.141203 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:29.247575 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:29.269398 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:29.270526 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:29.311160 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:29.538016 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:29.543474 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:29.566240 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:29.550618 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:29.646831 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:29.656206 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:29.658153 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:29.657363 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:29.771682 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:29.771669 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:29.791399 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:29.841239 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:30.224155 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:30.262115 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:30.233527 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:30.233731 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 3 finished [worker-3]: I0510 05:26:30.362241 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0510 05:26:30.363311 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:epoch 3 finished [worker-0]: I0510 05:26:30.362009 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0510 05:26:30.368268 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:30.504360 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:30.547511 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:30.587871 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:30.647883 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:30.750114 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:30.771601 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:30.841696 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:30.851428 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:30.932804 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:30.943044 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:30.952479 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:30.960806 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:31.041393 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:31.038925 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:31.052300 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:31.047668 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:31.175294 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:31.171249 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:31.190640 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:31.191495 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:31.264807 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:31.267152 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:31.291165 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:31.348590 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:epoch 4 finished [worker-3]: INFO:tensorflow:epoch 4 finished [worker-0]: I0510 05:26:31.410130 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: I0510 05:26:31.409736 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0510 05:26:31.410057 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-0]: I0510 05:26:31.410484 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0510 05:26:31.447275 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0510 05:26:31.447700 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0510 05:26:31.462892 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0510 05:26:31.463265 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-2]: Exception in thread PeerTerminationWatcher-2: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner I0510 05:26:31.660885 281473286435712 multi_process_runner.py:646] worker-0 exit code: 0 I0510 05:26:31.661143 281473286435712 multi_process_runner.py:646] worker-1 exit code: 0 I0510 05:26:31.661282 281473286435712 multi_process_runner.py:646] worker-2 exit code: 0 I0510 05:26:31.661406 281473286435712 multi_process_runner.py:646] worker-3 exit code: 0 I0510 05:26:31.664477 281473286435712 multi_process_runner.py:662] Joining log reading threads. I0510 05:26:31.664844 281473286435712 multi_process_runner.py:665] Joined log reading threads. INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_0_inputarg_checkpoint_strategyoption_MWMSmultiworker): 13.51s I0510 05:26:31.836160 281473286435712 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_0_inputarg_checkpoint_strategyoption_MWMSmultiworker): 13.51s [ OK ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_0_inputarg_checkpoint_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_7_inputarg_checkpoint_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 16569 I0510 05:26:31.838177 281473286435712 test_util.py:3796] Using local port 16569 INFO:tensorflow:Using local port 20893 I0510 05:26:31.838705 281473286435712 test_util.py:3796] Using local port 20893 INFO:tensorflow:Using local port 22535 I0510 05:26:31.839140 281473286435712 test_util.py:3796] Using local port 22535 INFO:tensorflow:Using local port 17053 I0510 05:26:31.839560 281473286435712 test_util.py:3796] Using local port 17053 INFO:tensorflow:Cluster starting. I0510 05:26:31.911957 281473286435712 gce_failure_handler_test.py:405] Cluster starting. [worker-0]: I0510 05:26:31.955014 281473111126912 multi_process_runner.py:840] Subprocess with PID 1841771 (worker, 0) is now being started. [worker-0]: I0510 05:26:31.955463 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:16569", "localhost:20893", "localhost:22535", "localhost:17053"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-0]: 2023-05-10 05:26:32.032687: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:16569 [worker-0]: 2023-05-10 05:26:32.036087: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 12048492305917045222 [worker-0]: 2023-05-10 05:26:32.036352: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-1]: I0510 05:26:32.047894 281473111126912 multi_process_runner.py:840] Subprocess with PID 1841780 (worker, 1) is now being started. [worker-1]: I0510 05:26:32.048307 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:16569", "localhost:20893", "localhost:22535", "localhost:17053"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-3]: I0510 05:26:32.119518 281473111126912 multi_process_runner.py:840] Subprocess with PID 1841845 (worker, 3) is now being started. [worker-3]: I0510 05:26:32.119938 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:16569", "localhost:20893", "localhost:22535", "localhost:17053"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:26:32.122309 281473111126912 multi_process_runner.py:840] Subprocess with PID 1841786 (worker, 2) is now being started. [worker-2]: I0510 05:26:32.122702 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:16569", "localhost:20893", "localhost:22535", "localhost:17053"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: 2023-05-10 05:26:32.200342: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:17053 [worker-0]: 2023-05-10 05:26:32.216900: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 13757887101810626039 [worker-1]: 2023-05-10 05:26:32.217359: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:20893 [worker-0]: 2023-05-10 05:26:32.226482: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 9474882095919479381 [worker-1]: 2023-05-10 05:26:32.226979: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: 2023-05-10 05:26:32.328292: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: 2023-05-10 05:26:32.337771: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:22535 [worker-0]: 2023-05-10 05:26:32.346192: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 12214514350688509609 [worker-2]: 2023-05-10 05:26:32.347159: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:26:32.349743 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-3]: I0510 05:26:32.349290 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:26:32.356902 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-2]: I0510 05:26:32.429019 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:26:32.444536 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-1]: I0510 05:26:32.434615 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-1]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:26:32.445177 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: I0510 05:26:32.435072 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:26:32.445376 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:26:32.435271 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: I0510 05:26:32.512013 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:26:32.529291 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:26:32.530120 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0510 05:26:32.530337 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:26:32.513575 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:26:32.589343 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0510 05:26:32.887441 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0510 05:26:32.906924 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0510 05:26:32.924263 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: self.run() [worker-2]: I0510 05:26:32.938437 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: if self._termination_watcher_fn(): [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0510 05:26:32.946188 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: W0510 05:26:32.946592 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start training at 0 [worker-3]: I0510 05:26:32.946770 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0510 05:26:32.956272 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0510 05:26:32.957552 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: I0510 05:26:32.908152 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0510 05:26:32.976779 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-1]: self.run() [worker-0]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-0]: self.run() [worker-1]: self._target(*self._args, **self._kwargs) [worker-0]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: self._target(*self._args, **self._kwargs) [worker-1]: I0510 05:26:32.978524 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: if self._termination_watcher_fn(): [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-0]: if self._termination_watcher_fn(): [worker-2]: Traceback (most recent call last): [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: self.run() [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: self._target(*self._args, **self._kwargs) [worker-0]: I0510 05:26:32.977956 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: if self._termination_watcher_fn(): [worker-0]: Instructions for updating: [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: W0510 05:26:32.978354 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: W0510 05:26:32.978942 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: I0510 05:26:32.986193 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: Instructions for updating: [worker-0]: INFO:tensorflow:Start training at 0 [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-0]: I0510 05:26:32.978536 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: INFO:tensorflow:Start training at 0 [worker-2]: Instructions for updating: [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: W0510 05:26:32.986586 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: I0510 05:26:32.979181 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:26:32.986760 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.083877 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.083908 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.075759 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.108788 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.198427 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.207803 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.198906 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.225310 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.283792 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.283869 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.284171 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.287081 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.363776 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.378026 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.380439 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.380623 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.490255 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.487889 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.500330 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.521097 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:33.607842 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:33.612861 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:33.612237 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.619152 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:33.626481 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.621248 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.639424 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.640330 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:33.739269 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:epoch 0 finished [worker-3]: I0510 05:26:33.739657 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:33.745291 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: INFO:tensorflow:epoch 0 finished [worker-2]: I0510 05:26:33.745665 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:33.750314 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:epoch 0 finished [worker-0]: I0510 05:26:33.750690 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.759058 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.760313 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.777868 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:33.796343 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:epoch 0 finished [worker-1]: I0510 05:26:33.796724 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.840637 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.894092 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.907058 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.894117 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.894209 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:33.986188 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:33.986262 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:33.994878 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:33.998453 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:34.107276 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:34.150488 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:34.141865 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:34.170713 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:34.268614 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:34.290409 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:34.290356 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:34.307071 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:34.422554 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:34.412357 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:34.432310 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:34.457046 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0510 05:26:34.547323 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0510 05:26:34.552007 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0510 05:26:34.567128 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:34.575864 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0510 05:26:34.579035 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:34.581183 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:34.607067 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:34.612593 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:34.685369 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:34.686856 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:34.685908 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:34.720437 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:34.799159 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:34.816601 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:34.851714 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:34.868527 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:34.948863 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:34.952913 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:34.948670 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:34.961318 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:35.085402 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:35.101274 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:35.100484 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:35.110551 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:35.195375 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:35.206523 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:35.206906 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:35.210534 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-0]: I0510 05:26:35.294663 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0510 05:26:35.302208 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-1]: I0510 05:26:35.307279 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: I0510 05:26:35.289162 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:35.334001 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:35.330754 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:35.330754 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:35.350908 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:35.464594 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:35.467731 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:35.479511 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:35.474022 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:35.563748 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:35.563519 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:35.581650 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:35.600492 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:35.676835 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:35.677619 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:35.686056 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:35.701693 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:35.797229 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:35.795844 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:35.795791 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:35.807379 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:35.972479 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:35.963524 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:35.973058 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:35.992573 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 3 finished [worker-3]: I0510 05:26:36.087310 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:epoch 3 finished [worker-0]: I0510 05:26:36.110905 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0510 05:26:36.126492 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0510 05:26:36.126621 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:36.258039 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:36.257379 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:36.258704 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:36.344666 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:36.474927 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:36.478011 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:36.490474 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:36.514853 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:36.610764 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:36.611299 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:36.631705 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:36.650377 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:36.775964 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:36.763623 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:36.800600 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:36.841552 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:37.110662 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:37.127129 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:37.120239 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:37.160525 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:37.300461 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:37.325437 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:37.510843 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:37.530321 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 4 finished [worker-3]: I0510 05:26:37.658745 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0510 05:26:37.659068 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0510 05:26:37.677438 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0510 05:26:37.677871 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:epoch 4 finished [worker-0]: I0510 05:26:37.686611 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0510 05:26:37.686980 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0510 05:26:37.688700 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0510 05:26:37.688995 281473111126912 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:restarting workers I0510 05:26:39.009190 281473286435712 gce_failure_handler_test.py:411] restarting workers [worker-0]: I0510 05:26:39.087852 281473111126912 multi_process_runner.py:840] Subprocess with PID 1855800 (worker, 0) is now being started. [worker-0]: I0510 05:26:39.088268 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:16569", "localhost:20893", "localhost:22535", "localhost:17053"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' INFO:tensorflow:workers restarted I0510 05:26:39.166695 281473286435712 gce_failure_handler_test.py:415] workers restarted [worker-0]: 2023-05-10 05:26:39.196608: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:16569 [worker-0]: 2023-05-10 05:26:39.203586: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 18416096648761800057 [worker-0]: 2023-05-10 05:26:39.206555: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-1]: I0510 05:26:39.249166 281473111126912 multi_process_runner.py:840] Subprocess with PID 1855977 (worker, 1) is now being started. [worker-1]: I0510 05:26:39.249610 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:16569", "localhost:20893", "localhost:22535", "localhost:17053"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-3]: I0510 05:26:39.280697 281473111126912 multi_process_runner.py:840] Subprocess with PID 1856228 (worker, 3) is now being started. [worker-2]: I0510 05:26:39.282048 281473111126912 multi_process_runner.py:840] Subprocess with PID 1856223 (worker, 2) is now being started. [worker-3]: I0510 05:26:39.281118 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:16569", "localhost:20893", "localhost:22535", "localhost:17053"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: I0510 05:26:39.282448 281473111126912 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:16569", "localhost:20893", "localhost:22535", "localhost:17053"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-10 05:26:39.315403: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:20893 [worker-0]: 2023-05-10 05:26:39.326963: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 3518716907706818121 [worker-1]: 2023-05-10 05:26:39.327582: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-3]: 2023-05-10 05:26:39.343836: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:17053 [worker-0]: 2023-05-10 05:26:39.356394: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 6593781731182382379 [worker-3]: 2023-05-10 05:26:39.356659: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: 2023-05-10 05:26:39.366925: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:449] Started server with target: grpc://localhost:22535 [worker-0]: 2023-05-10 05:26:39.396187: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 16305713023873114315 [worker-2]: 2023-05-10 05:26:39.397348: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:298] Coordination agent has successfully connected. [worker-2]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-1]: I0510 05:26:39.399349 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-3]: I0510 05:26:39.399655 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1'] [worker-0]: INFO:tensorflow:Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-0]: I0510 05:26:39.417047 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-2]: I0510 05:26:39.399478 281473111126912 collective_all_reduce_strategy.py:531] Enabled multi-worker collective ops with available devices: ['/job:worker/replica:0/task:2/device:CPU:0', '/job:worker/replica:0/task:2/device:CPU:1', '/job:worker/replica:0/task:0/device:CPU:0', '/job:worker/replica:0/task:0/device:CPU:1', '/job:worker/replica:0/task:1/device:CPU:0', '/job:worker/replica:0/task:1/device:CPU:1', '/job:worker/replica:0/task:3/device:CPU:0', '/job:worker/replica:0/task:3/device:CPU:1'] [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0510 05:26:39.467169 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0510 05:26:39.467833 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0510 05:26:39.468040 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0510 05:26:39.467168 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: INFO:tensorflow:Check health not enabled. [worker-1]: I0510 05:26:39.467834 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0510 05:26:39.468040 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: I0510 05:26:39.510261 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-0]: I0510 05:26:39.510962 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0510 05:26:39.511177 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0510 05:26:39.521326 281473111126912 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: INFO:tensorflow:Check health not enabled. [worker-2]: I0510 05:26:39.522025 281473111126912 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0510 05:26:39.522239 281473111126912 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:16569', 'localhost:20893', 'localhost:22535', 'localhost:17053']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0510 05:26:39.614109 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0510 05:26:39.615097 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0510 05:26:39.615671 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: W0510 05:26:39.616456 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-2]: Instructions for updating: [worker-2]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-2]: I0510 05:26:39.616649 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: if self._termination_watcher_fn(): [worker-0]: I0510 05:26:39.620244 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0510 05:26:39.621290 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-0]: I0510 05:26:39.621727 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: Instructions for updating: [worker-3]: I0510 05:26:39.623127 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-0]: W0510 05:26:39.622164 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: I0510 05:26:39.623717 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-0]: Instructions for updating: [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: Traceback (most recent call last): [worker-0]: INFO:tensorflow:Start training at 0 [worker-0]: I0510 05:26:39.622408 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-0]: self._target(*self._args, **self._kwargs) [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-0]: if self._termination_watcher_fn(): [worker-0]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-3]: I0510 05:26:39.624601 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: W0510 05:26:39.645965 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-3]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: INFO:tensorflow:Start training at 0 [worker-3]: I0510 05:26:39.646324 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-3]: self._target(*self._args, **self._kwargs) [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: if self._termination_watcher_fn(): [worker-3]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0510 05:26:39.656981 281473111126912 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0510 05:26:39.660615 281473111126912 failure_handling.py:683] Start polling for termination signal. [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.10/threading.py", line 953, in run [worker-1]: self._target(*self._args, **self._kwargs) [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-1]: if self._termination_watcher_fn(): [worker-1]: File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0510 05:26:39.665026 281473111126912 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: WARNING:tensorflow:From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: W0510 05:26:39.665390 281473111126912 deprecation.py:364] From /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py:195: PreemptionCheckpointHandler.total_run_calls (from tensorflow.python.distribute.failure_handling.failure_handling) is deprecated and will be removed in a future version. [worker-1]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: INFO:tensorflow:Start training at 0 [worker-1]: I0510 05:26:39.665570 281473111126912 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:39.719025 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:39.861467 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:39.934480 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:39.994996 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:40.096981 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:40.081436 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:40.090935 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:40.130460 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:40.226790 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:40.239238 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:40.247767 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:40.251727 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:40.412353 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:40.421850 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:40.411749 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:40.410427 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:40.740297 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:40.731981 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:40.750531 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:40.761106 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cecc280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:40.898715 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:40.897988 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec4280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:40.904101 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cecc280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:40.917027 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:40.920404 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:40.936505 281473111126912 polymorphic_function.py:159] 5 out of the last 5 calls to .wrapped_fn at 0xffff8cec8280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:40.945852 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:40.960441 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: W0510 05:26:41.066375 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec4700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-3]: INFO:tensorflow:epoch 0 finished [worker-3]: I0510 05:26:41.066766 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: W0510 05:26:41.077127 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-0]: INFO:tensorflow:epoch 0 finished [worker-0]: I0510 05:26:41.077522 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff8cecc700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: W0510 05:26:41.097754 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cecc700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-2]: W0510 05:26:41.096830 281473111126912 polymorphic_function.py:159] 6 out of the last 6 calls to .wrapped_fn at 0xffff8cec8700> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. [worker-1]: INFO:tensorflow:epoch 0 finished [worker-2]: INFO:tensorflow:epoch 0 finished [worker-1]: I0510 05:26:41.098101 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: I0510 05:26:41.097226 281473111126912 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:41.088362 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:41.120937 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:41.124493 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:41.134582 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:41.195633 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:41.199502 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:41.197376 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:41.249110 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:41.313221 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:41.314577 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:41.315609 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:41.340705 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:41.421246 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:41.424782 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:41.440696 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:41.457577 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:41.531551 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:41.533183 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:41.526900 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:41.535160 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:41.623943 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:41.630225 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:41.631829 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:41.654467 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0510 05:26:41.708216 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0510 05:26:41.712966 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0510 05:26:41.709373 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:41.720232 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0510 05:26:41.716781 281473111126912 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:41.716713 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:41.727923 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:41.740436 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:41.842540 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:41.847219 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:41.857119 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:41.861939 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:42.002467 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:42.011389 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:42.011456 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:42.027893 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:42.139972 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:42.140601 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:42.143688 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:42.171545 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:42.262011 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:42.270815 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:42.263240 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:42.281847 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:42.411496 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:42.433493 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:42.417155 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:42.442918 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 2 finished [worker-3]: I0510 05:26:42.499823 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-1]: I0510 05:26:42.507481 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: I0510 05:26:42.507128 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: I0510 05:26:42.507683 281473111126912 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:42.520134 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:42.511634 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:42.523887 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:42.518228 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:42.613973 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:42.619966 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:42.625090 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:42.620315 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:42.765939 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:42.771524 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:42.771743 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:42.781597 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:42.920619 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:42.938790 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:42.937126 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:42.937522 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:43.027671 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:43.028993 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:43.025758 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:43.071702 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:43.131605 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:43.139554 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:43.140090 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:43.146281 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 3 finished [worker-3]: I0510 05:26:43.241753 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:epoch 3 finished [worker-0]: I0510 05:26:43.245668 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0510 05:26:43.253734 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0510 05:26:43.259718 281473111126912 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:43.399809 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:43.436997 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:43.443969 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:43.548980 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:43.654474 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:43.651264 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:43.683058 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:43.681081 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:43.911660 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:43.916825 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:43.922143 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:43.931586 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:44.030905 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:44.035847 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:44.040133 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:44.051590 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:44.148479 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:44.154016 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:44.156637 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:44.152416 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0510 05:26:44.267507 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0510 05:26:44.287932 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0510 05:26:44.313655 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0510 05:26:44.321903 281473111126912 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: INFO:tensorflow:epoch 4 finished [worker-0]: INFO:tensorflow:epoch 4 finished [worker-0]: I0510 05:26:44.409740 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0510 05:26:44.410124 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-3]: I0510 05:26:44.407863 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0510 05:26:44.408285 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0510 05:26:44.428551 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: I0510 05:26:44.427456 281473111126912 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-1]: INFO:tensorflow:Training finished. [worker-2]: I0510 05:26:44.428939 281473111126912 gce_failure_handler_test.py:244] Training finished. [worker-1]: I0510 05:26:44.427874 281473111126912 gce_failure_handler_test.py:244] Training finished. I0510 05:26:45.112642 281473286435712 multi_process_runner.py:646] worker-0 exit code: 0 I0510 05:26:45.113004 281473286435712 multi_process_runner.py:646] worker-1 exit code: 0 I0510 05:26:45.113173 281473286435712 multi_process_runner.py:646] worker-2 exit code: 0 I0510 05:26:45.113326 281473286435712 multi_process_runner.py:646] worker-3 exit code: 0 I0510 05:26:45.116791 281473286435712 multi_process_runner.py:662] Joining log reading threads. I0510 05:26:45.117149 281473286435712 multi_process_runner.py:665] Joined log reading threads. INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_7_inputarg_checkpoint_strategyoption_MWMSmultiworker): 13.46s I0510 05:26:45.294326 281473286435712 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_7_inputarg_checkpoint_strategyoption_MWMSmultiworker): 13.46s [ OK ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_7_inputarg_checkpoint_strategyoption_MWMSmultiworker ====================================================================== FAIL: test_basic_run_test_inputarg_checkpoint_strategyoption_MWMSmultiworker (__main__.GceFailureHandlingTest) GceFailureHandlingTest.test_basic_run_test_inputarg_checkpoint_strategyoption_MWMSmultiworker test_basic_run_test_inputarg_checkpoint_strategyoption_MWMSmultiworker(input_arg='checkpoint', strategy_option='MWMS_multi_worker') ---------------------------------------------------------------------- Traceback (most recent call last): File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/parameterized.py", line 314, in bound_param_test return test_method(self, **testcase_params) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/framework/test_combinations.py", line 360, in decorated execute_test_method() File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/framework/test_combinations.py", line 343, in execute_test_method test_method(**kwargs_to_pass) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/combinations.py", line 559, in decorator test_method(self, **kwargs) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 329, in test_basic_run mpr.join(timeout=250) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 649, in join self._reraise_if_subprocess_error(process_statuses) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 565, in _reraise_if_subprocess_error six.reraise(*process_status.exc_info) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/six_archive/six.py", line 719, in reraise raise value File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 1060, in _run_contained return_value = fn(*args, **kwargs) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/org_tensorflow/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.py", line 211, in worker_fn self.assertNotEmpty(checkpoint_index) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 972, in assertNotEmpty self.fail('{!r} has length of 0.'.format(container), msg) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/python/distribute/failure_handling/gce_failure_handler_test.runfiles/absl_py/absl/testing/absltest.py", line 1814, in fail return super(TestCase, self).fail(self._formatMessage(prefix, msg)) File "/usr/lib/python3.10/unittest/case.py", line 675, in fail raise self.failureException(msg) AssertionError: [] has length of 0. ---------------------------------------------------------------------- Ran 7 tests in 99.911s FAILED (failures=1) ================================================================================ ==================== Test output for //tensorflow/dtensor/python/tests:input_util_test (shard 1 of 8): 2023-05-10 05:35:11.837831: I tensorflow/core/util/port.cc:116] Experimental oneDNN custom operations are on. If you experience issues, please turn them off by setting the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. Running tests under Python 3.10.11: /usr/local/bin/python3 [ RUN ] DTensorDatasetTest.testForInIterationEager I0510 05:35:16.547402 281472902132608 mesh_util.py:35] This is client 0 of 1 clients I0510 05:35:16.547659 281472902132608 mesh_util.py:36] Number of global CPU devices: 16 I0510 05:35:16.547829 281472902132608 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0510 05:35:16.548380 281472902132608 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0510 05:35:16.548575 281472902132608 mesh_util.py:41] Local devices: ['/job:localhost/replica:0/task:0/device:CPU:0', '/job:localhost/replica:0/task:0/device:CPU:1', '/job:localhost/replica:0/task:0/device:CPU:2', '/job:localhost/replica:0/task:0/device:CPU:3', '/job:localhost/replica:0/task:0/device:CPU:4', '/job:localhost/replica:0/task:0/device:CPU:5', '/job:localhost/replica:0/task:0/device:CPU:6', '/job:localhost/replica:0/task:0/device:CPU:7', '/job:localhost/replica:0/task:0/device:CPU:8', '/job:localhost/replica:0/task:0/device:CPU:9', '/job:localhost/replica:0/task:0/device:CPU:10', '/job:localhost/replica:0/task:0/device:CPU:11', '/job:localhost/replica:0/task:0/device:CPU:12', '/job:localhost/replica:0/task:0/device:CPU:13', '/job:localhost/replica:0/task:0/device:CPU:14', '/job:localhost/replica:0/task:0/device:CPU:15'] 2023-05-10 05:35:17.018487: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_0' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_0}}]] 2023-05-10 05:35:17.088164: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:17.149776: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:17.258253: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:17.313746: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:17.354447: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:17.355202: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:17.497957: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:17.498660: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:17.567214: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:17.567934: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:17.703280: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:17.704048: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:17.845722: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:17.846488: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:17.997916: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:17.998622: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:18.083756: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:18.084477: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:18.161103: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:18.161888: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:18.307318: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:18.308048: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:18.485567: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:18.486350: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:18.594384: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:18.595118: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:18.766037: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:18.767027: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:18.885061: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:18.885828: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:18.975638: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:18.976506: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:19.075691: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:19.076503: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:19.174281: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_14' with dtype int32 and shape [3,4] [[{{node Placeholder/_14}}]] 2023-05-10 05:35:19.175037: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [32,8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:19.990005: I tensorflow/core/common_runtime/executor.cc:1210] [/job:localhost/replica:0/task:0/device:CPU:13] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Operation was cancelled [[{{node tf.StatefulPartitionedCall/eager_operation}}]] 2023-05-10 05:35:19.992096: E tensorflow/dtensor/cc/dtensor_device.cc:2212] Encountered error while executing function: CopyToMesh__func_11982211519516188344_5950845106898307211_6858324592425701659_1 for mesh : |batch=4,height=2,width=2|0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15|0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15|/job:localhost/replica:0/task:0/device:CPU:0,/job:localhost/replica:0/task:0/device:CPU:1,/job:localhost/replica:0/task:0/device:CPU:2,/job:localhost/replica:0/task:0/device:CPU:3,/job:localhost/replica:0/task:0/device:CPU:4,/job:localhost/replica:0/task:0/device:CPU:5,/job:localhost/replica:0/task:0/device:CPU:6,/job:localhost/replica:0/task:0/device:CPU:7,/job:localhost/replica:0/task:0/device:CPU:8,/job:localhost/replica:0/task:0/device:CPU:9,/job:localhost/replica:0/task:0/device:CPU:10,/job:localhost/replica:0/task:0/device:CPU:11,/job:localhost/replica:0/task:0/device:CPU:12,/job:localhost/replica:0/task:0/device:CPU:13,/job:localhost/replica:0/task:0/device:CPU:14,/job:localhost/replica:0/task:0/device:CPU:15 / error : {{function_node IteratorGetNext__func_16384237157704047660_12989052755378955192_1628789561242421788_0}} End of sequence [[{{node tf.StatefulPartitionedCall/eager_operation}}]] Encountered when executing an operation using EagerExecutor. This error cancels all future operations and poisons their output tensors. 2023-05-10 05:35:20.049021: E tensorflow/dtensor/cc/dtensor_device.cc:2246] Error executing CopyToMesh {{function_node IteratorGetNext__func_16384237157704047660_12989052755378955192_1628789561242421788_0}} End of sequence [[{{node tf.StatefulPartitionedCall/eager_operation}}]] Encountered when executing an operation using EagerExecutor. This error cancels all future operations and poisons their output tensors. INFO:tensorflow:time(__main__.DTensorDatasetTest.testForInIterationEager): 3.65s I0510 05:35:20.201097 281472902132608 test_util.py:2464] time(__main__.DTensorDatasetTest.testForInIterationEager): 3.65s [ FAILED ] DTensorDatasetTest.testForInIterationEager [ RUN ] DTensorDatasetTest.testIterOnBatchedDatasetGraph I0510 05:35:20.204888 281472902132608 mesh_util.py:35] This is client 0 of 1 clients I0510 05:35:20.205098 281472902132608 mesh_util.py:36] Number of global CPU devices: 16 I0510 05:35:20.205265 281472902132608 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0510 05:35:20.205736 281472902132608 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0510 05:35:20.205883 281472902132608 mesh_util.py:41] Local devices: ['/job:localhost/replica:0/task:0/device:CPU:0', '/job:localhost/replica:0/task:0/device:CPU:1', '/job:localhost/replica:0/task:0/device:CPU:2', '/job:localhost/replica:0/task:0/device:CPU:3', '/job:localhost/replica:0/task:0/device:CPU:4', '/job:localhost/replica:0/task:0/device:CPU:5', '/job:localhost/replica:0/task:0/device:CPU:6', '/job:localhost/replica:0/task:0/device:CPU:7', '/job:localhost/replica:0/task:0/device:CPU:8', '/job:localhost/replica:0/task:0/device:CPU:9', '/job:localhost/replica:0/task:0/device:CPU:10', '/job:localhost/replica:0/task:0/device:CPU:11', '/job:localhost/replica:0/task:0/device:CPU:12', '/job:localhost/replica:0/task:0/device:CPU:13', '/job:localhost/replica:0/task:0/device:CPU:14', '/job:localhost/replica:0/task:0/device:CPU:15'] 2023-05-10 05:35:20.556212: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:20.644670: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:20.743109: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:20.816592: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:20.876711: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:20.877598: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:20.973310: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:20.974198: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:21.080087: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:21.081039: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:21.164637: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:21.165538: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:21.307282: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:21.308175: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:21.570024: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:21.570921: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:21.728970: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:21.729908: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:21.925599: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:21.926595: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:21.997025: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:21.997976: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:22.227854: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:22.228786: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:22.391491: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:22.392395: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:22.634946: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:22.635910: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:22.800269: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:22.801205: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:22.892850: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:22.893811: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:23.035693: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:23.036705: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:23.172035: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:23.173609: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:23.350208: I tensorflow/dtensor/cc/dtensor_device.cc:1574] DTensor cache key lookup missed for __inference_train_619. DTensor is (re-)computing its SPMD transformation. 2023-05-10 05:35:23.357651: I tensorflow/dtensor/cc/dtensor_device.cc:1643] DTensor cache key lookup missed for __inference_train_619. DTensor is (re-)computing its ExecutionFunctions. 2023-05-10 05:35:23.586283: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_1' with dtype float and shape [1] [[{{node Placeholder/_1}}]] INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterOnBatchedDatasetGraph): 4.29s I0510 05:35:24.495996 281472902132608 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterOnBatchedDatasetGraph): 4.29s [ OK ] DTensorDatasetTest.testIterOnBatchedDatasetGraph [ RUN ] DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True) I0510 05:35:24.497569 281472902132608 mesh_util.py:35] This is client 0 of 1 clients I0510 05:35:24.497730 281472902132608 mesh_util.py:36] Number of global CPU devices: 16 I0510 05:35:24.497886 281472902132608 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0510 05:35:24.498342 281472902132608 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0510 05:35:24.498490 281472902132608 mesh_util.py:41] Local devices: ['/job:localhost/replica:0/task:0/device:CPU:0', '/job:localhost/replica:0/task:0/device:CPU:1', '/job:localhost/replica:0/task:0/device:CPU:2', '/job:localhost/replica:0/task:0/device:CPU:3', '/job:localhost/replica:0/task:0/device:CPU:4', '/job:localhost/replica:0/task:0/device:CPU:5', '/job:localhost/replica:0/task:0/device:CPU:6', '/job:localhost/replica:0/task:0/device:CPU:7', '/job:localhost/replica:0/task:0/device:CPU:8', '/job:localhost/replica:0/task:0/device:CPU:9', '/job:localhost/replica:0/task:0/device:CPU:10', '/job:localhost/replica:0/task:0/device:CPU:11', '/job:localhost/replica:0/task:0/device:CPU:12', '/job:localhost/replica:0/task:0/device:CPU:13', '/job:localhost/replica:0/task:0/device:CPU:14', '/job:localhost/replica:0/task:0/device:CPU:15'] 2023-05-10 05:35:24.757504: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:24.813339: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:24.814270: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:24.993339: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:24.994250: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:25.114415: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:25.115364: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:25.209900: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:25.210815: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:25.515388: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:25.516366: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:25.731114: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:25.732060: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:26.061224: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:26.062159: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:26.144170: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:26.145143: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:26.301775: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:26.302721: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:26.419267: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:26.420228: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:26.535152: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:26.536082: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:26.693745: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:26.694668: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:26.761639: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:26.762556: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:26.936676: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:26.937614: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:27.008440: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:27.009339: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:27.162156: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:27.163054: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:27.580254: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_1' with dtype float and shape [1] [[{{node Placeholder/_1}}]] INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True)): 3.95s I0510 05:35:28.447618 281472902132608 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True)): 3.95s [ OK ] DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True) [ RUN ] DTensorDatasetTest.testIterWithLayouts17 (images_sharding=['batch', 'height', 'width', 'unsharded'], labels_sharding=['batch', 'unsharded'], is_graph=False, through_dtensor=True) I0510 05:35:28.449077 281472902132608 mesh_util.py:35] This is client 0 of 1 clients I0510 05:35:28.449240 281472902132608 mesh_util.py:36] Number of global CPU devices: 16 I0510 05:35:28.449398 281472902132608 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0510 05:35:28.449845 281472902132608 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0510 05:35:28.449989 281472902132608 mesh_util.py:41] Local devices: ['/job:localhost/replica:0/task:0/device:CPU:0', '/job:localhost/replica:0/task:0/device:CPU:1', '/job:localhost/replica:0/task:0/device:CPU:2', '/job:localhost/replica:0/task:0/device:CPU:3', '/job:localhost/replica:0/task:0/device:CPU:4', '/job:localhost/replica:0/task:0/device:CPU:5', '/job:localhost/replica:0/task:0/device:CPU:6', '/job:localhost/replica:0/task:0/device:CPU:7', '/job:localhost/replica:0/task:0/device:CPU:8', '/job:localhost/replica:0/task:0/device:CPU:9', '/job:localhost/replica:0/task:0/device:CPU:10', '/job:localhost/replica:0/task:0/device:CPU:11', '/job:localhost/replica:0/task:0/device:CPU:12', '/job:localhost/replica:0/task:0/device:CPU:13', '/job:localhost/replica:0/task:0/device:CPU:14', '/job:localhost/replica:0/task:0/device:CPU:15'] 2023-05-10 05:35:28.838724: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:28.917858: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:28.987897: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:29.197841: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:29.277560: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:29.278439: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:29.394408: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:29.395327: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:29.512118: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:29.513033: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:29.837260: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:29.838181: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:30.073044: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:30.073927: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:30.234580: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:30.235505: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:30.338662: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:30.339573: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:30.478959: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:30.479859: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:30.645536: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:30.666642: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:30.827853: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:30.828823: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:30.976016: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:30.977072: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:31.380458: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:31.381425: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:31.535114: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:31.536050: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:31.776144: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:31.777444: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:31.865570: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:31.866608: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:31.953766: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:31.954695: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:32.320915: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_1' with dtype float and shape [1] [[{{node Placeholder/_1}}]] INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts17 (images_sharding=['batch', 'height', 'width', 'unsharded'], labels_sharding=['batch', 'unsharded'], is_graph=False, through_dtensor=True)): 4.66s I0510 05:35:33.104053 281472902132608 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts17 (images_sharding=['batch', 'height', 'width', 'unsharded'], labels_sharding=['batch', 'unsharded'], is_graph=False, through_dtensor=True)): 4.66s [ OK ] DTensorDatasetTest.testIterWithLayouts17 (images_sharding=['batch', 'height', 'width', 'unsharded'], labels_sharding=['batch', 'unsharded'], is_graph=False, through_dtensor=True) [ RUN ] DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True) I0510 05:35:33.105690 281472902132608 mesh_util.py:35] This is client 0 of 1 clients I0510 05:35:33.105880 281472902132608 mesh_util.py:36] Number of global CPU devices: 16 I0510 05:35:33.106039 281472902132608 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0510 05:35:33.147606 281472902132608 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0510 05:35:33.147829 281472902132608 mesh_util.py:41] Local devices: ['/job:localhost/replica:0/task:0/device:CPU:0', '/job:localhost/replica:0/task:0/device:CPU:1', '/job:localhost/replica:0/task:0/device:CPU:2', '/job:localhost/replica:0/task:0/device:CPU:3', '/job:localhost/replica:0/task:0/device:CPU:4', '/job:localhost/replica:0/task:0/device:CPU:5', '/job:localhost/replica:0/task:0/device:CPU:6', '/job:localhost/replica:0/task:0/device:CPU:7', '/job:localhost/replica:0/task:0/device:CPU:8', '/job:localhost/replica:0/task:0/device:CPU:9', '/job:localhost/replica:0/task:0/device:CPU:10', '/job:localhost/replica:0/task:0/device:CPU:11', '/job:localhost/replica:0/task:0/device:CPU:12', '/job:localhost/replica:0/task:0/device:CPU:13', '/job:localhost/replica:0/task:0/device:CPU:14', '/job:localhost/replica:0/task:0/device:CPU:15'] 2023-05-10 05:35:33.470033: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-10 05:35:33.564151: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:33.565059: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:33.724132: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:33.725017: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:33.882294: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:33.883234: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:33.965038: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:33.965989: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:34.090473: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:34.091404: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:34.245693: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:34.246644: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:34.358506: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:34.359425: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:34.588719: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:34.589633: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:34.762501: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:34.763426: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:34.840431: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:34.841369: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:34.960181: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:34.961083: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:35.151994: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:35.152980: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:35.353039: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:35.353952: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:35.600627: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:35.601563: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:35.895559: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype float and shape [8,8,3] [[{{node Placeholder/_4}}]] 2023-05-10 05:35:35.896665: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_5' with dtype float and shape [1] [[{{node Placeholder/_5}}]] 2023-05-10 05:35:36.064900: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_18' with dtype int32 and shape [3,2] [[{{node Placeholder/_18}}]] 2023-05-10 05:35:36.065808: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype int32 and shape [3,4] [[{{node Placeholder/_17}}]] 2023-05-10 05:35:36.357981: I tensorflow/dtensor/cc/dtensor_device.cc:1574] DTensor cache key lookup missed for __inference_train_1463. DTensor is (re-)computing its SPMD transformation. 2023-05-10 05:35:36.365619: I tensorflow/dtensor/cc/dtensor_device.cc:1643] DTensor cache key lookup missed for __inference_train_1463. DTensor is (re-)computing its ExecutionFunctions. 2023-05-10 05:35:36.676036: I tensorflow/core/common_runtime/executor.cc:1210] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_1' with dtype float and shape [1] [[{{node Placeholder/_1}}]] INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True)): 4.26s I0510 05:35:37.366254 281472902132608 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True)): 4.26s [ OK ] DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True) [ RUN ] DTensorDatasetTest.testMixedLayoutsFails I0510 05:35:37.367903 281472902132608 mesh_util.py:35] This is client 0 of 1 clients I0510 05:35:37.368087 281472902132608 mesh_util.py:36] Number of global CPU devices: 16 I0510 05:35:37.368245 281472902132608 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0510 05:35:37.368719 281472902132608 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0510 05:35:37.368867 281472902132608 mesh_util.py:41] Local devices: ['/job:localhost/replica:0/task:0/device:CPU:0', '/job:localhost/replica:0/task:0/device:CPU:1', '/job:localhost/replica:0/task:0/device:CPU:2', '/job:localhost/replica:0/task:0/device:CPU:3', '/job:localhost/replica:0/task:0/device:CPU:4', '/job:localhost/replica:0/task:0/device:CPU:5', '/job:localhost/replica:0/task:0/device:CPU:6', '/job:localhost/replica:0/task:0/device:CPU:7', '/job:localhost/replica:0/task:0/device:CPU:8', '/job:localhost/replica:0/task:0/device:CPU:9', '/job:localhost/replica:0/task:0/device:CPU:10', '/job:localhost/replica:0/task:0/device:CPU:11', '/job:localhost/replica:0/task:0/device:CPU:12', '/job:localhost/replica:0/task:0/device:CPU:13', '/job:localhost/replica:0/task:0/device:CPU:14', '/job:localhost/replica:0/task:0/device:CPU:15'] INFO:tensorflow:time(__main__.DTensorDatasetTest.testMixedLayoutsFails): 0.35s I0510 05:35:37.712424 281472902132608 test_util.py:2464] time(__main__.DTensorDatasetTest.testMixedLayoutsFails): 0.35s [ OK ] DTensorDatasetTest.testMixedLayoutsFails [ RUN ] InputUtilHelpersTest.testShardCounts1 (mesh_dims=[('batch', 8)], layout_specs=['batch'], batch_dim=None, counts=[8]) I0510 05:35:37.713890 281472902132608 mesh_util.py:35] This is client 0 of 1 clients I0510 05:35:37.714059 281472902132608 mesh_util.py:36] Number of global CPU devices: 8 I0510 05:35:37.714216 281472902132608 mesh_util.py:39] Global device IDs: [0 1 2 3 4 5 6 7] I0510 05:35:37.714570 281472902132608 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7] I0510 05:35:37.714708 281472902132608 mesh_util.py:41] Local devices: ['/job:localhost/replica:0/task:0/device:CPU:0', '/job:localhost/replica:0/task:0/device:CPU:1', '/job:localhost/replica:0/task:0/device:CPU:2', '/job:localhost/replica:0/task:0/device:CPU:3', '/job:localhost/replica:0/task:0/device:CPU:4', '/job:localhost/replica:0/task:0/device:CPU:5', '/job:localhost/replica:0/task:0/device:CPU:6', '/job:localhost/replica:0/task:0/device:CPU:7'] INFO:tensorflow:time(__main__.InputUtilHelpersTest.testShardCounts1 (mesh_dims=[('batch', 8)], layout_specs=['batch'], batch_dim=None, counts=[8])): 0.0s I0510 05:35:37.715178 281472902132608 test_util.py:2464] time(__main__.InputUtilHelpersTest.testShardCounts1 (mesh_dims=[('batch', 8)], layout_specs=['batch'], batch_dim=None, counts=[8])): 0.0s [ OK ] InputUtilHelpersTest.testShardCounts1 (mesh_dims=[('batch', 8)], layout_specs=['batch'], batch_dim=None, counts=[8]) ====================================================================== ERROR: testForInIterationEager (__main__.DTensorDatasetTest) DTensorDatasetTest.testForInIterationEager testForInIterationEager(False) ---------------------------------------------------------------------- Traceback (most recent call last): File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/dtensor/python/tests/input_util_test.runfiles/absl_py/absl/testing/parameterized.py", line 316, in bound_param_test return test_method(self, *testcase_params) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/dtensor/python/tests/input_util_test.runfiles/org_tensorflow/tensorflow/dtensor/python/tests/input_util_test.py", line 188, in testForInIteration self.assertDTensorEqual(output, images_layout, d_output) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/dtensor/python/tests/input_util_test.runfiles/org_tensorflow/tensorflow/dtensor/python/tests/test_util.py", line 303, in assertDTensorEqual unpacked = [t.numpy() for t in api.unpack(result_dtensor)] File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/dtensor/python/tests/input_util_test.runfiles/org_tensorflow/tensorflow/dtensor/python/api.py", line 352, in unpack return _dtensor_device().unpack(tensor) File "/home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/bin/tensorflow/dtensor/python/tests/input_util_test.runfiles/org_tensorflow/tensorflow/dtensor/python/dtensor_device.py", line 246, in unpack raise core._status_to_exception(e) from None # pylint: disable=protected-access tensorflow.python.framework.errors_impl.CancelledError: {{function_node AddV2__func_10002104140573508028_13230101824050524202_2386512056599665587_2}} Function was cancelled before it was started ---------------------------------------------------------------------- Ran 7 tests in 21.170s FAILED (errors=1) ================================================================================ //tensorflow/c:c_api_experimental_test PASSED in 36.6s //tensorflow/c:c_api_function_test PASSED in 35.9s //tensorflow/c:c_api_test_cpu PASSED in 44.3s //tensorflow/c:c_test PASSED in 34.6s //tensorflow/c:env_test_cpu PASSED in 33.4s //tensorflow/c:kernels_test_cpu PASSED in 52.1s //tensorflow/c:ops_test PASSED in 38.8s //tensorflow/c:while_loop_test PASSED in 42.1s //tensorflow/c/eager:c_api_cluster_test_cpu PASSED in 40.1s //tensorflow/c/eager:c_api_remote_function_test_cpu PASSED in 36.6s //tensorflow/c/eager:c_api_remote_test_cpu PASSED in 41.7s //tensorflow/c/eager:c_api_test_cpu PASSED in 45.7s //tensorflow/c/eager:custom_device_test PASSED in 41.5s //tensorflow/c/eager/parallel_device:parallel_device_lib_test PASSED in 42.0s //tensorflow/c/eager/parallel_device:parallel_device_remote_test PASSED in 39.4s //tensorflow/c/eager/parallel_device:parallel_device_test PASSED in 39.9s //tensorflow/c/experimental/filesystem/plugins/gcs:expiring_lru_cache_test PASSED in 0.3s //tensorflow/c/experimental/filesystem/plugins/gcs:ram_file_block_cache_test PASSED in 3.1s //tensorflow/c/experimental/grappler:grappler_test PASSED in 35.7s //tensorflow/c/experimental/ops/gen/common:case_format_test PASSED in 0.7s //tensorflow/c/experimental/ops/gen/cpp:cpp_generator_test PASSED in 1.0s //tensorflow/c/experimental/ops/gen/cpp/renderers:renderer_test PASSED in 2.7s //tensorflow/c/experimental/saved_model/core:constant_loading_test PASSED in 21.8s //tensorflow/c/experimental/saved_model/core:object_graph_traversal_test PASSED in 14.9s //tensorflow/c/experimental/saved_model/core:saved_variable_loading_test PASSED in 20.2s //tensorflow/c/experimental/saved_model/core:signature_flattening_test PASSED in 16.4s //tensorflow/c/experimental/saved_model/core:tf_concrete_function_loading_test PASSED in 19.1s //tensorflow/c/experimental/saved_model/core/ops:restore_ops_test PASSED in 20.3s //tensorflow/c/experimental/saved_model/core/ops:variable_ops_test PASSED in 16.2s //tensorflow/c/experimental/saved_model/internal:saved_model_api_test PASSED in 49.7s //tensorflow/c/experimental/stream_executor:stream_executor_test PASSED in 0.3s //tensorflow/c/kernels:bitcast_op_test PASSED in 0.6s //tensorflow/c/kernels:summary_op_benchmark_test PASSED in 0.6s //tensorflow/c/kernels:summary_op_test PASSED in 1.1s //tensorflow/c/kernels:tensor_shape_utils_test PASSED in 0.2s //tensorflow/cc:cc_op_gen_test PASSED in 0.9s //tensorflow/cc:client_client_session_test PASSED in 3.1s //tensorflow/cc:coordinator_test PASSED in 6.8s //tensorflow/cc:framework_cc_ops_test PASSED in 3.0s //tensorflow/cc:framework_gradient_checker_test PASSED in 3.7s //tensorflow/cc:framework_gradients_test PASSED in 6.8s //tensorflow/cc:framework_scope_test PASSED in 0.5s //tensorflow/cc:framework_while_gradients_test PASSED in 3.4s //tensorflow/cc:gradients_array_grad_test PASSED in 24.9s //tensorflow/cc:gradients_data_flow_grad_test PASSED in 2.6s //tensorflow/cc:gradients_functional_grad_test PASSED in 6.0s //tensorflow/cc:gradients_image_grad_test PASSED in 7.8s //tensorflow/cc:gradients_linalg_grad_test PASSED in 3.1s //tensorflow/cc:gradients_manip_grad_test PASSED in 2.7s //tensorflow/cc:gradients_math_grad_test PASSED in 10.4s //tensorflow/cc:gradients_nn_grad_test PASSED in 11.4s //tensorflow/cc:gradients_resource_variable_grad_test PASSED in 2.5s //tensorflow/cc:ops_const_op_test PASSED in 0.5s //tensorflow/cc:ops_while_loop_test PASSED in 2.7s //tensorflow/cc:queue_runner_test PASSED in 12.8s //tensorflow/cc/experimental/base/tests:tensor_test PASSED in 0.5s //tensorflow/cc/experimental/base/tests:tensorhandle_test PASSED in 36.7s //tensorflow/cc/experimental/libexport:load_test PASSED in 0.1s //tensorflow/cc/experimental/libexport:save_test PASSED in 0.2s //tensorflow/cc/experimental/libtf:libtf_module_test PASSED in 37.4s //tensorflow/cc/experimental/libtf:libtf_object_test PASSED in 0.5s //tensorflow/cc/experimental/libtf:libtf_perf_test PASSED in 0.7s //tensorflow/cc/experimental/libtf:libtf_runtime_test PASSED in 41.3s //tensorflow/cc/experimental/libtf:libtf_transform_test PASSED in 48.1s //tensorflow/cc/experimental/libtf:libtf_value_test PASSED in 0.3s //tensorflow/cc/experimental/libtf:libtf_visit_test PASSED in 0.1s //tensorflow/cc/experimental/libtf/impl:iostream_test PASSED in 0.1s //tensorflow/cc/experimental/libtf/impl:none_test PASSED in 0.1s //tensorflow/cc/experimental/libtf/impl:scalars_test PASSED in 0.5s //tensorflow/cc/experimental/libtf/impl:string_test PASSED in 0.5s //tensorflow/cc/experimental/libtf/impl:tensor_spec_test PASSED in 0.1s //tensorflow/cc/saved_model:bundle_v2_test PASSED in 0.1s //tensorflow/cc/saved_model:fingerprinting_test PASSED in 1.7s //tensorflow/cc/saved_model:metrics_test PASSED in 0.1s //tensorflow/cc/saved_model:reader_test PASSED in 0.2s //tensorflow/cc/saved_model:saved_model_bundle_lite_test PASSED in 8.7s //tensorflow/cc/saved_model:saved_model_bundle_test PASSED in 11.5s //tensorflow/cc/saved_model:util_test PASSED in 0.3s //tensorflow/cc/saved_model/experimental/tests:saved_model_api_test PASSED in 42.7s //tensorflow/cc/tools:freeze_saved_model_test PASSED in 2.6s //tensorflow/compiler/aot:codegen_test PASSED in 43.4s //tensorflow/compiler/jit:compilability_check_util_test PASSED in 24.9s //tensorflow/compiler/jit:deadness_analysis_test PASSED in 11.9s //tensorflow/compiler/jit:device_compilation_cache_test PASSED in 6.4s //tensorflow/compiler/jit:device_compilation_cluster_signature_test PASSED in 7.1s //tensorflow/compiler/jit:device_compilation_profiler_test PASSED in 34.7s //tensorflow/compiler/jit:device_compiler_client_test PASSED in 5.5s //tensorflow/compiler/jit:device_compiler_disable_test PASSED in 35.9s //tensorflow/compiler/jit:device_executable_persistor_test PASSED in 32.0s //tensorflow/compiler/jit:device_util_test PASSED in 7.7s //tensorflow/compiler/jit:encapsulate_util_test PASSED in 1.3s //tensorflow/compiler/jit:node_matchers_test PASSED in 4.1s //tensorflow/compiler/jit:resource_operation_safety_analysis_test PASSED in 10.7s //tensorflow/compiler/jit:shape_inference_test PASSED in 0.9s //tensorflow/compiler/jit:xla_activity_listener_test PASSED in 31.6s //tensorflow/compiler/jit:xla_cluster_util_test PASSED in 9.7s //tensorflow/compiler/jit:xla_compile_util_test PASSED in 5.6s //tensorflow/compiler/jit:xla_kernel_creator_test PASSED in 10.9s //tensorflow/compiler/jit:xla_launch_util_test PASSED in 35.9s //tensorflow/compiler/jit/tests:auto_clustering_test PASSED in 32.6s //tensorflow/compiler/mlir:mlir_graph_optimization_pass_test PASSED in 15.1s //tensorflow/compiler/mlir:register_common_dialects_test PASSED in 19.1s //tensorflow/compiler/mlir/lite:lstm_utils_test PASSED in 1.7s //tensorflow/compiler/mlir/lite:perception_ops_utils_test PASSED in 0.9s //tensorflow/compiler/mlir/lite:size_utils_test PASSED in 0.1s //tensorflow/compiler/mlir/lite:tftext_utils_test PASSED in 0.5s //tensorflow/compiler/mlir/lite/experimental/remat:rematerializer_test PASSED in 1.1s //tensorflow/compiler/mlir/lite/experimental/tac:execution_metadata_exporter_test PASSED in 3.5s //tensorflow/compiler/mlir/lite/experimental/tac/tests:compute-cost.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/experimental/tac/tests:device-transform-gpu.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/experimental/tac/tests:device-transform-nnapi.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/lite/experimental/tac/tests:fold-constants-to-subgraph.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/experimental/tac/tests:get-alternative-subgraph.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/experimental/tac/tests:get-op-cost.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/experimental/tac/tests:pick-subgraphs.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/experimental/tac/tests:raise-target-subgraphs.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/experimental/tac/tests:target-annotation.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/experimental/tac/tests/e2e:device-transform-nnapi.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/experimental/tac/tests/e2e:simple-graph.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/metrics:error_collector_inst_test PASSED in 0.3s //tensorflow/compiler/mlir/lite/quantization:numerical_utils_test PASSED in 0.6s //tensorflow/compiler/mlir/lite/quantization/lite:quantize_model_test PASSED in 16.9s //tensorflow/compiler/mlir/lite/quantization/lite:quantize_weights_test PASSED in 13.0s //tensorflow/compiler/mlir/lite/quantization/tensorflow/tests:fallback_to_flex_ops_default.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/quantization/tensorflow/tests:fallback_to_flex_ops_legacy.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/quantization/tensorflow/tests:tf_to_quant.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/quantization/tensorflow/tests:tf_to_quant_4bit.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/quantization/tests:import_quant_stats.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/sparsity:sparsify_model_test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:fold_broadcast.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:fuse_mhlo_convolution.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-inplaceupdate.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-skip-quantization-ops.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tf-fb-tf.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-add.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-broadcast_in_dim.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-clamp.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-compare.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-concat.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-constant.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-conv.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-dot.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-gather.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-max.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-mul.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-pad.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-reshape.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-rsqrt.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-scatter.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-sub.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-add.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-broadcast.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-clamp.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-concat.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-constant.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-conv.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-max.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-mul.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-pad.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-reshape.mlir.test PASSED in 4.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-rsqrt.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-sub.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/stablehlo/tests:odml-to-stablehlo-allow-tf.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/stablehlo/tests:odml-to-stablehlo-smuggle-resize.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/stablehlo/tests:optimize.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-clamp.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-concat.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-conv.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-division.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-logistic.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-multiply.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-reduce-window.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-resize-bilinear.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-subtract.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-tf-quantize.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:unfuse_mhlo_batch_norm.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/tests:analyze-variables.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:canonicalize.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:const-fold.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests:decompose-hybrid-quantization.mlir.test PASSED in 2.1s //tensorflow/compiler/mlir/lite/tests:default_quant_params.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/tests:dilated-conv.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:fuse-tftext.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/lite/tests:get-arithmetic-count.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:guarantee_func_has_one_use.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests:inlining.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests:insert_call_once_op.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:legalize-tf-assert.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:legalize-tf-hashtables.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests:legalize-tf-no-runtime-verification.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:legalize-tf-variables.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:legalize-tf-while.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests:legalize-tf.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/lite/tests:legalize_jax_random.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:lift_tflite_flex_ops.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests:lower-static-tensor-list-default-to-single-batch.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests:lower-static-tensor-list-enable-dynamic-update-slice.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests:lower-static-tensor-list.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:modify_io_nodes.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests:ops.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:optimize-after-quantization.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:optimize.mlir.test PASSED in 2.8s //tensorflow/compiler/mlir/lite/tests:optimize_functional_ops.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/lite/tests:optimize_no_verify.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:optimize_op_order.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:partitioned-topological-sort.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:pin-ops-with-side-effects.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:post-quantize-dynamic-range.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests:post-quantize.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests:prepare-composite-functions-tf.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/lite/tests:prepare-quantize-dynamic-range.mlir.test PASSED in 3.1s //tensorflow/compiler/mlir/lite/tests:prepare-quantize-post-training-16bits.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:prepare-quantize-post-training.mlir.test PASSED in 2.6s //tensorflow/compiler/mlir/lite/tests:prepare-quantize-signed.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:prepare-quantize.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests:prepare-tf-fake-quant-4bit.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:prepare-tf-fake-quant.mlir.test PASSED in 2.2s //tensorflow/compiler/mlir/lite/tests:prepare-tf-with-allowing-bf16-and-f16-type-legalization.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:prepare-tf.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests:quantize-dynamic-range.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/lite/tests:quantize-numeric-verify.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests:quantize-variables.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:quantize.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/lite/tests:raise-custom-ops.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:reduce_while_operands.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:shape-inference.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:split-merged-operands.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:tfl_while_op_licm.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:tfl_while_outline.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:trim-functions-tf.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:unfold-large-splat-constant.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/debuginfo:v1_1.0_224_frozen.wrong_attr.line.part.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/debuginfo:v1_1.0_224_frozen.wrong_attr.stack.part.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/end2end:add.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/end2end:back2back_fake_quant.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/end2end:control_flow_v1.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/end2end:conv_2d.pbtxt.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/tests/end2end:conv_2d_nchw.pbtxt.test PASSED in 1.9s //tensorflow/compiler/mlir/lite/tests/end2end:custom_opdef.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/end2end:disallow_stateful_partitioned_call.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/end2end:fake_quant_per_channel.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/end2end:fake_quant_per_channel_4bit.pbtxt.test PASSED in 2.2s //tensorflow/compiler/mlir/lite/tests/end2end:fake_quant_without_identity.pbtxt.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/tests/end2end:fake_quant_without_identity_4bit.pbtxt.test PASSED in 2.4s //tensorflow/compiler/mlir/lite/tests/end2end:graph-input-node.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/end2end:graph_with_placeholder_with_default.pbtxt.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/end2end:if_op.pbtxt.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/tests/end2end:quant_stats.pbtxt.test PASSED in 1.7s //tensorflow/compiler/mlir/lite/tests/end2end:unroll_batch_matmul.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/end2end:unroll_batch_matmul_disabled.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:basic_lstm.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:bucketize.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:constants.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:control_edges.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:custom_op.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:dynamic_shape.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:external_constant.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:if_op.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:import_json.json.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:importer_test_min_max.cc.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:importer_test_min_max.cc.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:input_arrays.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:input_output_names_attr.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:legacy_reshape.json.test PASSED in 1.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:lstm.json.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:lstm.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:many_attribute_op.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:math.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:matmul.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:multi_output_op.json.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:optional.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:optional_input.json.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:output_arrays.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:pruning.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:pruning_function_input_as_output.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:quant_stats.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:quantization.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:reshape.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:signature.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:signature_with_multiple_entry_points.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:simple.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:tf_variant_type.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:unranked_function_output.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:unranked_tensor.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:while_op.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2exec:tfl_while_op.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:basic_lstm.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:bucketize.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:custom_op_with_tflite_op.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:depthwise_conv2d.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:depthwise_conv2d_v2.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:disable_builtin.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:disable_custom.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:disable_flex.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:disable_flex_enable_builtin.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:dynamic_shape_constant.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:fake_quant.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:flex_exclusively.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:flex_op_with_complex128.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:flex_op_with_f64.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:flex_op_with_tflite_op.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:fully_connected.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:fully_connected_v2.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:hashtable_resource.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:if_op.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:logical.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:low_bit_packing.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:lstm.mlir.test PASSED in 0.4s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:lstm_asym_attr.mlir.test PASSED in 0.4s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:lstm_quantized.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:math.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:metadata.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:mul_v2.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:mul_v3.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:nn.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:numeric_verify.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:optional.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:quantization.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:reshape.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:signature_def.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:signature_def_output_override.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:signature_def_with_multiple_entry_points.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:signature_def_with_no_inputs.mlir.test PASSED in 3.1s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:simple.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:simple_with_connected_control_nodes.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:simple_with_unconnected_control_nodes.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:svdf.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:svdf_v2.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:tf_entry_function.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:tfl_while_op.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:transpose_conv_optional.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:type_attr.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:unidirectional_sequence_lstm.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:unidirectional_sequence_rnn.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:unranked_tensor.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:unsorted_segment_prod.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:variant_type_on_func.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:variant_type_on_op.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:while_op.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/calibrator:calibrator_singleton_test PASSED in 0.4s //tensorflow/compiler/mlir/quantization/tensorflow/calibrator:custom_aggregator_op_test PASSED in 15.2s //tensorflow/compiler/mlir/quantization/tensorflow/cc:const_op_size_test PASSED in 0.4s //tensorflow/compiler/mlir/quantization/tensorflow/cc:convert_asset_args_test PASSED in 6.4s //tensorflow/compiler/mlir/quantization/tensorflow/cc:save_variables_test PASSED in 0.8s //tensorflow/compiler/mlir/quantization/tensorflow/cc:status_macro_test PASSED in 0.1s //tensorflow/compiler/mlir/quantization/tensorflow/debugging:mlir_dump_test PASSED in 0.1s //tensorflow/compiler/mlir/quantization/tensorflow/python:concurrency_test PASSED in 39.4s //tensorflow/compiler/mlir/quantization/tensorflow/python:pywrap_quantize_model_test PASSED in 19.7s //tensorflow/compiler/mlir/quantization/tensorflow/python:representative_dataset_test PASSED in 8.2s //tensorflow/compiler/mlir/quantization/tensorflow/tests:cast_bf16_ops_to_f32.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/quantization/tensorflow/tests:convert_custom_aggregation_op_to_quant_stats.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/quantization/tensorflow/tests:convert_fake_quant_to_qdq.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/quantization/tensorflow/tests:convert_tf_quant_ops_to_mhlo.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/quantization/tensorflow/tests:convert_tpu_model_to_cpu.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:duplicate_shape_determining_constants.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/quantization/tensorflow/tests:fake_quant_e2e_flow.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/quantization/tensorflow/tests:fake_quant_e2e_xla.mlir.test PASSED in 2.4s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_custom_aggregation_ops.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_main_function.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_quantized_functions.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_quantized_functions_drq.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_quantized_functions_weight_only.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_restore_op.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_save_op.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/quantization/tensorflow/tests:issue_ids_of_custom_aggregation_ops.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/quantization/tensorflow/tests:lift_quantizable_spots_as_functions.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/quantization/tensorflow/tests:lift_quantizable_spots_as_functions_drq.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/quantization/tensorflow/tests:lift_quantizable_spots_as_functions_drq_min_elements.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/quantization/tensorflow/tests:lift_quantizable_spots_as_functions_xla.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:mark_functions_noinline.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/quantization/tensorflow/tests:merge_initializer_function_ops_to_main.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:merge_save_function_ops_to_main.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/quantization/tensorflow/tests:optimize.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_lifting.mlir.test PASSED in 2.2s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize_drq.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize_drq_per_channel.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize_ptq.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize_ptq_per_channel.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/quantization/tensorflow/tests:preprocess_op.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_composite_functions.mlir.test PASSED in 3.5s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_composite_functions_drq.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_composite_functions_weight_only.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_composite_functions_xla.mlir.test PASSED in 2.3s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_drq.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_xla.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/quantization/tensorflow/tests:remove_var_init_by_const.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:replace_cast_hacks_with_tf_xla_ops.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/quantization/tensorflow/tests:replace_cast_hacks_with_tf_xla_ops_large_constants.mlir.test PASSED in 14.9s //tensorflow/compiler/mlir/quantization/tensorflow/tests:unfreeze_constants.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/quantization/tensorflow/utils:tf_to_xla_attribute_utils_test PASSED in 40.0s //tensorflow/compiler/mlir/tensorflow:bridge_logger_test PASSED in 8.6s //tensorflow/compiler/mlir/tensorflow:cluster_util_test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow:convert_tensor_test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow:convert_type_test PASSED in 0.3s //tensorflow/compiler/mlir/tensorflow:device_util_test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow:dump_graph_test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow:dump_mlir_util_test PASSED in 11.1s //tensorflow/compiler/mlir/tensorflow:error_util_test PASSED in 0.1s //tensorflow/compiler/mlir/tensorflow:tf_saved_model_test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow:tpu_rewrite_device_util_test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:add_functions_for_exported_names.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:annotate-parameter-replication.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:batchmatmul_to_einsum.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:breakup-islands.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:cannonicalize_ops_outside_compilation.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:canonicalize.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:canonicalize_compile_and_replicate_attributes.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:check_control_dependencies.mlir.test PASSED in 2.1s //tensorflow/compiler/mlir/tensorflow/tests:cluster_formation.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:cluster_ops_by_policy.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:cluster_outlining.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:cluster_tf_ops_pass.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:constant-fold.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:constant_op_device_assignment.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:convert-tf-control-flow-to-scf.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:convert_control_to_data_outputs.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:convert_launch_func_to_tf_call.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:convert_session_initializer_to_function.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:convert_to_legacy_compile_and_replicate_attributes.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:decompose_reduce_dataset.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:decompose_resource_ops.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:device_assignment.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:device_assignment_by_func_attr.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:device_attribute_to_launch.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:device_canonicalize.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:device_copy.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:drop_while_shape_invariant.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:einsum.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:embedding_pipelining.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:empty-main.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:end-to-end-tpu-reshard-variables.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:executor_canonicalize.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:executor_island_coarsening.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:executor_island_materialize_const.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:extract_head_tail_outside_compilation.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:extract_outside_compilation.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:extract_tpu_copy_with_dynamic_shape_op.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:fold-broadcast.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:freeze_variables.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:func-attr-invalid.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:func-attr.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:functional-control-flow-to-cfg.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests:functional-control-flow-to-regions.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/tensorflow/tests:functionalize-if-fail.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:functionalize-if.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:fused_kernel_matcher.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:gpu_fusion.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:graph_pruning.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:graph_pruning_preserve_ops.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:group_by_dialect.mlir.test PASSED in 2.2s //tensorflow/compiler/mlir/tensorflow/tests:guarantee-all-funcs-one-use.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:hoist_loop_invariant.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:hoist_replicate_invariant_resource_writes.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:host_launch_to_outside_compiled.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:init_text_file_to_import.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:init_text_file_to_import_invalid.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:init_text_file_to_import_saved_model.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:inlining.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:isolate-placer.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:launch_outlining.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:launch_to_device_attribute.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:launch_to_device_attribute_legacy.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_layout_assignment_gpu_cc_60.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_layout_assignment_gpu_cc_70.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_layout_assignment_to_nchw.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_layout_assignment_to_nhwc.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_move_transposes_begin.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_move_transposes_end.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_to_nchw.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_to_nhwc.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:legalize_hlo.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:legalize_tfg.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:legalize_tfg_arg_control_dep.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:legalize_tfg_with_control_flow.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:localize_var_handles.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:lower_globals_to_ml_program.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:lower_globals_to_ml_program_invalid.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:lower_quantized.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:lower_tf.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/tensorflow/tests:lower_variable_ops_to_ml_program.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:mark_input_output_aliases.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:mark_ops_for_outside_compilation.mlir.test PASSED in 2.6s //tensorflow/compiler/mlir/tensorflow/tests:materialize_passthrough_op.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:merge_control_flow.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:mlprogram.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:name_anonymous_iterators.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:optimize-arg-operand-constraint.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:optimize.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:order_by_dialect.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:outside_compiled_to_host_launch.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:parallel_execute_to_islands.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:parallel_execute_to_islands_legacy.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:prepare_tpu_computation_for_tf_export.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:promote_resources_to_args.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:promote_resources_to_args_functions.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:promote_var_handles_to_args.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:readonly_references_to_resources.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:region-control-flow-to-functional.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:remove_unused_arguments.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:remove_unused_while_results.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:replica_id_to_device_ordinal.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:replicate_invariant_op_hoisting.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:replicate_tensor_list_init_ops.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:replicate_to_island.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:replicate_to_island_legacy.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:resource-alias-analysis-test.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:resource-device-inference.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:resource_analyzer.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:resource_inlining.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:resource_op_lifting.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:rewrite_tpu_embedding_ops.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:roundtrip-tf-executor.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:shape_inference.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests:side-effect-analysis-test.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:sink_constant.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:split_into_island_per_op.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:stack_ops_decomposition.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:strip_noinline.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:strip_saved_module_metadata.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:strip_tf_attributes.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tensor_array_ops_decomposition.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:tensor_list_ops_decomposition.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tf-executor-to-functional.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf-functional-to-executor.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tf-ops.mlir.test PASSED in 3.1s //tensorflow/compiler/mlir/tensorflow/tests:tf-reduce-identity.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tf_data_fuse_map_and_batch.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tf_data_fuse_pmap_and_batch.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:tf_device_index_selector.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_device_ops.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:tf_device_ops_invalid.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops_invalid.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops_location_roundtrip.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops_printer.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops_side_effect.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:tf_optimize.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_deduplicate_bound_input_bindings.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_freeze_assets.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_freeze_global_tensors.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_freeze_global_tensors_mutable_tensors.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_initialize_variables_in_session_init.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_initialize_variables_in_session_init_fail.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_lift_variables.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_lift_variables_invalid_session.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_mark_initialized_variables.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_ops.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_ops_invalid.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_optimize_global_tensors.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_optimize_global_tensors_interprocedural.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_remove_vars_in_session_initializer.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_side_effect.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:tf_trait_folds.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tpu-annotate-dynamic-shape-inputs.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:tpu-cluster-cleanup-attributes.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tpu-dynamic-layout-pass.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu-merge-variables-with-execute.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tpu-multiple-while-body-func.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tpu-resource-read-for-write.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu-variable-runtime-reformatting.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tpu_cluster_formation.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu_colocate_composite_resource_ops.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tpu_colocate_splits.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:tpu_device_propagation.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tpu_host_computation_expansion.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/tensorflow/tests:tpu_identity_pruning.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tpu_parallel_execute_sink_resource_write.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu_partitioned_op_conversion.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:tpu_reorder_replicate_and_partitioned_inputs.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tpu_resource_partitioning.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tpu_rewrite.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:tpu_sharding_identification.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu_space_to_depth_pass.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tpu_tail_with_tobool_op.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:tpu_update_embedding_enqueue_op_inputs.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:tpu_validate_inputs.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:transpose-op.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:unroll-batch-matmul.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:update_control_dependencies.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:warn_when_using_deprecated_dumps.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:while_licm.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:xla_cluster_formation.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:xla_inline_device_ops.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:xla_rewrite.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:add.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:argument-sharding-invalid.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:argument-sharding.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:constant-folding-hook.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:constant-folding.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:graph-resource.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:graph-resource.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:graph.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:mlir-module-serialized-str-attr.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:replicate-tensor-list-init-ops.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:result-sharding.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:serialized-mlir-module-str-attr-invalid.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:serialized-mlir-module-str-attr.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:shape-inference-after-legalization.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:shape-inference.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:stablehlo_add.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_island_coarsening:executor_tpuv1_island_coarsening.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_island_coarsening:while_op.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_island_inlining:executor_tpuv1_inline_tpu_island.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_island_inlining:while_op.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_outline_island:case_op.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_outline_island:executor_tpuv1_outline_tpu_island.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_outline_island:while_op.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:add.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-as-fetch.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-control-dep.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-data-type-with-subtype.pbtxt.test PASSED in 1.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-data-type.pbtxt.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-multi-data-type-with-subtype.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-retval-attrs.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:case_op.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:const-values.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:device-arg-retval-attr.pbtxt.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:empty-input-shapes.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:empty-value-attr.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:feed-as-fetch.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:feed-control-dep.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:force_shared_name_for_resource_ops.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:function-func-attr.pbtxt.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:functional-if-ops.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:functional-while-ops.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-as-function-control-ret.pbtxt.test PASSED in 1.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-as-function-retval-of-arg.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-as-function.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-custom-operation.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-default-attr.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-device-retval.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-empty-tensor-content.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-func-attr.pbtxt.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-call.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-control-ret-diff-island.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-control-ret-same-island.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-defs.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-input-shapes.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-name-bug.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-resource-args.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-gradient-def.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-input-func-arg-name-collision.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-library.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-malformed.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-scalar-input.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-uint8-return.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-undefined-output.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-version-info.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-while-loop.pbtxt.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:invalid-output-index.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:legacy-fed-input-without-inputs.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:merge_node_with_function.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:mlir_passthrough_op.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:multi-output-feeds.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:multiple-use-next-iteration.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:node-locations.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:output-shapes-attr.pbtxt.test PASSED in 1.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:output-shapes.pbtxt.test PASSED in 1.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:parse_example.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:parse_example_v2.pbtxt.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:partial-device-name.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:prune_unused_nodes.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:quint8-const.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:shape-attrs.pbtxt.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:stateful-attribute.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:string-attr.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:switch_n.pbtxt.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:target.pbtxt.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:tensor-list.pbtxt.test PASSED in 2.2s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:tf-data-pipeline.pbtxt.test PASSED in 2.0s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:unregistered_kernel.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir/batch_use_same_function:saved_model.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:aliasing_arg_attr.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:case.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:convert_tensor.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:derived_shape_attr.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:derived_size_attr.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:device-arg-retval-attr.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:export_main_to_flib.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:fetch_feed_names.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:func_attr.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:func_list_attr.mlir.test PASSED in 2.0s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:function-control-ret.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:function-order.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:function-resource-args-handle-info.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:function-resource-args.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:functional-if-ops.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:functional-while-ops.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:graph-as-function.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:infer_derived_attribute.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:invalid_input.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:legalized_name.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:missing-main.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:noop.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:optional_symbol_ref.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:output-shapes-attr.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:parse_example.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:parse_example_v2.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:preserve-entry-func-names.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:ref-type-attr.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:ref-while-loop.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:shape_list_attr.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:simple.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:simple_tf_dialect_op.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:stringescape.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:switchn.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:tf-gradient-attr.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:tf-legacy-call.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:tf_add.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:tf_identity_n.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:tf_tpu_embedding_ops.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:type_attr.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:type_list_attr.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:unique_name.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:unique_output_name.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:while-loop.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/tf_to_hlo_pipeline:sccp-post-shape-inference.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests/tpu_bridge_v1:end_to_end.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tf2xla/api/v0:compile_mlir_util_test PASSED in 6.8s //tensorflow/compiler/mlir/tf2xla/api/v0:compile_tf_graph_test PASSED in 0.9s //tensorflow/compiler/mlir/tf2xla/api/v1:legalize_tf_test PASSED in 28.7s //tensorflow/compiler/mlir/tf2xla/tests:adjust-layout.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tf2xla/tests:convert-mhlo-quant-to-int.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tf2xla/tests:hlo_xla_runtime_pipeline.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tf2xla/tests:hlo_xla_sparsification.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-BatchMatMulV2.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-binary-elementwise.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-collective.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-communication.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-include-tf2xla-fallback.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-no-tf2xla-fallback.mlir.test PASSED in 7.2s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-prefer-tf2xla.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-types.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-with-tf2xla-hlo-importer.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-with-tf2xla.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf.mlir.test PASSED in 12.7s //tensorflow/compiler/mlir/tf2xla/tests:tfxla_device_specific_transformations_cpu.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tf2xla/tests:tfxla_device_specific_transformations_gpu.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tf2xla/tests:verify-tfxla-legalization-no-chlo.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/tf2xla/tests:verify-tfxla-legalization.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tf2xla/transforms:tf2xla_rewriter_test PASSED in 16.7s //tensorflow/compiler/mlir/tf2xla/transforms:verify_tfxla_legalization_test PASSED in 18.1s //tensorflow/compiler/mlir/tf2xla/transforms:xla_legalize_targets_test PASSED in 1.1s //tensorflow/compiler/mlir/tf2xla/transforms:xla_legalize_tf_test PASSED in 2.8s //tensorflow/compiler/mlir/tfr:graph_decompose_test PASSED in 11.5s //tensorflow/compiler/mlir/tfr:node_expansion_test PASSED in 13.4s //tensorflow/compiler/mlir/tfr:op_reg_gen_test PASSED in 21.8s //tensorflow/compiler/mlir/tfr:tfr_decompose_ctx_test PASSED in 6.0s //tensorflow/compiler/mlir/tfr:tfr_gen_test PASSED in 17.5s //tensorflow/compiler/mlir/tfr/examples/customization:test_ops_test PASSED in 16.1s //tensorflow/compiler/mlir/tfr/examples/pad:pad_ops_test PASSED in 23.6s //tensorflow/compiler/mlir/tools/kernel_gen/tests:buffer_deallocation.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tools/kernel_gen/tests:buffer_reuse.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tools/kernel_gen/tests:bufferize.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tools/kernel_gen/tests:copy_cleanup.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tools/kernel_gen/tests:embed_tf_framework.mlir.test PASSED in 0.4s //tensorflow/compiler/mlir/tools/kernel_gen/tests:invalid.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tools/kernel_gen/tests:isinf.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tools/kernel_gen/tests:ops.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tools/kernel_gen/tests:parallel_loops_to_sequential.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tools/kernel_gen/tests:rewrite_tf_framework_assert.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tanh.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf-legalize-to-lmhlo.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf_abi_knowledge.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf_framework_legalize_to_llvm.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf_kernel_gpu_launch_to_llvm.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf_to_jit_invocations.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tosa/tests:convert-tfl-uint8.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tosa/tests:convert_metadata.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tosa/tests:fuse-bias-tf.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tosa/tests:lower-complex-types.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tosa/tests:lower_global_tensors.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tosa/tests:multi_add.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tosa/tests:retain_call_once_funcs.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tosa/tests:strip-quant-types.mlir.test PASSED in 4.6s //tensorflow/compiler/mlir/tosa/tests:strip_metadata.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tosa/tests:tf-tfl-to-tosa-pipeline.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tosa/tests:tf-to-tosa-pipeline.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tosa/tests:tfl-to-tosa-dequantize_softmax.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tosa/tests:tfl-to-tosa-pipeline-filtered.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tosa/tests:tfl-to-tosa-pipeline.mlir.test PASSED in 5.6s //tensorflow/compiler/mlir/tosa/tests:verify_fully_converted.mlir.test PASSED in 1.6s //tensorflow/compiler/tests:adadelta_test_cpu PASSED in 12.9s //tensorflow/compiler/tests:adagrad_da_test_cpu PASSED in 15.4s //tensorflow/compiler/tests:adagrad_test_cpu PASSED in 11.6s //tensorflow/compiler/tests:adam_test_cpu PASSED in 12.2s //tensorflow/compiler/tests:add_n_test_cpu PASSED in 8.2s //tensorflow/compiler/tests:argminmax_test_cpu PASSED in 16.3s //tensorflow/compiler/tests:argminmax_test_cpu_mlir_bridge_test PASSED in 20.6s //tensorflow/compiler/tests:bucketize_op_test_cpu PASSED in 11.0s //tensorflow/compiler/tests:bucketize_op_test_cpu_mlir_bridge_test PASSED in 10.8s //tensorflow/compiler/tests:case_test_cpu PASSED in 7.6s //tensorflow/compiler/tests:cast_ops_test_cpu PASSED in 6.5s //tensorflow/compiler/tests:cast_ops_test_cpu_mlir_bridge_test PASSED in 7.2s //tensorflow/compiler/tests:categorical_op_test_cpu PASSED in 11.9s //tensorflow/compiler/tests:categorical_op_test_cpu_mlir_bridge_test PASSED in 12.5s //tensorflow/compiler/tests:cholesky_op_test_cpu PASSED in 17.8s //tensorflow/compiler/tests:cholesky_op_test_cpu_mlir_bridge_test PASSED in 25.1s //tensorflow/compiler/tests:clustering_test_cpu PASSED in 7.0s //tensorflow/compiler/tests:clustering_test_cpu_mlir_bridge_test PASSED in 6.9s //tensorflow/compiler/tests:concat_ops_test_cpu PASSED in 10.5s //tensorflow/compiler/tests:concat_ops_test_cpu_mlir_bridge_test PASSED in 12.5s //tensorflow/compiler/tests:cond_test_cpu PASSED in 10.5s //tensorflow/compiler/tests:const_arg_test_cpu PASSED in 7.1s //tensorflow/compiler/tests:const_test_cpu PASSED in 10.0s //tensorflow/compiler/tests:data_format_ops_test_cpu PASSED in 12.5s //tensorflow/compiler/tests:data_format_ops_test_cpu_mlir_bridge_test PASSED in 15.0s //tensorflow/compiler/tests:dense_layer_test_cpu PASSED in 10.4s //tensorflow/compiler/tests:dynamic_slice_ops_test_cpu PASSED in 9.7s //tensorflow/compiler/tests:dynamic_slice_ops_test_cpu_mlir_bridge_test PASSED in 11.0s //tensorflow/compiler/tests:dynamic_stitch_test_cpu PASSED in 7.7s //tensorflow/compiler/tests:dynamic_stitch_test_cpu_mlir_bridge_test PASSED in 7.1s //tensorflow/compiler/tests:eager_test_cpu PASSED in 18.2s //tensorflow/compiler/tests:einsum_op_test_cpu PASSED in 9.0s //tensorflow/compiler/tests:einsum_op_test_cpu_mlir_bridge_test PASSED in 7.2s //tensorflow/compiler/tests:ensure_shape_op_test_cpu PASSED in 8.1s //tensorflow/compiler/tests:extract_image_patches_op_test_cpu PASSED in 7.0s //tensorflow/compiler/tests:extract_image_patches_op_test_cpu_mlir_bridge_test PASSED in 8.3s //tensorflow/compiler/tests:fake_quant_ops_test_cpu PASSED in 13.1s //tensorflow/compiler/tests:fake_quant_ops_test_cpu_mlir_bridge_test PASSED in 14.4s //tensorflow/compiler/tests:fifo_queue_test_cpu PASSED in 9.7s //tensorflow/compiler/tests:fifo_queue_test_cpu_mlir_bridge_test PASSED in 7.9s //tensorflow/compiler/tests:ftrl_ops_test_cpu PASSED in 9.8s //tensorflow/compiler/tests:ftrl_ops_test_cpu_mlir_bridge_test PASSED in 10.4s //tensorflow/compiler/tests:function_test_cpu PASSED in 7.5s //tensorflow/compiler/tests:function_test_cpu_mlir_bridge_test PASSED in 10.1s //tensorflow/compiler/tests:gather_nd_op_test_cpu PASSED in 9.1s //tensorflow/compiler/tests:gather_nd_op_test_cpu_mlir_bridge_test PASSED in 12.1s //tensorflow/compiler/tests:gather_test_cpu PASSED in 39.4s //tensorflow/compiler/tests:gather_test_cpu_mlir_bridge_test PASSED in 57.1s //tensorflow/compiler/tests:jit_test_cpu PASSED in 48.4s //tensorflow/compiler/tests:listdiff_op_test_cpu PASSED in 15.6s //tensorflow/compiler/tests:listdiff_op_test_cpu_mlir_bridge_test PASSED in 12.1s //tensorflow/compiler/tests:lrn_ops_test_cpu PASSED in 7.7s //tensorflow/compiler/tests:lrn_ops_test_cpu_mlir_bridge_test PASSED in 9.0s //tensorflow/compiler/tests:lstm_test_cpu PASSED in 23.9s //tensorflow/compiler/tests:manip_ops_test_cpu PASSED in 10.0s //tensorflow/compiler/tests:manip_ops_test_cpu_mlir_bridge_test PASSED in 18.0s //tensorflow/compiler/tests:matrix_band_part_test_cpu PASSED in 60.2s //tensorflow/compiler/tests:matrix_band_part_test_cpu_mlir_bridge_test PASSED in 41.8s //tensorflow/compiler/tests:matrix_inverse_op_test_cpu PASSED in 21.6s //tensorflow/compiler/tests:matrix_inverse_op_test_cpu_mlir_bridge_test PASSED in 26.6s //tensorflow/compiler/tests:matrix_solve_op_test_cpu PASSED in 9.4s //tensorflow/compiler/tests:matrix_solve_op_test_cpu_mlir_bridge_test PASSED in 7.9s //tensorflow/compiler/tests:matrix_triangular_solve_op_test_cpu PASSED in 25.4s //tensorflow/compiler/tests:matrix_triangular_solve_op_test_cpu_mlir_bridge_test PASSED in 32.7s //tensorflow/compiler/tests:momentum_test_cpu PASSED in 9.2s //tensorflow/compiler/tests:nary_ops_test_cpu PASSED in 8.7s //tensorflow/compiler/tests:nary_ops_test_cpu_mlir_bridge_test PASSED in 9.9s //tensorflow/compiler/tests:nullary_ops_test_cpu PASSED in 8.1s //tensorflow/compiler/tests:nullary_ops_test_cpu_mlir_bridge_test PASSED in 7.3s //tensorflow/compiler/tests:placeholder_test_cpu PASSED in 6.3s //tensorflow/compiler/tests:placeholder_test_cpu_mlir_bridge_test PASSED in 7.7s //tensorflow/compiler/tests:proximal_adagrad_test_cpu PASSED in 8.8s //tensorflow/compiler/tests:proximal_gradient_descent_test_cpu PASSED in 6.9s //tensorflow/compiler/tests:quantized_ops_test_cpu PASSED in 8.0s //tensorflow/compiler/tests:reduce_window_test_cpu PASSED in 9.3s //tensorflow/compiler/tests:reduce_window_test_cpu_mlir_bridge_test PASSED in 7.2s //tensorflow/compiler/tests:reshape_op_test_cpu PASSED in 13.4s //tensorflow/compiler/tests:reshape_op_test_cpu_mlir_bridge_test PASSED in 9.1s //tensorflow/compiler/tests:reverse_ops_test_cpu PASSED in 11.4s //tensorflow/compiler/tests:reverse_ops_test_cpu_mlir_bridge_test PASSED in 16.2s //tensorflow/compiler/tests:reverse_sequence_op_test_cpu PASSED in 10.9s //tensorflow/compiler/tests:reverse_sequence_op_test_cpu_mlir_bridge_test PASSED in 9.2s //tensorflow/compiler/tests:risc_ops_test_cpu_mlir_bridge_test PASSED in 7.4s //tensorflow/compiler/tests:rmsprop_test_cpu PASSED in 9.8s //tensorflow/compiler/tests:scatter_nd_op_test_cpu PASSED in 20.1s //tensorflow/compiler/tests:scatter_nd_op_test_cpu_mlir_bridge_test PASSED in 37.8s //tensorflow/compiler/tests:searchsorted_op_test_cpu PASSED in 9.3s //tensorflow/compiler/tests:searchsorted_op_test_cpu_mlir_bridge_test PASSED in 9.2s //tensorflow/compiler/tests:segment_reduction_ops_test_cpu PASSED in 18.1s //tensorflow/compiler/tests:segment_reduction_ops_test_cpu_mlir_bridge_test PASSED in 27.1s //tensorflow/compiler/tests:self_adjoint_eig_op_test_cpu PASSED in 18.0s //tensorflow/compiler/tests:self_adjoint_eig_op_test_cpu_mlir_bridge_test PASSED in 15.5s //tensorflow/compiler/tests:slice_ops_test_cpu PASSED in 17.6s //tensorflow/compiler/tests:slice_ops_test_cpu_mlir_bridge_test PASSED in 19.9s //tensorflow/compiler/tests:sparse_to_dense_op_test_cpu PASSED in 10.4s //tensorflow/compiler/tests:sparse_to_dense_op_test_cpu_mlir_bridge_test PASSED in 7.8s //tensorflow/compiler/tests:stack_ops_test_cpu PASSED in 8.9s //tensorflow/compiler/tests:tensor_float_32_test_cpu PASSED in 9.0s //tensorflow/compiler/tests:tensor_float_32_test_cpu_mlir_bridge_test PASSED in 13.0s //tensorflow/compiler/tests:tensor_list_ops_test_cpu PASSED in 9.7s //tensorflow/compiler/tests:tridiagonal_matmul_ops_test_cpu PASSED in 13.3s //tensorflow/compiler/tests:tridiagonal_matmul_ops_test_cpu_mlir_bridge_test PASSED in 13.2s //tensorflow/compiler/tests:tridiagonal_solve_ops_test_cpu PASSED in 14.0s //tensorflow/compiler/tests:tridiagonal_solve_ops_test_cpu_mlir_bridge_test PASSED in 17.9s //tensorflow/compiler/tests:unique_ops_test_cpu PASSED in 5.9s //tensorflow/compiler/tests:variable_ops_test_cpu PASSED in 27.2s //tensorflow/compiler/tests:variable_ops_test_cpu_mlir_bridge_test PASSED in 16.5s //tensorflow/compiler/tests:where_op_test_cpu PASSED in 12.3s //tensorflow/compiler/tests:while_test_cpu PASSED in 8.9s //tensorflow/compiler/tests:xla_call_module_test_cpu PASSED in 9.6s //tensorflow/compiler/tests:xla_custom_call_ops_test_cpu PASSED in 7.8s //tensorflow/compiler/tests:xla_device_gpu_test_cpu PASSED in 8.4s //tensorflow/compiler/tests:xla_device_test_cpu PASSED in 12.4s //tensorflow/compiler/tests:xla_device_test_cpu_mlir_bridge_test PASSED in 20.7s //tensorflow/compiler/tests:xla_ops_test_cpu PASSED in 34.2s //tensorflow/compiler/tests:xla_ops_test_cpu_mlir_bridge_test PASSED in 38.9s //tensorflow/compiler/tests:xla_test_test PASSED in 7.6s //tensorflow/compiler/tf2xla:const_analysis_test PASSED in 6.3s //tensorflow/compiler/tf2xla:cpu_function_runtime_test PASSED in 0.2s //tensorflow/compiler/tf2xla:functionalize_cond_test PASSED in 1.4s //tensorflow/compiler/tf2xla:functionalize_control_flow_test PASSED in 0.8s //tensorflow/compiler/tf2xla:fused_batchnorm_reserve_space_test_cpu PASSED in 41.1s //tensorflow/compiler/tf2xla:graph_compiler_test PASSED in 7.7s //tensorflow/compiler/tf2xla:literal_util_test PASSED in 0.6s //tensorflow/compiler/tf2xla:resource_operation_table_test PASSED in 10.8s //tensorflow/compiler/tf2xla:resource_util_test_cpu PASSED in 2.4s //tensorflow/compiler/tf2xla:sharding_util_test PASSED in 1.1s //tensorflow/compiler/tf2xla:tf2xla_opset_test PASSED in 14.3s //tensorflow/compiler/tf2xla:tf2xla_test PASSED in 24.6s //tensorflow/compiler/tf2xla:tf2xla_util_test PASSED in 2.6s //tensorflow/compiler/tf2xla:xla_compiler_test PASSED in 18.3s //tensorflow/compiler/tf2xla:xla_jit_compiled_cpu_function_test PASSED in 26.5s //tensorflow/compiler/tf2xla:xla_op_registry_test PASSED in 4.7s //tensorflow/compiler/tf2xla/kernels:rng_converter_utils_test PASSED in 1.3s //tensorflow/compiler/xla:array2d_test PASSED in 0.5s //tensorflow/compiler/xla:array3d_test PASSED in 0.6s //tensorflow/compiler/xla:array4d_test PASSED in 0.1s //tensorflow/compiler/xla:array_test PASSED in 0.6s //tensorflow/compiler/xla:bit_cast_test PASSED in 0.1s //tensorflow/compiler/xla:comparison_util_test PASSED in 0.5s //tensorflow/compiler/xla:debug_options_parsers_test PASSED in 0.1s //tensorflow/compiler/xla:index_util_test PASSED in 0.3s //tensorflow/compiler/xla:iterator_util_test PASSED in 0.7s //tensorflow/compiler/xla:layout_test PASSED in 0.1s //tensorflow/compiler/xla:layout_util_test PASSED in 0.2s //tensorflow/compiler/xla:literal_test PASSED in 0.4s //tensorflow/compiler/xla:parse_flags_from_env_test PASSED in 0.5s //tensorflow/compiler/xla:permutation_util_test PASSED in 0.1s //tensorflow/compiler/xla:primitive_util_test PASSED in 0.6s //tensorflow/compiler/xla:refcounting_hash_map_test PASSED in 0.2s //tensorflow/compiler/xla:reference_util_test PASSED in 0.3s //tensorflow/compiler/xla:shape_test PASSED in 0.2s //tensorflow/compiler/xla:shape_tree_test PASSED in 0.2s //tensorflow/compiler/xla:shape_util_test PASSED in 2.1s //tensorflow/compiler/xla:status_macros_test PASSED in 0.3s //tensorflow/compiler/xla:text_literal_reader_test PASSED in 0.3s //tensorflow/compiler/xla:text_literal_writer_test PASSED in 0.5s //tensorflow/compiler/xla:types_test PASSED in 0.9s //tensorflow/compiler/xla:util_test PASSED in 0.1s //tensorflow/compiler/xla:window_util_test PASSED in 0.2s //tensorflow/compiler/xla/client:padding_test PASSED in 0.1s //tensorflow/compiler/xla/client:xla_builder_test PASSED in 0.4s //tensorflow/compiler/xla/client/lib:arithmetic_test_cpu PASSED in 11.6s //tensorflow/compiler/xla/client/lib:comparators_test_cpu PASSED in 11.6s //tensorflow/compiler/xla/client/lib:constants_test_cpu PASSED in 11.1s //tensorflow/compiler/xla/client/lib:logdet_test_cpu PASSED in 16.7s //tensorflow/compiler/xla/client/lib:math_test_cpu PASSED in 18.3s //tensorflow/compiler/xla/client/lib:matrix_test_cpu PASSED in 19.6s //tensorflow/compiler/xla/client/lib:pooling_test_cpu PASSED in 12.1s //tensorflow/compiler/xla/client/lib:qr_test_cpu PASSED in 14.3s //tensorflow/compiler/xla/client/lib:slicing_test_cpu PASSED in 13.5s //tensorflow/compiler/xla/client/lib:sorting_test_cpu PASSED in 11.2s //tensorflow/compiler/xla/examples/axpy:stablehlo_compile_test PASSED in 18.5s //tensorflow/compiler/xla/experiments/sm_bandwidth_benchmark:sm_bw_test PASSED in 0.1s //tensorflow/compiler/xla/hlo/evaluator:hlo_evaluator_test PASSED in 3.6s //tensorflow/compiler/xla/hlo/experimental/auto_sharding:auto_sharding_test PASSED in 2.2s //tensorflow/compiler/xla/hlo/transforms:hlo_constant_splitter_test PASSED in 1.3s //tensorflow/compiler/xla/hlo/utils:hlo_live_range_test PASSED in 1.1s //tensorflow/compiler/xla/hlo/utils:hlo_matchers_test PASSED in 1.3s //tensorflow/compiler/xla/hlo/utils:hlo_sharding_util_test PASSED in 0.9s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:collective_ops.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:collective_ops_to_cpu_runtime.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:fft.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:legalize_i1_vector_transfers.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:lmhlo_custom_call.mlir.test PASSED in 1.6s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:lmhlo_infeed.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:remove_copies_to_out_params.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:rng_bit_generator.mlir.test PASSED in 3.5s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:xla_abi_legalization.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:xla_cpu_memref_element_cast_to_llvm.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:xla_cpu_outfeed.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:add_hlo_trace.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:gpu_launch.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:gpu_memcpy.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:gpu_memset.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_case.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_custom_call.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_fft.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_gpu_cholesky.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_gpu_conv.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_gpu_cublas_lt_matmul.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_gpu_gemm.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_infeed.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_outfeed.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_send_recv.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_while.mlir.test PASSED in 1.6s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:memref_get_global_to_arg.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:outline_cuda_graphs.mlir.test PASSED in 1.7s //tensorflow/compiler/xla/mlir/framework/tests:legalize-xla-framework.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/framework/tests:outline-with-xla-framework.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir/framework/tests:xla-framework.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/math/transforms/tests:math_optimization.mlir.test PASSED in 2.1s //tensorflow/compiler/xla/mlir/memref/transforms/tests:aligned_allocations.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/runtime/ir/tests:ops.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/runtime/ir/tests:ops_verify.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/runtime/ir/tests:testlib.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir/runtime/transforms:calling_convention_test PASSED in 0.3s //tensorflow/compiler/xla/mlir/runtime/transforms:type_converter_test PASSED in 0.1s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:compilation_pipeline.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:convert_asserts.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:convert_custom_calls.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:export_functions.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:ordinal_assignment.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:rt_to_llvm.mlir.test PASSED in 1.6s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:erase-op-without-results.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:inline-scf-while.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:reduce-scf-forall-bounds.mlir.test PASSED in 1.8s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:replace-op-with-constant.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:replace-op-with-value.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:replace-operand-with-constant.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:return-operands-of-terminator-operands.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:truncate-function.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/tests:bisect.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/tests:no-bug.mlir.test PASSED in 1.8s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/tests:snapshot.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/tools/mlir_replay/public:execution_trace_utils_test PASSED in 0.2s //tensorflow/compiler/xla/mlir/utils:error_util_test PASSED in 0.3s //tensorflow/compiler/xla/mlir/xla_cpu/tests:bufferize.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir/xla_cpu/tests:invalid.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/xla_cpu/tests:ops.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/bufferization/hlo_one_shot_bufferize.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/chlo/chlo_legalize_to_hlo_broadcasts.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/chlo/chlo_legalize_to_hlo_no_broadcasts.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/chlo/chlo_legalize_to_mhlo.mlir.test PASSED in 2.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/chlo/sparse_chlo_legalize_to_linalg.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/buffer_reuse.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/convert_deallocation_ops_to_llvm.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/deallocate.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/deallocate_invalid.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/deallocation_ops.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/deallocation_simplification.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/deallocation_to_scf.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/split_alloc_tensors.mlir.test PASSED in 1.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/add_debug_info.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/bufferization.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/collapse-shape.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/collect_stats.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/compose_extract_insert_slice.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/batch_matmul.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/conv_2d_nhwc_hwcf.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/dot.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/duplicate_fusions.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/fibonacci.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/fusion_outlining.mlir.test PASSED in 2.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/fusion_planning_for_cpu.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/inline_fusion_clusters.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/map_bcast_map.mlir.test PASSED in 4.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/map_matmul.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/map_reduce_map.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/map_reshape_map.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/matmul.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reduce_1d.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reduce_1d_map.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reduce_2d.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reduce_window.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reverse.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/scatter.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/sort.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/transpose.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/greedy_fusion.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/invalid.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/lower_vectors.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/nested_tiling_softmax.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/ops.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/optimize_linalg_ops.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/rewrite_forall_to_for.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/simplify_dead_copy.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/tile_by_one.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/tiling_softmax.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/vectorize_copy.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/vectorize_for_cpu.mlir.test PASSED in 1.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/lhlo-legalize-select-and-scatter.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/lhlo-legalize-to-affine.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/lhlo-legalize-to-gpu.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/lhlo-legalize-to-parallel-loops.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/lhlo-legalize-to-tensor-op.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/ops.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo_gpu/lhlo_gpu_ops.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/attrs.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/broadcast_propagation.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/bitcast.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/canonicalize.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/concatenate.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/convert.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/convolution.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/custom_call.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/folder_limit.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/reduce.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/reshape.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/reverse.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/scatter.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/transpose.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/tuple.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/while.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/constraint_fusion.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/convert_to_signless.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/expand_hlo_tuples.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/expand_ops_simplifier.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/group_reduction_dimensions.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-collapse-elementwise-map.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-einsum-to-dot-general.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-gather-to-torch-index-select.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-rng-to-linalg.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-shape-ops-to-standard.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-sort.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-arithmetic.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-lhlo-only-dynamic.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-lhlo-unranked.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-lhlo.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-linalg.mlir.test PASSED in 3.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-memref-unranked.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-memref.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-stablehlo-experimental.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-stablehlo.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/inlining.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/invalid.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/legalize-control-flow.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/legalize-hlo-shape-computations.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/legalize-mhlo-to-thlo.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/legalize-to-std.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/lower-complex.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/lower-general-dot.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/materialize-broadcasts.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/merge_assuming_ops.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_bytecode_customizations.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_canonicalize_dot.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_canonicalize_gather.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_canonicalize_reduction.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_canonicalize_scatter.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_flatten_tuple.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_infer_shape_type_methods.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_ops_prettyprint.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_reduce_pretty_print.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/ops.mlir.test PASSED in 3.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/optimize-hlo.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/prepare-for-export.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/reify-result-types.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/restrict_max_rank.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/shape_legalize_to_hlo.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/shape_reification.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sink-constants-to-control-flow.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_gendot_lower.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_lower.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_ops.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_rewriting.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_transpose.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/stablehlo-legalize-to-hlo.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/symbolic-shape-optimization.mlir.test PASSED in 1.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/unfuse_batch_norm.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_bounds.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_conv_op.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_reduce_op.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_reduce_window_op.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_scatter_op.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_select_and_scatter_op.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_while_op.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/while_prettyprint.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/bufferize.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/canonicalize.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/invalid.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/legalize_sort.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/ops.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/tiling.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:alloc_to_arg.mlir.test PASSED in 2.2s //tensorflow/compiler/xla/mlir_hlo/tests:assuming-structural-propagation.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:buffer_packing.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:bufferize.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:bufferize_one_shot.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:collapse_parallel_loops_to_1d_pass.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir_hlo/tests:detensorize_scf_ops.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:index_type_llvm_lowering.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:legalize-trigonometric-to-approximation.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:lower_index_cast.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:propagate_static_shapes.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:rank-specialization.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:scalarization.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:shape-component-analysis.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:shape_simplification.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:test_userange.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/mlir_hlo/tests:tile_loops.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:unbufferize.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:unroll-loops.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tools/mlir_interpreter/framework/tests:interpreter_value_test PASSED in 0.2s //tensorflow/compiler/xla/mlir_hlo/tools/mlir_interpreter/framework/tests:tensor_or_memref_test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:binary.mlir.test PASSED in 1.6s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:nullary.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:prepare-mhlo.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:ternary.mlir.test PASSED in 5.9s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:unary.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/pjrt:host_callback_test PASSED in 0.3s //tensorflow/compiler/xla/pjrt:lru_cache_test PASSED in 0.6s //tensorflow/compiler/xla/pjrt:pjrt_api_test PASSED in 0.9s //tensorflow/compiler/xla/pjrt:pjrt_client_test_cpu PASSED in 11.3s //tensorflow/compiler/xla/pjrt:pjrt_compiler_test PASSED in 0.2s //tensorflow/compiler/xla/pjrt:pjrt_executable_test PASSED in 0.7s //tensorflow/compiler/xla/pjrt:pjrt_stream_executor_client_test PASSED in 10.1s //tensorflow/compiler/xla/pjrt:semaphore_test PASSED in 0.2s //tensorflow/compiler/xla/pjrt:tf_pjrt_client_test PASSED in 10.6s //tensorflow/compiler/xla/pjrt:tfrt_cpu_pjrt_client_test PASSED in 12.3s //tensorflow/compiler/xla/pjrt:tracked_device_buffer_test PASSED in 8.7s //tensorflow/compiler/xla/pjrt:tracked_tfrt_cpu_device_buffer_test PASSED in 0.7s //tensorflow/compiler/xla/pjrt:transpose_test PASSED in 66.1s //tensorflow/compiler/xla/pjrt/c:pjrt_c_api_cpu_test PASSED in 10.4s //tensorflow/compiler/xla/pjrt/c:pjrt_c_api_helpers_test PASSED in 0.6s //tensorflow/compiler/xla/pjrt/distributed:client_server_test PASSED in 41.1s //tensorflow/compiler/xla/pjrt/distributed:service_test PASSED in 10.5s //tensorflow/compiler/xla/pjrt/gpu:se_gpu_pjrt_client_test PASSED in 2.6s //tensorflow/compiler/xla/python:outfeed_receiver_test_cpu PASSED in 18.3s //tensorflow/compiler/xla/python/ifrt:array_test PASSED in 0.9s //tensorflow/compiler/xla/python/ifrt:array_test_no_impl PASSED in 0.6s //tensorflow/compiler/xla/python/ifrt:client_test_no_impl PASSED in 0.3s //tensorflow/compiler/xla/python/ifrt:executable_test_no_impl PASSED in 1.4s //tensorflow/compiler/xla/python/ifrt:future_test PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt:index_domain_test PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt:index_test PASSED in 1.3s //tensorflow/compiler/xla/python/ifrt:shape_test PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt:sharding_test PASSED in 0.5s //tensorflow/compiler/xla/python/ifrt:tuple_test_no_impl PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_array.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_assemble.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_call.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_call_loaded_executable.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_disassemble.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_loaded_executable.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_reshard.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/python/ifrt/support:sharding_param_to_op_sharding_test PASSED in 0.3s //tensorflow/compiler/xla/python/pjrt_ifrt:pjrt_array_impl_test_tfrt_cpu PASSED in 19.7s //tensorflow/compiler/xla/python/pjrt_ifrt:pjrt_client_impl_test_tfrt_cpu PASSED in 11.0s //tensorflow/compiler/xla/python/pjrt_ifrt:pjrt_executable_impl_test_tfrt_cpu PASSED in 11.6s //tensorflow/compiler/xla/python/pjrt_ifrt:pjrt_tuple_impl_test_tfrt_cpu PASSED in 10.9s //tensorflow/compiler/xla/python_api:xla_literal_test PASSED in 1.4s //tensorflow/compiler/xla/python_api:xla_shape_test PASSED in 0.9s //tensorflow/compiler/xla/rpc:grpc_client_test PASSED in 6.4s //tensorflow/compiler/xla/runtime:arguments_test PASSED in 0.3s //tensorflow/compiler/xla/runtime:async_runtime_test PASSED in 0.3s //tensorflow/compiler/xla/runtime:custom_call_test PASSED in 3.1s //tensorflow/compiler/xla/runtime:diagnostics_test PASSED in 0.2s //tensorflow/compiler/xla/runtime:executable_test PASSED in 2.0s //tensorflow/compiler/xla/runtime:ffi_test PASSED in 1.6s //tensorflow/compiler/xla/runtime:map_by_type_test PASSED in 0.8s //tensorflow/compiler/xla/runtime:module_test PASSED in 0.2s //tensorflow/compiler/xla/runtime:results_test PASSED in 0.2s //tensorflow/compiler/xla/runtime:state_test PASSED in 0.1s //tensorflow/compiler/xla/runtime:symbolic_shape_test PASSED in 0.8s //tensorflow/compiler/xla/runtime:type_id_test PASSED in 0.2s //tensorflow/compiler/xla/service:algebraic_simplifier_overflow_test_cpu PASSED in 11.3s //tensorflow/compiler/xla/service:algebraic_simplifier_test PASSED in 42.4s //tensorflow/compiler/xla/service:all_gather_broadcast_reorder_test PASSED in 1.7s //tensorflow/compiler/xla/service:all_gather_combiner_test PASSED in 1.3s //tensorflow/compiler/xla/service:all_gather_decomposer_test PASSED in 1.4s //tensorflow/compiler/xla/service:all_reduce_combiner_test PASSED in 1.9s //tensorflow/compiler/xla/service:all_reduce_contiguous_test PASSED in 4.8s //tensorflow/compiler/xla/service:all_reduce_folder_test PASSED in 1.0s //tensorflow/compiler/xla/service:all_reduce_promotion_test PASSED in 1.3s //tensorflow/compiler/xla/service:all_reduce_reassociate_test PASSED in 1.2s //tensorflow/compiler/xla/service:all_reduce_simplifier_test PASSED in 1.2s //tensorflow/compiler/xla/service:ar_crs_combiner_test PASSED in 1.5s //tensorflow/compiler/xla/service:async_collective_creator_test PASSED in 1.0s //tensorflow/compiler/xla/service:async_op_canonicalizer_test PASSED in 1.0s //tensorflow/compiler/xla/service:batch_dot_simplification_test PASSED in 1.5s //tensorflow/compiler/xla/service:batchnorm_expander_test_cpu PASSED in 14.2s //tensorflow/compiler/xla/service:bfloat16_conversion_folding_test PASSED in 1.2s //tensorflow/compiler/xla/service:bfloat16_propagation_test PASSED in 1.6s //tensorflow/compiler/xla/service:bitcast_dtypes_expander_test PASSED in 1.9s //tensorflow/compiler/xla/service:broadcast_canonicalizer_test PASSED in 2.1s //tensorflow/compiler/xla/service:buffer_assignment_test PASSED in 18.5s //tensorflow/compiler/xla/service:call_graph_test PASSED in 2.0s //tensorflow/compiler/xla/service:call_inliner_test PASSED in 0.9s //tensorflow/compiler/xla/service:change_op_data_type_test PASSED in 1.5s //tensorflow/compiler/xla/service:collective_ops_utils_test PASSED in 0.3s //tensorflow/compiler/xla/service:collectives_schedule_linearizer_test PASSED in 1.1s //tensorflow/compiler/xla/service:compilation_environments_test PASSED in 0.5s //tensorflow/compiler/xla/service:conditional_canonicalizer_test PASSED in 1.3s //tensorflow/compiler/xla/service:conditional_code_motion_test PASSED in 3.1s //tensorflow/compiler/xla/service:conditional_simplifier_test PASSED in 1.5s //tensorflow/compiler/xla/service:conditional_to_select_test PASSED in 1.2s //tensorflow/compiler/xla/service:convert_async_collectives_to_sync_test PASSED in 1.4s //tensorflow/compiler/xla/service:convert_mover_test PASSED in 1.2s //tensorflow/compiler/xla/service:convert_operand_folding_test PASSED in 1.2s //tensorflow/compiler/xla/service:convolution_4d_expander_test PASSED in 1.5s //tensorflow/compiler/xla/service:convolution_group_converter_test PASSED in 1.5s //tensorflow/compiler/xla/service:convolution_pred_expander_test PASSED in 1.2s //tensorflow/compiler/xla/service:copy_insertion_test PASSED in 2.1s //tensorflow/compiler/xla/service:custom_call_status_test PASSED in 0.3s //tensorflow/compiler/xla/service:defuser_test PASSED in 1.1s //tensorflow/compiler/xla/service:despecializer_test PASSED in 0.9s //tensorflow/compiler/xla/service:dfs_hlo_visitor_with_default_test PASSED in 1.0s //tensorflow/compiler/xla/service:dot_decomposer_test PASSED in 1.2s //tensorflow/compiler/xla/service:dot_merger_test PASSED in 2.6s //tensorflow/compiler/xla/service:dynamic_dimension_inference_test PASSED in 1.2s //tensorflow/compiler/xla/service:dynamic_dimension_simplifier_test PASSED in 1.2s //tensorflow/compiler/xla/service:dynamic_index_splitter_test PASSED in 1.2s //tensorflow/compiler/xla/service:dynamic_padder_test_cpu PASSED in 17.2s //tensorflow/compiler/xla/service:dynamic_parameter_binding_test PASSED in 0.8s //tensorflow/compiler/xla/service:dynamic_update_slice_test_cpu PASSED in 12.2s //tensorflow/compiler/xla/service:elemental_ir_emitter_test_cpu PASSED in 13.2s //tensorflow/compiler/xla/service:flatten_call_graph_test PASSED in 1.0s //tensorflow/compiler/xla/service:float_normalization_test PASSED in 1.1s //tensorflow/compiler/xla/service:fusion_node_indexing_evaluation_test PASSED in 1.3s //tensorflow/compiler/xla/service:gather_expander_test PASSED in 1.6s //tensorflow/compiler/xla/service:gather_simplifier_test PASSED in 1.0s //tensorflow/compiler/xla/service:heap_simulator_test PASSED in 1.3s //tensorflow/compiler/xla/service:hlo_alias_analysis_test PASSED in 1.3s //tensorflow/compiler/xla/service:hlo_casting_utils_test PASSED in 10.3s //tensorflow/compiler/xla/service:hlo_computation_deduplicator_test PASSED in 2.0s //tensorflow/compiler/xla/service:hlo_computation_test PASSED in 5.7s //tensorflow/compiler/xla/service:hlo_constant_folding_test PASSED in 7.0s //tensorflow/compiler/xla/service:hlo_cost_analysis_test PASSED in 11.9s //tensorflow/compiler/xla/service:hlo_creation_utils_test PASSED in 5.5s //tensorflow/compiler/xla/service:hlo_cse_test PASSED in 13.1s //tensorflow/compiler/xla/service:hlo_dataflow_analysis_test PASSED in 1.5s //tensorflow/compiler/xla/service:hlo_dce_test PASSED in 2.1s //tensorflow/compiler/xla/service:hlo_domain_test PASSED in 1.1s //tensorflow/compiler/xla/service:hlo_element_type_converter_test PASSED in 1.3s //tensorflow/compiler/xla/service:hlo_execution_profile_test PASSED in 9.9s //tensorflow/compiler/xla/service:hlo_graph_dumper_test PASSED in 1.4s //tensorflow/compiler/xla/service:hlo_input_output_alias_config_test PASSED in 2.0s //tensorflow/compiler/xla/service:hlo_instruction_test PASSED in 0.9s //tensorflow/compiler/xla/service:hlo_liveness_analysis_test PASSED in 1.0s //tensorflow/compiler/xla/service:hlo_memory_scheduler_test PASSED in 1.0s //tensorflow/compiler/xla/service:hlo_module_dce_test PASSED in 1.0s //tensorflow/compiler/xla/service:hlo_module_metadata_test PASSED in 0.7s //tensorflow/compiler/xla/service:hlo_module_test PASSED in 1.4s //tensorflow/compiler/xla/service:hlo_opcode_test PASSED in 0.4s //tensorflow/compiler/xla/service:hlo_ordering_test PASSED in 1.1s //tensorflow/compiler/xla/service:hlo_parser_test PASSED in 0.3s //tensorflow/compiler/xla/service:hlo_pass_pipeline_test PASSED in 2.9s //tensorflow/compiler/xla/service:hlo_phi_graph_test PASSED in 0.3s //tensorflow/compiler/xla/service:hlo_proto_util_test PASSED in 0.9s //tensorflow/compiler/xla/service:hlo_reachability_test PASSED in 1.3s //tensorflow/compiler/xla/service:hlo_rematerialization_test PASSED in 4.1s //tensorflow/compiler/xla/service:hlo_rematerialization_test_utils_test PASSED in 1.3s //tensorflow/compiler/xla/service:hlo_replication_analysis_test PASSED in 1.1s //tensorflow/compiler/xla/service:hlo_schedule_test PASSED in 1.5s //tensorflow/compiler/xla/service:hlo_sharding_test PASSED in 1.3s //tensorflow/compiler/xla/service:hlo_value_semantics_analysis_test PASSED in 5.0s //tensorflow/compiler/xla/service:hlo_verifier_test PASSED in 0.9s //tensorflow/compiler/xla/service:indexed_array_analysis_test PASSED in 5.2s //tensorflow/compiler/xla/service:instruction_fusion_test PASSED in 1.1s //tensorflow/compiler/xla/service:latency_hiding_scheduler_test PASSED in 1.8s //tensorflow/compiler/xla/service:layout_assignment_test PASSED in 13.2s //tensorflow/compiler/xla/service:layout_normalization_test PASSED in 3.2s //tensorflow/compiler/xla/service:logistic_expander_test PASSED in 1.9s //tensorflow/compiler/xla/service:loop_schedule_linearizer_test PASSED in 1.2s //tensorflow/compiler/xla/service:map_inliner_test PASSED in 2.0s //tensorflow/compiler/xla/service:mapped_ptr_container_sorter_test PASSED in 0.3s //tensorflow/compiler/xla/service:memory_space_assignment_best_fit_repacker_test PASSED in 0.2s //tensorflow/compiler/xla/service:memory_space_assignment_test PASSED in 3.1s //tensorflow/compiler/xla/service:memory_space_propagation_test PASSED in 2.6s //tensorflow/compiler/xla/service:name_uniquer_test PASSED in 0.3s //tensorflow/compiler/xla/service:operand_upcaster_test PASSED in 1.8s //tensorflow/compiler/xla/service:optimize_input_output_buffer_alias_test PASSED in 1.0s //tensorflow/compiler/xla/service:pattern_matcher_gmock_test PASSED in 0.3s //tensorflow/compiler/xla/service:pattern_matcher_test PASSED in 3.0s //tensorflow/compiler/xla/service:profile_guided_latency_estimator_test PASSED in 1.3s //tensorflow/compiler/xla/service:real_imag_expander_test PASSED in 2.6s //tensorflow/compiler/xla/service:reduce_decomposer_test PASSED in 1.1s //tensorflow/compiler/xla/service:reduce_scatter_combiner_test PASSED in 1.2s //tensorflow/compiler/xla/service:reduce_scatter_decomposer_test PASSED in 1.8s //tensorflow/compiler/xla/service:reduce_scatter_reassociate_test PASSED in 2.6s //tensorflow/compiler/xla/service:reshape_decomposer_test PASSED in 1.0s //tensorflow/compiler/xla/service:reshape_mover_test PASSED in 1.3s //tensorflow/compiler/xla/service:result_caster_test PASSED in 1.4s //tensorflow/compiler/xla/service:root_instruction_sinker_test PASSED in 1.8s //tensorflow/compiler/xla/service:scatter_expander_test PASSED in 1.1s //tensorflow/compiler/xla/service:scatter_simplifier_test PASSED in 1.0s //tensorflow/compiler/xla/service:select_and_scatter_expander_test PASSED in 1.5s //tensorflow/compiler/xla/service:shape_inference_test PASSED in 0.6s //tensorflow/compiler/xla/service:shaped_buffer_test PASSED in 11.2s //tensorflow/compiler/xla/service:sharding_propagation_test PASSED in 2.6s //tensorflow/compiler/xla/service:sharding_remover_test PASSED in 1.8s //tensorflow/compiler/xla/service:simplify_fp_conversions_test PASSED in 0.9s //tensorflow/compiler/xla/service:slice_sinker_test PASSED in 1.3s //tensorflow/compiler/xla/service:sort_simplifier_test PASSED in 2.1s //tensorflow/compiler/xla/service:space_to_batch_converter_test PASSED in 1.2s //tensorflow/compiler/xla/service:stable_sort_expander_test PASSED in 1.5s //tensorflow/compiler/xla/service:stochastic_convert_decomposer_test PASSED in 2.1s //tensorflow/compiler/xla/service:stream_pool_test PASSED in 0.3s //tensorflow/compiler/xla/service:topk_rewriter_test PASSED in 4.6s //tensorflow/compiler/xla/service:transpose_folding_test PASSED in 3.3s //tensorflow/compiler/xla/service:tuple_points_to_analysis_test PASSED in 1.0s //tensorflow/compiler/xla/service:tuple_simplifier_test PASSED in 1.6s //tensorflow/compiler/xla/service:tuple_util_test PASSED in 1.7s //tensorflow/compiler/xla/service:while_loop_all_reduce_code_motion_test PASSED in 1.7s //tensorflow/compiler/xla/service:while_loop_analysis_test PASSED in 1.1s //tensorflow/compiler/xla/service:while_loop_concat_code_motion_test PASSED in 2.8s //tensorflow/compiler/xla/service:while_loop_constant_sinking_test PASSED in 2.2s //tensorflow/compiler/xla/service:while_loop_expensive_invariant_code_motion_test PASSED in 4.1s //tensorflow/compiler/xla/service:while_loop_invariant_code_motion_test PASSED in 1.1s //tensorflow/compiler/xla/service:while_loop_simplifier_test PASSED in 1.9s //tensorflow/compiler/xla/service:while_loop_trip_count_annotator_test PASSED in 1.1s //tensorflow/compiler/xla/service:while_util_test PASSED in 1.2s //tensorflow/compiler/xla/service:xla_aot_compile_stablehlo_cpu_test PASSED in 10.5s //tensorflow/compiler/xla/service:xla_debug_info_manager_test PASSED in 1.0s //tensorflow/compiler/xla/service:zero_sized_hlo_elimination_test PASSED in 1.0s //tensorflow/compiler/xla/service/cpu:conv_canonicalization_test PASSED in 2.8s //tensorflow/compiler/xla/service/cpu:cpu_eigen_tensor_alignment_test PASSED in 1.5s //tensorflow/compiler/xla/service/cpu:cpu_instruction_fusion_test PASSED in 2.0s //tensorflow/compiler/xla/service/cpu:cpu_layout_assignment_test PASSED in 6.5s //tensorflow/compiler/xla/service/cpu:ir_emission_utils_test PASSED in 1.5s //tensorflow/compiler/xla/service/cpu:parallel_task_assignment_test PASSED in 2.9s //tensorflow/compiler/xla/service/cpu:runtime_fft_test PASSED in 0.2s //tensorflow/compiler/xla/service/cpu:shape_partition_test PASSED in 2.2s //tensorflow/compiler/xla/service/cpu:xfeed_manager_test PASSED in 0.8s //tensorflow/compiler/xla/service/cpu/tests:cpu_bytesizeof_test PASSED in 0.6s //tensorflow/compiler/xla/service/cpu/tests:cpu_dyn_shape_test PASSED in 11.6s //tensorflow/compiler/xla/service/cpu/tests:cpu_eigen_dot_operation_test PASSED in 11.2s //tensorflow/compiler/xla/service/cpu/tests:cpu_external_constants_test PASSED in 29.3s //tensorflow/compiler/xla/service/cpu/tests:cpu_fusion_test PASSED in 12.2s //tensorflow/compiler/xla/service/cpu/tests:cpu_infeed_test PASSED in 8.9s //tensorflow/compiler/xla/service/cpu/tests:cpu_intrinsic_test PASSED in 13.5s //tensorflow/compiler/xla/service/cpu/tests:cpu_key_value_sort_test PASSED in 9.9s //tensorflow/compiler/xla/service/cpu/tests:cpu_literal_caching_test PASSED in 11.0s //tensorflow/compiler/xla/service/cpu/tests:cpu_noalias_test PASSED in 14.6s //tensorflow/compiler/xla/service/cpu/tests:cpu_outfeed_test PASSED in 14.5s //tensorflow/compiler/xla/service/cpu/tests:cpu_profiling_test PASSED in 13.5s //tensorflow/compiler/xla/service/cpu/tests:cpu_spmd_compile_test PASSED in 9.6s //tensorflow/compiler/xla/service/cpu/tests:cpu_topk_test PASSED in 12.7s //tensorflow/compiler/xla/service/cpu/tests:cpu_vectorization_test PASSED in 11.0s //tensorflow/compiler/xla/service/cpu/tests:cpu_while_test PASSED in 11.0s //tensorflow/compiler/xla/service/cpu/tests:tree_reduction_rewriter_test PASSED in 11.8s //tensorflow/compiler/xla/service/gpu:alias_passthrough_params_test PASSED in 1.6s //tensorflow/compiler/xla/service/gpu:all_reduce_blueconnect_test PASSED in 1.2s //tensorflow/compiler/xla/service/gpu:backend_configs_test PASSED in 1.4s //tensorflow/compiler/xla/service/gpu:cublas_pad_for_gemms_test PASSED in 2.0s //tensorflow/compiler/xla/service/gpu:cudnn_pad_for_convolutions_test PASSED in 2.6s //tensorflow/compiler/xla/service/gpu:cudnn_simplify_padding_test PASSED in 3.7s //tensorflow/compiler/xla/service/gpu:cudnn_support_utils_test PASSED in 2.9s //tensorflow/compiler/xla/service/gpu:cudnn_vectorize_convolutions_test PASSED in 2.4s //tensorflow/compiler/xla/service/gpu:fusion_merger_test PASSED in 3.6s //tensorflow/compiler/xla/service/gpu:gemm_rewriter_triton_test PASSED in 2.0s //tensorflow/compiler/xla/service/gpu:gpu_async_collective_annotator_test PASSED in 1.1s //tensorflow/compiler/xla/service/gpu:gpu_conv_padding_legalization_test PASSED in 1.2s //tensorflow/compiler/xla/service/gpu:gpu_conv_rewriter_test PASSED in 1.2s //tensorflow/compiler/xla/service/gpu:gpu_convert_async_collectives_to_sync_test PASSED in 1.0s //tensorflow/compiler/xla/service/gpu:gpu_fusible_test PASSED in 4.8s //tensorflow/compiler/xla/service/gpu:gpu_hlo_cost_analysis_test PASSED in 2.5s //tensorflow/compiler/xla/service/gpu:gpu_performance_model_test PASSED in 2.3s //tensorflow/compiler/xla/service/gpu:gpu_sanitize_constant_names_test PASSED in 2.6s //tensorflow/compiler/xla/service/gpu:hlo_algorithm_denylist_test PASSED in 0.2s //tensorflow/compiler/xla/service/gpu:hlo_fusion_stats_test PASSED in 1.4s //tensorflow/compiler/xla/service/gpu:instruction_fusion_test PASSED in 2.4s //tensorflow/compiler/xla/service/gpu:ir_emission_utils_test PASSED in 1.7s //tensorflow/compiler/xla/service/gpu:matmul_utils_test PASSED in 1.7s //tensorflow/compiler/xla/service/gpu:move_copy_to_users_test PASSED in 2.2s //tensorflow/compiler/xla/service/gpu:multi_output_fusion_test PASSED in 6.7s //tensorflow/compiler/xla/service/gpu:non_atomically_upgradeable_rw_lock_test PASSED in 0.3s //tensorflow/compiler/xla/service/gpu:reduction_splitter_test PASSED in 1.6s //tensorflow/compiler/xla/service/gpu:scatter_slice_simplifier_test PASSED in 1.4s //tensorflow/compiler/xla/service/gpu:target_util_test PASSED in 0.6s //tensorflow/compiler/xla/service/gpu:topk_splitter_test PASSED in 32.8s //tensorflow/compiler/xla/service/gpu:variadic_op_splitter_test PASSED in 2.2s //tensorflow/compiler/xla/service/gpu:while_transformer_test PASSED in 2.0s //tensorflow/compiler/xla/service/gpu/llvm_gpu_backend:utils_test PASSED in 0.6s //tensorflow/compiler/xla/service/gpu/tests:gpu_reduce_scatter_creator_test PASSED in 2.3s //tensorflow/compiler/xla/service/gpu/tests:reduction_degenerate_dim_remover_test PASSED in 1.8s //tensorflow/compiler/xla/service/gpu/tests:reduction_dimension_grouper_test PASSED in 2.4s //tensorflow/compiler/xla/service/gpu/tests:tree_reduction_rewriter_test PASSED in 2.6s //tensorflow/compiler/xla/service/graphcycles:graphcycles_test PASSED in 1.3s //tensorflow/compiler/xla/service/graphcycles:ordered_set_test PASSED in 0.2s //tensorflow/compiler/xla/service/llvm_ir:alias_analysis_test PASSED in 9.1s //tensorflow/compiler/xla/service/llvm_ir:ir_array_test PASSED in 0.7s //tensorflow/compiler/xla/service/spmd:canonicalize_all_gather_for_cse_test PASSED in 1.0s //tensorflow/compiler/xla/service/spmd:collective_permute_motion_test PASSED in 1.9s //tensorflow/compiler/xla/service/spmd:partition_assignment_test PASSED in 1.0s //tensorflow/compiler/xla/service/spmd:schedule_aware_collective_ops_cse_test PASSED in 1.3s //tensorflow/compiler/xla/service/spmd:spmd_partitioner_test PASSED in 4.1s //tensorflow/compiler/xla/service/spmd:stateful_rng_spmd_partitioner_test PASSED in 1.5s //tensorflow/compiler/xla/stream_executor:dnn_test PASSED in 0.2s //tensorflow/compiler/xla/stream_executor:stream_test PASSED in 0.6s //tensorflow/compiler/xla/stream_executor/host:host_stream_test PASSED in 1.0s //tensorflow/compiler/xla/tests:all_reduce_test_cpu PASSED in 11.9s //tensorflow/compiler/xla/tests:axpy_simple_test_cpu PASSED in 14.3s //tensorflow/compiler/xla/tests:bad_rng_shape_validation_test_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests:binop_scaling_test_cpu PASSED in 10.0s //tensorflow/compiler/xla/tests:bitcast_convert_test_cpu PASSED in 15.4s //tensorflow/compiler/xla/tests:broadcast_simple_test_cpu PASSED in 8.6s //tensorflow/compiler/xla/tests:broadcast_test_cpu PASSED in 16.5s //tensorflow/compiler/xla/tests:buffer_donation_test_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests:call_test_cpu PASSED in 15.7s //tensorflow/compiler/xla/tests:check_execution_arity_test_cpu PASSED in 13.3s //tensorflow/compiler/xla/tests:cholesky_test_cpu PASSED in 20.8s //tensorflow/compiler/xla/tests:client_test_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests:collective_ops_test_cpu PASSED in 39.1s //tensorflow/compiler/xla/tests:compilation_cache_test_cpu PASSED in 13.8s //tensorflow/compiler/xla/tests:compute_constant_test_cpu PASSED in 7.9s //tensorflow/compiler/xla/tests:concat_test_cpu PASSED in 12.8s //tensorflow/compiler/xla/tests:constant_reduction_function_test_cpu PASSED in 12.9s //tensorflow/compiler/xla/tests:constants_test_cpu PASSED in 12.6s //tensorflow/compiler/xla/tests:convert_test_cpu PASSED in 16.4s //tensorflow/compiler/xla/tests:copy_test_cpu PASSED in 15.5s //tensorflow/compiler/xla/tests:cpu_gpu_fusion_test_cpu PASSED in 18.2s //tensorflow/compiler/xla/tests:custom_call_test_cpu PASSED in 12.8s //tensorflow/compiler/xla/tests:deallocation_test_cpu PASSED in 10.3s //tensorflow/compiler/xla/tests:deconstruct_tuple_test_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests:deep_graph_test_cpu PASSED in 14.4s //tensorflow/compiler/xla/tests:execution_profile_test_cpu PASSED in 12.6s //tensorflow/compiler/xla/tests:fft_test_cpu PASSED in 16.6s //tensorflow/compiler/xla/tests:float8_test_cpu PASSED in 12.5s //tensorflow/compiler/xla/tests:floor_ceil_test_cpu PASSED in 11.6s //tensorflow/compiler/xla/tests:fmax_fmin_test_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests:gather_operation_test_cpu PASSED in 13.6s //tensorflow/compiler/xla/tests:get_dimension_size_test_cpu PASSED in 14.1s //tensorflow/compiler/xla/tests:half_test_cpu PASSED in 15.3s //tensorflow/compiler/xla/tests:hlo_metadata_test PASSED in 11.5s //tensorflow/compiler/xla/tests:literal_test_util_test PASSED in 4.9s //tensorflow/compiler/xla/tests:local_client_allocation_test_cpu PASSED in 9.2s //tensorflow/compiler/xla/tests:local_client_aot_test PASSED in 0.2s //tensorflow/compiler/xla/tests:log_test_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests:map_test_cpu PASSED in 13.9s //tensorflow/compiler/xla/tests:matrix_ops_simple_test_cpu PASSED in 18.8s //tensorflow/compiler/xla/tests:multidimensional_slice_test_cpu PASSED in 13.2s //tensorflow/compiler/xla/tests:multiple_devices_on_host_test PASSED in 8.6s //tensorflow/compiler/xla/tests:multithreaded_compilation_test_cpu PASSED in 14.4s //tensorflow/compiler/xla/tests:outfeed_in_nested_computation_test_cpu PASSED in 15.6s //tensorflow/compiler/xla/tests:pad_test_cpu PASSED in 12.9s //tensorflow/compiler/xla/tests:pred_test_cpu PASSED in 12.0s //tensorflow/compiler/xla/tests:query_inferred_shape_test_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests:reduce_hlo_test_cpu PASSED in 22.9s //tensorflow/compiler/xla/tests:reduce_precision_test_cpu PASSED in 17.6s //tensorflow/compiler/xla/tests:replay_test_cpu PASSED in 12.5s //tensorflow/compiler/xla/tests:reshape_motion_test_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests:reverse_test_cpu PASSED in 10.6s //tensorflow/compiler/xla/tests:round_trip_packed_literal_test_cpu PASSED in 10.6s //tensorflow/compiler/xla/tests:round_trip_transfer_test_cpu PASSED in 15.9s //tensorflow/compiler/xla/tests:sample_text_test_cpu PASSED in 10.3s //tensorflow/compiler/xla/tests:scatter_test_cpu PASSED in 24.5s //tensorflow/compiler/xla/tests:select_test_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests:test_utils_test_cpu PASSED in 12.9s //tensorflow/compiler/xla/tests:token_hlo_test_cpu PASSED in 12.9s //tensorflow/compiler/xla/tests:topk_test_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests:transfer_manager_test_cpu PASSED in 28.7s //tensorflow/compiler/xla/tests:transpose_test_cpu PASSED in 13.3s //tensorflow/compiler/xla/tests:tuple_test_cpu PASSED in 15.1s //tensorflow/compiler/xla/tests:unary_op_test_cpu PASSED in 11.8s //tensorflow/compiler/xla/tests:value_inference_test_cpu PASSED in 11.2s //tensorflow/compiler/xla/tests:vector_ops_reduce_test_cpu PASSED in 11.7s //tensorflow/compiler/xla/tests:vector_ops_simple_test_cpu PASSED in 15.9s //tensorflow/compiler/xla/tests:while_test_cpu PASSED in 11.8s //tensorflow/compiler/xla/tests/fuzz:rand_0_cpu PASSED in 9.5s //tensorflow/compiler/xla/tests/fuzz:rand_10_cpu PASSED in 15.2s //tensorflow/compiler/xla/tests/fuzz:rand_11_cpu PASSED in 11.2s //tensorflow/compiler/xla/tests/fuzz:rand_12_cpu PASSED in 13.1s //tensorflow/compiler/xla/tests/fuzz:rand_13_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests/fuzz:rand_14_cpu PASSED in 11.6s //tensorflow/compiler/xla/tests/fuzz:rand_15_cpu PASSED in 10.7s //tensorflow/compiler/xla/tests/fuzz:rand_16_cpu PASSED in 14.3s //tensorflow/compiler/xla/tests/fuzz:rand_17_cpu PASSED in 11.6s //tensorflow/compiler/xla/tests/fuzz:rand_18_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests/fuzz:rand_19_cpu PASSED in 10.9s //tensorflow/compiler/xla/tests/fuzz:rand_20_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests/fuzz:rand_21_cpu PASSED in 12.7s //tensorflow/compiler/xla/tests/fuzz:rand_22_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests/fuzz:rand_23_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests/fuzz:rand_24_cpu PASSED in 10.9s //tensorflow/compiler/xla/tests/fuzz:rand_25_cpu PASSED in 10.4s //tensorflow/compiler/xla/tests/fuzz:rand_26_cpu PASSED in 10.7s //tensorflow/compiler/xla/tests/fuzz:rand_27_cpu PASSED in 11.5s //tensorflow/compiler/xla/tests/fuzz:rand_28_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests/fuzz:rand_29_cpu PASSED in 13.0s //tensorflow/compiler/xla/tests/fuzz:rand_2_cpu PASSED in 10.9s //tensorflow/compiler/xla/tests/fuzz:rand_30_cpu PASSED in 10.4s //tensorflow/compiler/xla/tests/fuzz:rand_31_cpu PASSED in 12.4s //tensorflow/compiler/xla/tests/fuzz:rand_32_cpu PASSED in 11.0s //tensorflow/compiler/xla/tests/fuzz:rand_33_cpu PASSED in 15.1s //tensorflow/compiler/xla/tests/fuzz:rand_34_cpu PASSED in 12.7s //tensorflow/compiler/xla/tests/fuzz:rand_35_cpu PASSED in 11.9s //tensorflow/compiler/xla/tests/fuzz:rand_36_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests/fuzz:rand_37_cpu PASSED in 9.5s //tensorflow/compiler/xla/tests/fuzz:rand_38_cpu PASSED in 14.7s //tensorflow/compiler/xla/tests/fuzz:rand_39_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests/fuzz:rand_3_cpu PASSED in 12.4s //tensorflow/compiler/xla/tests/fuzz:rand_40_cpu PASSED in 12.4s //tensorflow/compiler/xla/tests/fuzz:rand_41_cpu PASSED in 10.2s //tensorflow/compiler/xla/tests/fuzz:rand_42_cpu PASSED in 15.5s //tensorflow/compiler/xla/tests/fuzz:rand_43_cpu PASSED in 16.4s //tensorflow/compiler/xla/tests/fuzz:rand_44_cpu PASSED in 11.7s //tensorflow/compiler/xla/tests/fuzz:rand_45_cpu PASSED in 11.2s //tensorflow/compiler/xla/tests/fuzz:rand_46_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests/fuzz:rand_47_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests/fuzz:rand_48_cpu PASSED in 10.2s //tensorflow/compiler/xla/tests/fuzz:rand_49_cpu PASSED in 11.9s //tensorflow/compiler/xla/tests/fuzz:rand_50_cpu PASSED in 9.9s //tensorflow/compiler/xla/tests/fuzz:rand_51_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests/fuzz:rand_52_cpu PASSED in 10.0s //tensorflow/compiler/xla/tests/fuzz:rand_53_cpu PASSED in 10.8s //tensorflow/compiler/xla/tests/fuzz:rand_54_cpu PASSED in 13.3s //tensorflow/compiler/xla/tests/fuzz:rand_56_cpu PASSED in 11.0s //tensorflow/compiler/xla/tests/fuzz:rand_57_cpu PASSED in 10.8s //tensorflow/compiler/xla/tests/fuzz:rand_58_cpu PASSED in 10.5s //tensorflow/compiler/xla/tests/fuzz:rand_59_cpu PASSED in 13.7s //tensorflow/compiler/xla/tests/fuzz:rand_5_cpu PASSED in 9.9s //tensorflow/compiler/xla/tests/fuzz:rand_61_cpu PASSED in 12.6s //tensorflow/compiler/xla/tests/fuzz:rand_62_cpu PASSED in 15.5s //tensorflow/compiler/xla/tests/fuzz:rand_63_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests/fuzz:rand_64_cpu PASSED in 10.6s //tensorflow/compiler/xla/tests/fuzz:rand_65_cpu PASSED in 12.8s //tensorflow/compiler/xla/tests/fuzz:rand_66_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests/fuzz:rand_68_cpu PASSED in 11.5s //tensorflow/compiler/xla/tests/fuzz:rand_69_cpu PASSED in 15.5s //tensorflow/compiler/xla/tests/fuzz:rand_6_cpu PASSED in 10.3s //tensorflow/compiler/xla/tests/fuzz:rand_70_cpu PASSED in 13.1s //tensorflow/compiler/xla/tests/fuzz:rand_71_cpu PASSED in 11.7s //tensorflow/compiler/xla/tests/fuzz:rand_73_cpu PASSED in 11.7s //tensorflow/compiler/xla/tests/fuzz:rand_74_cpu PASSED in 9.6s //tensorflow/compiler/xla/tests/fuzz:rand_75_cpu PASSED in 11.6s //tensorflow/compiler/xla/tests/fuzz:rand_76_cpu PASSED in 13.0s //tensorflow/compiler/xla/tests/fuzz:rand_77_cpu PASSED in 12.7s //tensorflow/compiler/xla/tests/fuzz:rand_78_cpu PASSED in 13.3s //tensorflow/compiler/xla/tests/fuzz:rand_79_cpu PASSED in 13.8s //tensorflow/compiler/xla/tests/fuzz:rand_7_cpu PASSED in 9.3s //tensorflow/compiler/xla/tests/fuzz:rand_80_cpu PASSED in 11.0s //tensorflow/compiler/xla/tests/fuzz:rand_81_cpu PASSED in 10.6s //tensorflow/compiler/xla/tests/fuzz:rand_82_cpu PASSED in 15.7s //tensorflow/compiler/xla/tests/fuzz:rand_83_cpu PASSED in 13.2s //tensorflow/compiler/xla/tests/fuzz:rand_84_cpu PASSED in 12.7s //tensorflow/compiler/xla/tests/fuzz:rand_85_cpu PASSED in 12.1s //tensorflow/compiler/xla/tests/fuzz:rand_86_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests/fuzz:rand_87_cpu PASSED in 12.8s //tensorflow/compiler/xla/tests/fuzz:rand_88_cpu PASSED in 11.5s //tensorflow/compiler/xla/tests/fuzz:rand_89_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests/fuzz:rand_8_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests/fuzz:rand_90_cpu PASSED in 12.0s //tensorflow/compiler/xla/tests/fuzz:rand_91_cpu PASSED in 10.1s //tensorflow/compiler/xla/tests/fuzz:rand_92_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests/fuzz:rand_93_cpu PASSED in 11.1s //tensorflow/compiler/xla/tests/fuzz:rand_94_cpu PASSED in 11.2s //tensorflow/compiler/xla/tests/fuzz:rand_95_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests/fuzz:rand_96_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests/fuzz:rand_97_cpu PASSED in 15.6s //tensorflow/compiler/xla/tests/fuzz:rand_98_cpu PASSED in 14.6s //tensorflow/compiler/xla/tests/fuzz:rand_99_cpu PASSED in 12.3s //tensorflow/compiler/xla/tests/fuzz:rand_9_cpu PASSED in 11.8s //tensorflow/compiler/xla/tools:hlo_control_flow_flattening_test PASSED in 2.7s //tensorflow/compiler/xla/tools:hlo_extractor_test PASSED in 2.3s //tensorflow/compiler/xla/tools:hlo_module_loader_test PASSED in 1.0s //tensorflow/compiler/xla/tools:interactive_graphviz_bin_test PASSED in 0.3s //tensorflow/compiler/xla/tools:run_hlo_module_bin_test PASSED in 1.3s //tensorflow/compiler/xla/tools/hlo_bisect:hlo_bisect_state_test PASSED in 1.2s //tensorflow/compiler/xla/translate/hlo_to_mhlo:hlo_utils_test PASSED in 1.4s //tensorflow/compiler/xla/translate/hlo_to_mhlo:mlir_hlo_builder_test PASSED in 2.0s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:bool_compare.hlotxt.test PASSED in 0.8s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:case_conditional.hlotxt.test PASSED in 1.4s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:dynamic_param.hlo.test PASSED in 1.4s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:entry_computation_layout.hlotxt.test PASSED in 0.4s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:frontend_attributes.hlotxt.test PASSED in 0.4s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:fully_connected_reference_model.hlotxt.test PASSED in 1.0s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:fusion.hlotxt.test PASSED in 0.4s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:if_conditional.hlotxt.test PASSED in 0.4s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:import.hlotxt.test PASSED in 1.3s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:import_async.hlotxt.test PASSED in 1.1s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:layouts_and_names.hlotxt.test PASSED in 0.6s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:location.hlotxt.test PASSED in 0.6s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:module_attributes.hlo.test PASSED in 0.5s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:simple.hlo.test PASSED in 0.6s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:spmd_module_sharding.hlo.test PASSED in 0.5s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:types.hlotxt.test PASSED in 1.3s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:while.hlotxt.test PASSED in 0.7s //tensorflow/compiler/xla/translate/mhlo_to_hlo:type_to_shape_test PASSED in 0.9s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:add.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:case.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:dynamic.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export-with-layouts.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export.mlir.test PASSED in 2.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export_and_check_layouts.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export_large_constants.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export_replicas.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:frontend_attributes.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:fusion.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:if.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:input_output_aliasing.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:layouts_and_names.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:location_to_op_metadata.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:missing_main.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:module_attributes.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:multiple_return_tuple.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:opaque_elements_attr.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:rng_get_and_update_state.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:sharding.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:simple.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:unsupported_type.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:while.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_lhlo_with_xla/tests:hlo_text_to_lhlo_no_opt.hlotxt.test PASSED in 1.2s //tensorflow/compiler/xla/translate/mhlo_to_lhlo_with_xla/tests:no_opt_ops.hlotxt.test PASSED in 1.1s //tensorflow/compiler/xla/translate/mhlo_to_lhlo_with_xla/tests:non_identity_layouts.hlotxt.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_lhlo_with_xla/tests:ops.mlir.test PASSED in 2.2s //tensorflow/compiler/xla/translate/mhlo_to_lhlo_with_xla/tests:passthrough.mlir.test PASSED in 1.1s //tensorflow/core:__tensorflow_core_lib_core_legacy_lib_core_all_tests PASSED in 7.2s //tensorflow/core:__tensorflow_core_lib_gtl_legacy_lib_gtl_tests PASSED in 1.0s //tensorflow/core:__tensorflow_core_lib_monitoring_cell_reader_test PASSED in 37.9s //tensorflow/core:__tensorflow_core_lib_monitoring_collection_registry_test PASSED in 0.1s //tensorflow/core:__tensorflow_core_lib_monitoring_counter_test PASSED in 0.7s //tensorflow/core:__tensorflow_core_lib_monitoring_gauge_test PASSED in 0.1s //tensorflow/core:__tensorflow_core_lib_monitoring_metric_def_test PASSED in 0.6s //tensorflow/core:__tensorflow_core_lib_monitoring_percentile_sampler_test PASSED in 0.6s //tensorflow/core:__tensorflow_core_lib_monitoring_sampler_test PASSED in 0.6s //tensorflow/core:__tensorflow_core_lib_monitoring_test_utils_test PASSED in 0.4s //tensorflow/core:__tensorflow_core_lib_strings_legacy_low_level_library_tests PASSED in 0.4s //tensorflow/core:__tensorflow_core_lib_wav_wav_io_test PASSED in 0.5s //tensorflow/core:__tensorflow_core_util_mkl_util_test_srcs PASSED in 0.5s //tensorflow/core:__tensorflow_tsl_lib_core_legacy_lib_core_all_tests PASSED in 0.4s //tensorflow/core:lib_strings_ordered_code_test PASSED in 1.2s //tensorflow/core:lib_strings_proto_serialization_test PASSED in 0.1s //tensorflow/core/api_def:api_test PASSED in 4.4s //tensorflow/core/api_def:update_api_def_test PASSED in 0.4s //tensorflow/core/common_runtime:all_to_all_test_cpu PASSED in 1.9s //tensorflow/core/common_runtime:arg_ret_placement_test PASSED in 0.5s //tensorflow/core/common_runtime:buf_rendezvous_test PASSED in 0.8s //tensorflow/core/common_runtime:collective_executor_mgr_test PASSED in 1.5s //tensorflow/core/common_runtime:collective_param_resolver_local_test PASSED in 5.8s //tensorflow/core/common_runtime:collective_rma_local_test PASSED in 1.7s //tensorflow/core/common_runtime:composite_device_test PASSED in 0.5s //tensorflow/core/common_runtime:cost_measurement_registry_test PASSED in 2.3s //tensorflow/core/common_runtime:cost_util_test PASSED in 0.3s //tensorflow/core/common_runtime:device_mgr_test PASSED in 0.9s //tensorflow/core/common_runtime:device_propagation_test PASSED in 0.7s //tensorflow/core/common_runtime:device_resolver_local_test PASSED in 1.4s //tensorflow/core/common_runtime:device_set_test PASSED in 1.4s //tensorflow/core/common_runtime:direct_session_test_cpu PASSED in 2.4s //tensorflow/core/common_runtime:direct_session_with_debug_test PASSED in 4.3s //tensorflow/core/common_runtime:direct_session_with_tracking_alloc_test PASSED in 1.4s //tensorflow/core/common_runtime:dynamic_device_mgr_test PASSED in 1.3s //tensorflow/core/common_runtime:eval_const_tensor_test PASSED in 0.8s //tensorflow/core/common_runtime:executor_test PASSED in 2.3s //tensorflow/core/common_runtime:function_optimization_registration_test PASSED in 1.5s //tensorflow/core/common_runtime:function_optimization_registry_no_pass_test PASSED in 1.1s //tensorflow/core/common_runtime:function_optimization_registry_pass_failure_test PASSED in 1.1s //tensorflow/core/common_runtime:function_optimization_registry_test PASSED in 1.6s //tensorflow/core/common_runtime:function_threadpool_test PASSED in 5.7s //tensorflow/core/common_runtime:graph_constructor_test PASSED in 2.5s //tensorflow/core/common_runtime:graph_runner_test PASSED in 1.6s //tensorflow/core/common_runtime:hierarchical_tree_broadcaster_test_cpu PASSED in 3.8s //tensorflow/core/common_runtime:inline_function_utils_test PASSED in 1.2s //tensorflow/core/common_runtime:input_colocation_exemption_registry_test PASSED in 0.7s //tensorflow/core/common_runtime:int32_fulltype_test PASSED in 1.4s //tensorflow/core/common_runtime:isolate_placer_inspection_required_ops_pass_test PASSED in 2.4s //tensorflow/core/common_runtime:lower_case_op_test PASSED in 2.8s //tensorflow/core/common_runtime:lower_function_call_test PASSED in 3.3s //tensorflow/core/common_runtime:lower_functional_ops_test PASSED in 2.7s //tensorflow/core/common_runtime:lower_if_op_test PASSED in 2.8s //tensorflow/core/common_runtime:lower_while_op_test PASSED in 3.5s //tensorflow/core/common_runtime:mkl_cpu_allocator_test PASSED in 0.5s //tensorflow/core/common_runtime:mkl_threadpool_device_test PASSED in 0.2s //tensorflow/core/common_runtime:no_op_cost_measurement_test PASSED in 0.2s //tensorflow/core/common_runtime:null_request_cost_accessor_test PASSED in 0.6s //tensorflow/core/common_runtime:optimization_registry_test PASSED in 1.3s //tensorflow/core/common_runtime:optimize_cross_host_control_deps_test PASSED in 7.5s //tensorflow/core/common_runtime:optimize_function_graph_utils_test PASSED in 1.4s //tensorflow/core/common_runtime:partitioning_utils_test PASSED in 1.2s //tensorflow/core/common_runtime:pending_counts_test PASSED in 1.1s //tensorflow/core/common_runtime:permuter_test_cpu PASSED in 3.8s //tensorflow/core/common_runtime:placer_inspection_required_ops_utils_test PASSED in 1.3s //tensorflow/core/common_runtime:placer_test PASSED in 1.3s //tensorflow/core/common_runtime:process_function_library_runtime_test_cpu PASSED in 0.9s //tensorflow/core/common_runtime:process_util_test PASSED in 0.1s //tensorflow/core/common_runtime:quantize_training_test PASSED in 3.3s //tensorflow/core/common_runtime:rendezvous_util_test PASSED in 0.1s //tensorflow/core/common_runtime:replicate_per_replica_nodes_test PASSED in 0.9s //tensorflow/core/common_runtime:request_cost_accessor_registry_test PASSED in 2.8s //tensorflow/core/common_runtime:request_cost_test PASSED in 0.3s //tensorflow/core/common_runtime:ring_gatherer_test_cpu PASSED in 5.7s //tensorflow/core/common_runtime:ring_reducer_test_cpu PASSED in 9.5s //tensorflow/core/common_runtime:scoped_allocator_mgr_test PASSED in 6.1s //tensorflow/core/common_runtime:session_test PASSED in 0.9s //tensorflow/core/common_runtime:shape_refiner_test PASSED in 1.7s //tensorflow/core/common_runtime:single_threaded_executor_test PASSED in 1.3s //tensorflow/core/common_runtime:threadpool_device_test PASSED in 0.7s //tensorflow/core/common_runtime:type_inference_test PASSED in 7.2s //tensorflow/core/common_runtime/eager:attr_builder_test PASSED in 33.3s //tensorflow/core/common_runtime/eager:context_test PASSED in 16.3s //tensorflow/core/common_runtime/eager:custom_device_test PASSED in 17.9s //tensorflow/core/common_runtime/eager:eager_executor_test PASSED in 21.6s //tensorflow/core/common_runtime/eager:eager_op_rewrite_registry_test PASSED in 1.7s //tensorflow/core/common_runtime/eager:eager_operation_test PASSED in 21.4s //tensorflow/core/common_runtime/eager:execute_node_test PASSED in 16.5s //tensorflow/core/common_runtime/eager:execute_test PASSED in 43.4s //tensorflow/core/common_runtime/eager:kernel_and_device_test PASSED in 1.3s //tensorflow/core/common_runtime/eager:mkl_eager_op_rewrite_test PASSED in 16.0s //tensorflow/core/common_runtime/eager:placement_test PASSED in 22.4s //tensorflow/core/common_runtime/eager:placement_utils_test PASSED in 23.6s //tensorflow/core/common_runtime/eager:tensor_handle_data_test PASSED in 18.2s //tensorflow/core/common_runtime/eager:tensor_handle_test PASSED in 19.6s //tensorflow/core/common_runtime/gpu:gpu_device_on_non_gpu_machine_test PASSED in 0.7s //tensorflow/core/common_runtime/next_pluggable_device/c:plugin_c_api_test PASSED in 41.2s //tensorflow/core/config:flags_py_test PASSED in 6.9s //tensorflow/core/config:flags_test PASSED in 0.1s //tensorflow/core/data:compression_utils_test PASSED in 3.9s //tensorflow/core/data:dataset_utils_test PASSED in 0.6s //tensorflow/core/data:hash_utils_test PASSED in 1.5s //tensorflow/core/data:metric_utils_test PASSED in 5.8s //tensorflow/core/data:name_utils_test PASSED in 0.1s //tensorflow/core/data:rewrite_utils_test PASSED in 0.9s //tensorflow/core/data:serialization_utils_test PASSED in 0.7s //tensorflow/core/data:snapshot_utils_test PASSED in 1.3s //tensorflow/core/data:split_utils_test PASSED in 1.0s //tensorflow/core/data:standalone_save_restore_test PASSED in 3.2s //tensorflow/core/data:standalone_test PASSED in 3.1s //tensorflow/core/data:tfdataz_metrics_test PASSED in 2.5s //tensorflow/core/data:unbounded_thread_pool_test PASSED in 1.2s //tensorflow/core/data/service:auto_shard_rewriter_test PASSED in 0.7s //tensorflow/core/data/service:common_test PASSED in 0.2s //tensorflow/core/data/service:credentials_factory_test PASSED in 0.8s //tensorflow/core/data/service:cross_trainer_cache_test PASSED in 2.3s //tensorflow/core/data/service:data_service_test PASSED in 21.7s //tensorflow/core/data/service:data_transfer_test PASSED in 0.9s //tensorflow/core/data/service:dataset_store_test PASSED in 2.1s //tensorflow/core/data/service:dispatcher_client_test PASSED in 5.0s //tensorflow/core/data/service:dispatcher_state_test PASSED in 1.7s //tensorflow/core/data/service:grpc_dispatcher_impl_test PASSED in 6.1s //tensorflow/core/data/service:grpc_util_test PASSED in 1.1s //tensorflow/core/data/service:grpc_worker_impl_test PASSED in 5.1s //tensorflow/core/data/service:journal_test PASSED in 1.1s //tensorflow/core/data/service:logging_utils_test PASSED in 0.2s //tensorflow/core/data/service:task_runner_test PASSED in 6.7s //tensorflow/core/data/service:test_util_test PASSED in 7.3s //tensorflow/core/data/service:url_test PASSED in 0.3s //tensorflow/core/data/service:utils_test PASSED in 1.3s //tensorflow/core/data/service:validate_utils_test PASSED in 0.2s //tensorflow/core/data/service:worker_client_test PASSED in 3.9s //tensorflow/core/data/service:worker_impl_test PASSED in 4.5s //tensorflow/core/data/service/client:data_service_client_test PASSED in 4.8s //tensorflow/core/data/service/client:utils_test PASSED in 5.2s //tensorflow/core/data/service/client:validate_utils_test PASSED in 2.6s //tensorflow/core/data/service/snapshot:distributed_snapshot_test PASSED in 19.5s //tensorflow/core/data/service/snapshot:file_utils_test PASSED in 1.0s //tensorflow/core/data/service/snapshot:path_utils_test PASSED in 0.1s //tensorflow/core/data/service/snapshot:snapshot_manager_test PASSED in 2.7s //tensorflow/core/data/service/snapshot:snapshot_split_provider_test PASSED in 1.6s //tensorflow/core/data/service/snapshot:snapshot_stream_writer_checkpoint_test PASSED in 4.6s //tensorflow/core/data/service/snapshot:snapshot_stream_writer_test PASSED in 3.1s //tensorflow/core/data/service/snapshot:utils_test PASSED in 0.1s //tensorflow/core/debug:debug_graph_utils_test PASSED in 0.7s //tensorflow/core/distributed_runtime:call_options_test PASSED in 0.1s //tensorflow/core/distributed_runtime:cluster_function_library_runtime_test PASSED in 6.3s //tensorflow/core/distributed_runtime:collective_param_resolver_distributed_test PASSED in 1.0s //tensorflow/core/distributed_runtime:collective_rma_distributed_test PASSED in 2.1s //tensorflow/core/distributed_runtime:device_resolver_distributed_test PASSED in 1.1s //tensorflow/core/distributed_runtime:message_wrappers_test PASSED in 0.7s //tensorflow/core/distributed_runtime:partial_run_mgr_test PASSED in 0.6s //tensorflow/core/distributed_runtime:recent_request_ids_test PASSED in 0.2s //tensorflow/core/distributed_runtime:request_id_test PASSED in 0.1s //tensorflow/core/distributed_runtime:rpc_collective_executor_mgr_test PASSED in 0.7s //tensorflow/core/distributed_runtime:server_lib_test PASSED in 0.1s //tensorflow/core/distributed_runtime:session_mgr_test PASSED in 0.7s //tensorflow/core/distributed_runtime:tensor_coding_test PASSED in 0.3s //tensorflow/core/distributed_runtime/coordination:coordination_service_barrier_proxy_test PASSED in 3.9s //tensorflow/core/distributed_runtime/eager:eager_service_impl_test PASSED in 23.6s //tensorflow/core/distributed_runtime/eager:remote_mgr_test PASSED in 17.9s //tensorflow/core/distributed_runtime/integration_test:c_api_coordination_test_cpu PASSED in 56.9s //tensorflow/core/distributed_runtime/integration_test:c_api_multi_client_test_cpu PASSED in 41.3s //tensorflow/core/distributed_runtime/integration_test:c_api_recoverable_jobs_test_cpu PASSED in 50.9s //tensorflow/core/distributed_runtime/integration_test:c_api_session_coordination_test_cpu PASSED in 50.0s //tensorflow/core/distributed_runtime/rpc:grpc_tensor_coding_test PASSED in 4.6s //tensorflow/core/distributed_runtime/rpc:grpc_worker_cache_test PASSED in 1.6s //tensorflow/core/distributed_runtime/rpc/eager:grpc_eager_client_test PASSED in 0.8s //tensorflow/core/example:example_parser_configuration_test PASSED in 2.6s //tensorflow/core/example:feature_util_test PASSED in 0.6s //tensorflow/core/framework:allocator_test PASSED in 4.7s //tensorflow/core/framework:attr_value_util_test PASSED in 1.3s //tensorflow/core/framework:batch_util_test PASSED in 0.9s //tensorflow/core/framework:bfloat16_test PASSED in 1.3s //tensorflow/core/framework:common_shape_fns_test PASSED in 1.4s //tensorflow/core/framework:dataset_test PASSED in 0.8s //tensorflow/core/framework:device_base_test PASSED in 2.7s //tensorflow/core/framework:disable_jit_test PASSED in 1.0s //tensorflow/core/framework:framework_op_gen_lib_test PASSED in 0.5s //tensorflow/core/framework:framework_op_segment_test PASSED in 1.5s //tensorflow/core/framework:framework_resource_var_test PASSED in 0.2s //tensorflow/core/framework:framework_run_handler_test PASSED in 2.6s //tensorflow/core/framework:framework_run_handler_util_test PASSED in 3.9s //tensorflow/core/framework:full_type_inference_util_test PASSED in 2.6s //tensorflow/core/framework:full_type_util_test PASSED in 0.7s //tensorflow/core/framework:function_test PASSED in 0.7s //tensorflow/core/framework:graph_def_util_test PASSED in 1.7s //tensorflow/core/framework:graph_to_functiondef_test PASSED in 0.9s //tensorflow/core/framework:kernel_def_builder_test PASSED in 0.9s //tensorflow/core/framework:kernel_def_util_test PASSED in 0.7s //tensorflow/core/framework:memory_types_test PASSED in 1.0s //tensorflow/core/framework:model_test PASSED in 2.0s //tensorflow/core/framework:node_def_builder_test PASSED in 1.0s //tensorflow/core/framework:node_def_util_test PASSED in 1.9s //tensorflow/core/framework:node_properties_test PASSED in 1.7s //tensorflow/core/framework:op_compatibility_test PASSED in 3.0s //tensorflow/core/framework:op_def_builder_test PASSED in 1.2s //tensorflow/core/framework:op_def_util_test PASSED in 0.9s //tensorflow/core/framework:op_kernel_test PASSED in 1.2s //tensorflow/core/framework:op_registration_test PASSED in 1.3s //tensorflow/core/framework:partial_tensor_shape_test PASSED in 1.9s //tensorflow/core/framework:rendezvous_test PASSED in 4.0s //tensorflow/core/framework:resource_handle_test PASSED in 0.1s //tensorflow/core/framework:resource_mgr_test PASSED in 1.8s //tensorflow/core/framework:resource_op_kernel_test PASSED in 2.0s //tensorflow/core/framework:shape_inference_test PASSED in 0.8s //tensorflow/core/framework:shape_inference_testutil_test PASSED in 0.7s //tensorflow/core/framework:tensor_shape_test PASSED in 8.2s //tensorflow/core/framework:tensor_slice_test PASSED in 1.2s //tensorflow/core/framework:tensor_test PASSED in 33.7s //tensorflow/core/framework:tensor_testutil_test PASSED in 2.0s //tensorflow/core/framework:tensor_util_test PASSED in 1.6s //tensorflow/core/framework:tracking_allocator_test PASSED in 1.2s //tensorflow/core/framework:types_test PASSED in 2.1s //tensorflow/core/framework:variant_op_registry_test PASSED in 22.1s //tensorflow/core/framework:variant_test PASSED in 1.1s //tensorflow/core/framework/registration:registration_test PASSED in 1.4s //tensorflow/core/function/capture:by_ref_capture_test PASSED in 8.7s //tensorflow/core/function/capture:capture_container_test PASSED in 6.7s //tensorflow/core/function/integration_test:side_inputs_manual_api_test PASSED in 15.8s //tensorflow/core/function/integration_test:side_inputs_test PASSED in 14.1s //tensorflow/core/function/polymorphism:function_cache_test PASSED in 10.4s //tensorflow/core/function/polymorphism:function_type_test PASSED in 7.2s //tensorflow/core/function/polymorphism:type_dispatch_test PASSED in 6.9s //tensorflow/core/function/runtime_client:runtime_client_cc_test PASSED in 46.4s //tensorflow/core/function/trace_type:default_types_test PASSED in 7.1s //tensorflow/core/function/trace_type:serialization_test PASSED in 6.5s //tensorflow/core/function/trace_type:trace_type_test PASSED in 11.6s //tensorflow/core/graph:algorithm_test PASSED in 1.0s //tensorflow/core/graph:collective_order_test PASSED in 1.1s //tensorflow/core/graph:control_flow_test PASSED in 0.7s //tensorflow/core/graph:costmodel_test PASSED in 1.5s //tensorflow/core/graph:edgeset_test PASSED in 2.8s //tensorflow/core/graph:graph_def_builder_test PASSED in 2.9s //tensorflow/core/graph:graph_partition_test PASSED in 1.4s //tensorflow/core/graph:graph_test PASSED in 1.1s //tensorflow/core/graph:node_builder_test PASSED in 1.6s //tensorflow/core/graph:optimizer_cse_test PASSED in 1.3s //tensorflow/core/graph:subgraph_test PASSED in 1.2s //tensorflow/core/graph:tensor_id_test PASSED in 0.9s //tensorflow/core/graph:validate_test PASSED in 1.3s //tensorflow/core/graph/regularization:simple_delete_test PASSED in 0.9s //tensorflow/core/graph/regularization:util_test PASSED in 0.7s //tensorflow/core/grappler:graph_topology_view_test PASSED in 0.2s //tensorflow/core/grappler:graph_view_test PASSED in 4.0s //tensorflow/core/grappler:grappler_item_builder_test PASSED in 3.4s //tensorflow/core/grappler:grappler_item_test PASSED in 3.5s //tensorflow/core/grappler:mutable_graph_view_test PASSED in 2.9s //tensorflow/core/grappler:utils_test PASSED in 3.9s //tensorflow/core/grappler/clusters:single_machine_test PASSED in 25.4s //tensorflow/core/grappler/clusters:virtual_cluster_test PASSED in 1.6s //tensorflow/core/grappler/costs:analytical_cost_estimator_test PASSED in 3.0s //tensorflow/core/grappler/costs:cost_estimator_test PASSED in 0.1s //tensorflow/core/grappler/costs:graph_memory_test PASSED in 1.8s //tensorflow/core/grappler/costs:graph_properties_test PASSED in 11.4s //tensorflow/core/grappler/costs:robust_stats_test PASSED in 0.3s //tensorflow/core/grappler/costs:utils_test PASSED in 2.9s //tensorflow/core/grappler/costs:virtual_placer_test PASSED in 0.7s //tensorflow/core/grappler/costs:virtual_scheduler_test PASSED in 3.4s //tensorflow/core/grappler/graph_analyzer:gen_node_test PASSED in 2.0s //tensorflow/core/grappler/graph_analyzer:graph_analyzer_test PASSED in 2.4s //tensorflow/core/grappler/graph_analyzer:hash_tools_test PASSED in 3.1s //tensorflow/core/grappler/graph_analyzer:sig_node_test PASSED in 5.6s //tensorflow/core/grappler/graph_analyzer:subgraph_test PASSED in 1.7s //tensorflow/core/grappler/inputs:utils_test PASSED in 0.5s //tensorflow/core/grappler/optimizers:arithmetic_optimizer_test_cpu PASSED in 7.1s //tensorflow/core/grappler/optimizers:auto_parallel_test_cpu PASSED in 2.8s //tensorflow/core/grappler/optimizers:common_subgraph_elimination_test_cpu PASSED in 3.9s //tensorflow/core/grappler/optimizers:custom_graph_optimizer_registry_test_cpu PASSED in 5.6s //tensorflow/core/grappler/optimizers:debug_stripper_test_cpu PASSED in 3.6s //tensorflow/core/grappler/optimizers:dependency_optimizer_test_cpu PASSED in 3.9s //tensorflow/core/grappler/optimizers:evaluation_utils_test PASSED in 1.5s //tensorflow/core/grappler/optimizers:function_api_info_test PASSED in 0.3s //tensorflow/core/grappler/optimizers:function_optimizer_test_cpu PASSED in 4.6s //tensorflow/core/grappler/optimizers:generic_layout_optimizer_test_cpu PASSED in 6.1s //tensorflow/core/grappler/optimizers:generic_layout_optimizer_transposer_factory_test PASSED in 0.3s //tensorflow/core/grappler/optimizers:generic_layout_optimizer_transposer_test_cpu PASSED in 3.9s //tensorflow/core/grappler/optimizers:graph_optimizer_stage_test_cpu PASSED in 3.3s //tensorflow/core/grappler/optimizers:implementation_selector_test PASSED in 4.0s //tensorflow/core/grappler/optimizers:loop_optimizer_test_cpu PASSED in 4.4s //tensorflow/core/grappler/optimizers:memory_optimizer_test_cpu PASSED in 4.8s //tensorflow/core/grappler/optimizers:meta_optimizer_test_cpu PASSED in 9.0s //tensorflow/core/grappler/optimizers:mkl_remapper_test PASSED in 3.2s //tensorflow/core/grappler/optimizers:model_pruner_test_cpu PASSED in 2.6s //tensorflow/core/grappler/optimizers:pin_to_host_optimizer_test_cpu PASSED in 3.7s //tensorflow/core/grappler/optimizers:scoped_allocator_optimizer_test PASSED in 6.1s //tensorflow/core/grappler/optimizers:shape_optimizer_test_cpu PASSED in 2.7s //tensorflow/core/grappler/optimizers:static_schedule_test_cpu PASSED in 2.7s //tensorflow/core/grappler/optimizers:tfg_optimizer_hook_test PASSED in 0.8s //tensorflow/core/grappler/optimizers/data:auto_shard_test PASSED in 1.4s //tensorflow/core/grappler/optimizers/data:autotune_buffer_sizes_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:batch_parallelization_test PASSED in 0.6s //tensorflow/core/grappler/optimizers/data:disable_intra_op_parallelism_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:disable_prefetch_legacy_autotune_test PASSED in 0.5s //tensorflow/core/grappler/optimizers/data:enable_gradient_descent_test PASSED in 1.5s //tensorflow/core/grappler/optimizers/data:filter_fusion_test PASSED in 1.2s //tensorflow/core/grappler/optimizers/data:filter_parallelization_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:function_utils_test PASSED in 0.9s //tensorflow/core/grappler/optimizers/data:fusion_utils_test PASSED in 0.9s //tensorflow/core/grappler/optimizers/data:graph_utils_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:inject_prefetch_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:make_deterministic_test PASSED in 1.4s //tensorflow/core/grappler/optimizers/data:make_sloppy_test PASSED in 0.9s //tensorflow/core/grappler/optimizers/data:map_and_batch_fusion_test PASSED in 0.4s //tensorflow/core/grappler/optimizers/data:map_and_filter_fusion_test PASSED in 0.8s //tensorflow/core/grappler/optimizers/data:map_fusion_test PASSED in 0.5s //tensorflow/core/grappler/optimizers/data:map_parallelization_test PASSED in 0.9s //tensorflow/core/grappler/optimizers/data:noop_elimination_test PASSED in 0.6s //tensorflow/core/grappler/optimizers/data:parallel_batch_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:replicate_on_split_test PASSED in 1.2s //tensorflow/core/grappler/optimizers/data:shuffle_and_repeat_fusion_test PASSED in 0.4s //tensorflow/core/grappler/optimizers/data:slack_test PASSED in 1.6s //tensorflow/core/grappler/optimizers/data:split_utils_test PASSED in 3.4s //tensorflow/core/grappler/optimizers/data:use_private_thread_pool_test PASSED in 0.6s //tensorflow/core/grappler/optimizers/inference:batch_op_rewriter_test PASSED in 0.6s //tensorflow/core/grappler/utils:canonicalizer_test PASSED in 1.6s //tensorflow/core/grappler/utils:colocation_test PASSED in 1.0s //tensorflow/core/grappler/utils:frame_test PASSED in 0.2s //tensorflow/core/grappler/utils:functions_test PASSED in 2.1s //tensorflow/core/grappler/utils:graph_view_internal_test PASSED in 1.0s //tensorflow/core/grappler/utils:graph_view_test PASSED in 2.7s //tensorflow/core/grappler/utils:grappler_test_test PASSED in 7.6s //tensorflow/core/grappler/utils:pattern_utils_test PASSED in 0.8s //tensorflow/core/grappler/utils:scc_test PASSED in 1.9s //tensorflow/core/grappler/utils:symbolic_shapes_test PASSED in 0.7s //tensorflow/core/grappler/utils:topological_sort_test PASSED in 0.7s //tensorflow/core/grappler/utils:tpu_test PASSED in 0.5s //tensorflow/core/grappler/utils:transitive_fanin_test PASSED in 1.1s //tensorflow/core/grappler/utils:traversal_test PASSED in 0.7s //tensorflow/core/grappler/verifiers:structure_verifier_test PASSED in 4.4s //tensorflow/core/ir:interfaces_test PASSED in 0.2s //tensorflow/core/ir:ops_test PASSED in 1.1s //tensorflow/core/ir:shape_inference_utils_test PASSED in 0.4s //tensorflow/core/ir:tf_op_registry_test PASSED in 0.4s //tensorflow/core/ir:tf_op_wrapper_test PASSED in 0.3s //tensorflow/core/ir:utility_test PASSED in 0.2s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:arg_as_control_ret.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:backedge_segment.pbtxt.test PASSED in 1.0s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:empty.pbtxt.test PASSED in 1.1s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:error_during_backedge.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:import_case_with_attr_inference.pbtxt.test PASSED in 1.4s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:import_if_with_attr_inference.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:import_iterator_get_next_attr_inference.pbtxt.test PASSED in 1.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:import_underscore_output_shapes.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:import_while_with_attr_inference.pbtxt.test PASSED in 1.3s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:infeed_dequeue.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:infer_arg_handle_type.pbtxt.test PASSED in 1.1s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:infer_with_output_shapes.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_arg_name.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_backedge_input_size.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_duplicated_node_name.pbtxt.test PASSED in 1.1s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_edge_index.pbtxt.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_edge_name.pbtxt.test PASSED in 1.4s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_empty_attr_key.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_empty_func_attr_key.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_empty_func_attr_name.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_empty_op_type.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_func_with_empty_name.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_function_import.pbtxt.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_func_with_empty_control_result.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_func_with_empty_input.pbtxt.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_func_with_empty_name.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_func_with_empty_result.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_function_attr_name.pbtxt.test PASSED in 1.7s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_function_named_edge_index.pbtxt.test PASSED in 1.0s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_handle_data.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_control_input.pbtxt.test PASSED in 0.4s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_control_result.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_control_result_value.pbtxt.test PASSED in 0.7s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_data_result.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_data_result_value.pbtxt.test PASSED in 1.3s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_input.pbtxt.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_two_inputs.pbtxt.test PASSED in 1.0s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_named_edge_index.pbtxt.test PASSED in 1.0s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_op_name.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_type_list.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:legacy_call.pbtxt.test PASSED in 1.1s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:negative_shape.pbtxt.test PASSED in 1.1s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:negative_zero_constant.pbtxt.test PASSED in 1.0s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:three_nodes_with_attrs.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:version.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:empty.mlir.test PASSED in 1.7s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:fulltype.mlir.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:func_with_no_args_or_results.mlir.test PASSED in 1.5s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:negative_zero_constant.mlir.test PASSED in 1.3s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:nested_legacy_call.mlir.test PASSED in 1.3s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:three_nodes_with_attrs.mlir.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:version.mlir.test PASSED in 1.0s //tensorflow/core/ir/importexport/tests/saved_model:saved_model_roundtrip_test PASSED in 0.4s //tensorflow/core/ir/tests:attributes.mlir.test PASSED in 0.5s //tensorflow/core/ir/tests:canonicalize.mlir.test PASSED in 0.7s //tensorflow/core/ir/tests:compatible_types.mlir.test PASSED in 0.9s //tensorflow/core/ir/tests:concrete-ops.mlir.test PASSED in 1.1s //tensorflow/core/ir/tests:generic_concrete_ops.mlir.test PASSED in 0.4s //tensorflow/core/ir/tests:invalid-concrete-ops.mlir.test PASSED in 1.4s //tensorflow/core/ir/tests:invalid-preserved-attrs.mlir.test PASSED in 0.5s //tensorflow/core/ir/tests:invalid.mlir.test PASSED in 0.4s //tensorflow/core/ir/tests:invalid_types.mlir.test PASSED in 0.8s //tensorflow/core/ir/tests:ops.mlir.test PASSED in 0.9s //tensorflow/core/ir/tests:region-invalid-ops.mlir.test PASSED in 0.7s //tensorflow/core/ir/tests:region-ops-graph.mlir.test PASSED in 0.7s //tensorflow/core/ir/tests:region-ops.mlir.test PASSED in 0.6s //tensorflow/core/ir/tests:types.mlir.test PASSED in 0.4s //tensorflow/core/ir/types:dialect_test PASSED in 0.8s //tensorflow/core/kernels:as_string_op_test PASSED in 2.6s //tensorflow/core/kernels:basic_ops_benchmark_test PASSED in 0.6s //tensorflow/core/kernels:batch_kernels_env_test PASSED in 0.9s //tensorflow/core/kernels:batch_kernels_test PASSED in 1.2s //tensorflow/core/kernels:bias_op_test PASSED in 0.6s //tensorflow/core/kernels:bincount_op_test_cpu PASSED in 0.7s //tensorflow/core/kernels:broadcast_to_op_test_cpu PASSED in 1.0s //tensorflow/core/kernels:cast_op_test_cpu PASSED in 1.9s //tensorflow/core/kernels:checkpoint_callback_manager_test PASSED in 1.9s //tensorflow/core/kernels:clustering_ops_test PASSED in 0.6s //tensorflow/core/kernels:composite_tensor_variant_test PASSED in 0.5s //tensorflow/core/kernels:concat_op_test PASSED in 0.8s //tensorflow/core/kernels:constant_op_test_cpu PASSED in 0.6s //tensorflow/core/kernels:control_flow_ops_test PASSED in 8.1s //tensorflow/core/kernels:conv_grad_filter_ops_benchmark_test_cpu PASSED in 1.4s //tensorflow/core/kernels:conv_grad_input_ops_benchmark_test_cpu PASSED in 0.8s //tensorflow/core/kernels:conv_ops_benchmark_test_cpu PASSED in 1.9s //tensorflow/core/kernels:conv_ops_test_cpu PASSED in 19.8s //tensorflow/core/kernels:count_ops_test PASSED in 1.1s //tensorflow/core/kernels:cross_op_test PASSED in 1.2s //tensorflow/core/kernels:cwise_ops_test_cpu PASSED in 0.7s //tensorflow/core/kernels:debug_ops_test PASSED in 3.6s //tensorflow/core/kernels:decode_wav_op_test PASSED in 5.5s //tensorflow/core/kernels:deep_conv2d_test PASSED in 0.3s //tensorflow/core/kernels:dequantize_op_test PASSED in 1.3s //tensorflow/core/kernels:diag_op_test_cpu PASSED in 0.9s //tensorflow/core/kernels:dynamic_partition_op_test_cpu PASSED in 0.6s //tensorflow/core/kernels:dynamic_stitch_op_test_cpu PASSED in 0.6s //tensorflow/core/kernels:eigen_activations_test PASSED in 0.1s //tensorflow/core/kernels:eigen_attention_test PASSED in 0.2s //tensorflow/core/kernels:eigen_backward_cuboid_convolutions_test PASSED in 0.4s //tensorflow/core/kernels:eigen_backward_spatial_convolutions_test PASSED in 0.6s //tensorflow/core/kernels:eigen_benchmark_cpu_test PASSED in 0.3s //tensorflow/core/kernels:eigen_mkldnn_contraction_kernel_test PASSED in 0.1s //tensorflow/core/kernels:eigen_pooling_test PASSED in 0.3s //tensorflow/core/kernels:encode_wav_op_test PASSED in 5.3s //tensorflow/core/kernels:fingerprint_op_test PASSED in 1.7s //tensorflow/core/kernels:fused_batch_norm_ex_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:fused_batch_norm_op_test_cpu PASSED in 0.9s //tensorflow/core/kernels:gather_nd_op_test_cpu PASSED in 1.1s //tensorflow/core/kernels:gather_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:guarantee_const_op_test PASSED in 1.3s //tensorflow/core/kernels:identity_n_op_test PASSED in 1.1s //tensorflow/core/kernels:identity_op_test PASSED in 1.1s //tensorflow/core/kernels:immutable_constant_op_test PASSED in 2.2s //tensorflow/core/kernels:in_topk_op_test PASSED in 0.5s //tensorflow/core/kernels:isotonic_regression_op_test PASSED in 0.5s //tensorflow/core/kernels:logging_ops_test PASSED in 2.7s //tensorflow/core/kernels:lookup_ops_test PASSED in 0.6s //tensorflow/core/kernels:loss_test PASSED in 0.1s //tensorflow/core/kernels:lrn_op_test_cpu PASSED in 0.9s //tensorflow/core/kernels:matmul_op_test_cpu PASSED in 8.1s //tensorflow/core/kernels:merge_v2_checkpoints_op_test PASSED in 1.1s //tensorflow/core/kernels:mfcc_dct_test PASSED in 0.1s //tensorflow/core/kernels:mfcc_mel_filterbank_test PASSED in 0.2s //tensorflow/core/kernels:mfcc_op_test_cpu PASSED in 3.9s //tensorflow/core/kernels:mfcc_test PASSED in 0.3s //tensorflow/core/kernels:multinomial_op_test_cpu PASSED in 0.5s //tensorflow/core/kernels:nn_ops_test_cpu PASSED in 0.7s //tensorflow/core/kernels:one_hot_op_test PASSED in 1.3s //tensorflow/core/kernels:ops_testutil_test PASSED in 0.6s //tensorflow/core/kernels:ops_util_test PASSED in 0.4s //tensorflow/core/kernels:parameterized_truncated_normal_op_test_cpu PASSED in 0.8s //tensorflow/core/kernels:parse_tensor_test PASSED in 0.8s //tensorflow/core/kernels:quantization_utils_test PASSED in 0.8s //tensorflow/core/kernels:quantize_and_dequantize_op_test_cpu PASSED in 0.7s //tensorflow/core/kernels:quantize_down_and_shrink_range_op_test PASSED in 0.7s //tensorflow/core/kernels:quantize_op_test PASSED in 0.9s //tensorflow/core/kernels:quantized_activation_ops_test PASSED in 0.6s //tensorflow/core/kernels:quantized_add_op_test PASSED in 1.5s //tensorflow/core/kernels:quantized_batch_norm_op_test PASSED in 0.9s //tensorflow/core/kernels:quantized_bias_add_op_test PASSED in 1.2s //tensorflow/core/kernels:quantized_concat_op_test PASSED in 1.6s //tensorflow/core/kernels:quantized_conv_ops_test PASSED in 0.9s //tensorflow/core/kernels:quantized_instance_norm_test PASSED in 1.7s //tensorflow/core/kernels:quantized_matmul_op_test PASSED in 0.7s //tensorflow/core/kernels:quantized_mul_op_test PASSED in 1.0s //tensorflow/core/kernels:quantized_pooling_ops_test PASSED in 0.5s //tensorflow/core/kernels:quantized_reshape_op_test PASSED in 0.6s //tensorflow/core/kernels:quantized_resize_bilinear_op_test PASSED in 3.2s //tensorflow/core/kernels:ragged_fill_empty_rows_op_test PASSED in 0.9s //tensorflow/core/kernels:ragged_gather_op_test PASSED in 0.5s //tensorflow/core/kernels:ragged_range_op_test PASSED in 0.7s //tensorflow/core/kernels:ragged_tensor_from_variant_op_test PASSED in 1.3s //tensorflow/core/kernels:ragged_tensor_to_sparse_kernel_test PASSED in 0.7s //tensorflow/core/kernels:ragged_tensor_to_tensor_op_test PASSED in 0.6s //tensorflow/core/kernels:ragged_tensor_to_variant_op_test PASSED in 1.1s //tensorflow/core/kernels:random_binomial_op_test_cpu PASSED in 1.3s //tensorflow/core/kernels:random_index_shuffle_test PASSED in 0.4s //tensorflow/core/kernels:random_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:random_poisson_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:range_sampler_test PASSED in 1.5s //tensorflow/core/kernels:reduction_ops_test_cpu PASSED in 0.5s //tensorflow/core/kernels:regex_replace_op_test PASSED in 1.2s //tensorflow/core/kernels:requantization_range_op_test PASSED in 0.8s //tensorflow/core/kernels:requantize_op_test PASSED in 0.6s //tensorflow/core/kernels:resource_ops_test PASSED in 0.7s //tensorflow/core/kernels:restore_op_test PASSED in 0.6s //tensorflow/core/kernels:restore_v2_op_test PASSED in 0.8s //tensorflow/core/kernels:reverse_op_test PASSED in 0.6s //tensorflow/core/kernels:roll_op_test PASSED in 0.5s //tensorflow/core/kernels:save_op_test PASSED in 0.9s //tensorflow/core/kernels:save_v2_op_test PASSED in 1.0s //tensorflow/core/kernels:scan_ops_test_cpu PASSED in 0.8s //tensorflow/core/kernels:scatter_nd_op_test_cpu PASSED in 0.9s //tensorflow/core/kernels:scatter_op_test PASSED in 0.7s //tensorflow/core/kernels:scoped_allocator_ops_test_cpu PASSED in 7.0s //tensorflow/core/kernels:sdca_ops_test PASSED in 2.3s //tensorflow/core/kernels:segment_reduction_ops_test PASSED in 0.7s //tensorflow/core/kernels:sendrecv_ops_test PASSED in 0.5s //tensorflow/core/kernels:sequence_ops_test PASSED in 0.6s //tensorflow/core/kernels:shape_ops_test PASSED in 0.8s //tensorflow/core/kernels:slice_op_test PASSED in 1.2s //tensorflow/core/kernels:spacetobatch_benchmark_test_cpu PASSED in 0.7s //tensorflow/core/kernels:sparse_add_op_test PASSED in 0.7s //tensorflow/core/kernels:sparse_dense_binary_op_shared_test PASSED in 0.8s //tensorflow/core/kernels:sparse_fill_empty_rows_op_test_cpu PASSED in 0.5s //tensorflow/core/kernels:sparse_matmul_op_test_cpu PASSED in 0.7s //tensorflow/core/kernels:sparse_reduce_sum_op_test PASSED in 1.5s //tensorflow/core/kernels:sparse_tensor_dense_matmul_op_test_cpu PASSED in 1.1s //tensorflow/core/kernels:sparse_to_dense_op_test_cpu PASSED in 0.7s //tensorflow/core/kernels:sparse_utils_test PASSED in 0.6s //tensorflow/core/kernels:sparse_xent_op_test_cpu PASSED in 0.6s //tensorflow/core/kernels:spectrogram_op_test_cpu PASSED in 4.2s //tensorflow/core/kernels:spectrogram_test PASSED in 0.2s //tensorflow/core/kernels:split_op_test_cpu PASSED in 0.9s //tensorflow/core/kernels:split_v_op_test_cpu PASSED in 4.7s //tensorflow/core/kernels:strided_slice_op_test PASSED in 1.0s //tensorflow/core/kernels:string_format_op_test PASSED in 1.6s //tensorflow/core/kernels:string_ngrams_op_test PASSED in 0.8s //tensorflow/core/kernels:string_split_op_test PASSED in 0.6s //tensorflow/core/kernels:substr_op_test PASSED in 1.1s //tensorflow/core/kernels:summary_audio_op_test PASSED in 1.2s //tensorflow/core/kernels:summary_image_op_test PASSED in 0.9s //tensorflow/core/kernels:summary_op_test PASSED in 1.4s //tensorflow/core/kernels:summary_tensor_op_test PASSED in 2.0s //tensorflow/core/kernels:tensor_cord_test PASSED in 0.6s //tensorflow/core/kernels:tensor_flag_utils_test PASSED in 0.8s //tensorflow/core/kernels:tensor_map_test PASSED in 0.3s //tensorflow/core/kernels:training_ops_test PASSED in 0.6s //tensorflow/core/kernels:transpose_util_test PASSED in 0.6s //tensorflow/core/kernels:unary_ops_composition_test_cpu PASSED in 2.6s //tensorflow/core/kernels:unique_op_test PASSED in 0.9s //tensorflow/core/kernels:variable_ops_test PASSED in 3.1s //tensorflow/core/kernels:while_op_test PASSED in 3.0s //tensorflow/core/kernels:xent_op_test_cpu PASSED in 1.5s //tensorflow/core/kernels/batching_util:basic_batch_scheduler_test PASSED in 0.2s //tensorflow/core/kernels/batching_util:batch_input_task_test PASSED in 1.1s //tensorflow/core/kernels/batching_util:batch_resource_base_test PASSED in 0.2s //tensorflow/core/kernels/batching_util:batch_scheduler_test PASSED in 0.5s //tensorflow/core/kernels/batching_util:bounded_executor_test PASSED in 20.8s //tensorflow/core/kernels/batching_util:input_split_metadata_test PASSED in 0.2s //tensorflow/core/kernels/batching_util:periodic_function_test PASSED in 3.1s //tensorflow/core/kernels/batching_util:serial_device_batch_scheduler_test PASSED in 7.1s //tensorflow/core/kernels/batching_util:shared_batch_scheduler_test PASSED in 5.1s //tensorflow/core/kernels/batching_util:threadsafe_status_test PASSED in 0.2s //tensorflow/core/kernels/data:batch_dataset_op_test PASSED in 1.2s //tensorflow/core/kernels/data:cache_dataset_ops_test PASSED in 3.0s //tensorflow/core/kernels/data:concatenate_dataset_op_test PASSED in 2.1s //tensorflow/core/kernels/data:filter_dataset_op_test PASSED in 1.6s //tensorflow/core/kernels/data:finalize_dataset_op_test PASSED in 2.3s //tensorflow/core/kernels/data:fixed_length_record_dataset_op_test PASSED in 2.1s //tensorflow/core/kernels/data:flat_map_dataset_op_test PASSED in 1.6s //tensorflow/core/kernels/data:get_options_op_test PASSED in 1.6s //tensorflow/core/kernels/data:interleave_dataset_op_test PASSED in 1.7s //tensorflow/core/kernels/data:iterator_ops_test PASSED in 1.1s //tensorflow/core/kernels/data:map_dataset_op_test PASSED in 2.7s //tensorflow/core/kernels/data:map_defun_op_test PASSED in 1.2s //tensorflow/core/kernels/data:optimize_dataset_op_test PASSED in 1.5s //tensorflow/core/kernels/data:options_dataset_op_test PASSED in 1.5s //tensorflow/core/kernels/data:padded_batch_dataset_op_test PASSED in 1.8s //tensorflow/core/kernels/data:parallel_batch_dataset_op_test PASSED in 4.0s //tensorflow/core/kernels/data:parallel_filter_dataset_op_test PASSED in 1.5s //tensorflow/core/kernels/data:parallel_interleave_dataset_op_test PASSED in 0.8s //tensorflow/core/kernels/data:parallel_map_dataset_op_test PASSED in 1.0s //tensorflow/core/kernels/data:prefetch_autotuner_test PASSED in 0.7s //tensorflow/core/kernels/data:prefetch_dataset_op_test PASSED in 1.3s //tensorflow/core/kernels/data:range_dataset_op_test PASSED in 2.9s //tensorflow/core/kernels/data:reduce_dataset_op_test PASSED in 2.1s //tensorflow/core/kernels/data:repeat_dataset_op_test PASSED in 1.0s //tensorflow/core/kernels/data:rewrite_dataset_op_test PASSED in 1.4s //tensorflow/core/kernels/data:shard_dataset_op_test PASSED in 0.9s //tensorflow/core/kernels/data:shuffle_dataset_op_test PASSED in 1.4s //tensorflow/core/kernels/data:skip_dataset_op_test PASSED in 2.1s //tensorflow/core/kernels/data:sparse_tensor_slice_dataset_op_test PASSED in 2.0s //tensorflow/core/kernels/data:take_dataset_op_test PASSED in 1.7s //tensorflow/core/kernels/data:tensor_dataset_op_test PASSED in 0.9s //tensorflow/core/kernels/data:tensor_slice_dataset_op_test PASSED in 1.5s //tensorflow/core/kernels/data:text_line_dataset_op_test PASSED in 2.2s //tensorflow/core/kernels/data:tf_record_dataset_op_test PASSED in 4.0s //tensorflow/core/kernels/data:window_dataset_op_test PASSED in 2.7s //tensorflow/core/kernels/data:zip_dataset_op_test PASSED in 1.1s //tensorflow/core/kernels/data/experimental:assert_next_dataset_op_test PASSED in 1.1s //tensorflow/core/kernels/data/experimental:assert_prev_dataset_op_test PASSED in 1.6s //tensorflow/core/kernels/data/experimental:auto_shard_dataset_op_test PASSED in 1.7s //tensorflow/core/kernels/data/experimental:directed_interleave_dataset_op_test PASSED in 1.0s //tensorflow/core/kernels/data/experimental:list_dataset_op_test PASSED in 0.9s //tensorflow/core/kernels/data/experimental:map_and_batch_dataset_op_test PASSED in 1.7s //tensorflow/core/kernels/data/experimental:parallel_interleave_dataset_op_test PASSED in 1.4s //tensorflow/core/kernels/data/experimental:random_dataset_op_test PASSED in 2.7s //tensorflow/core/kernels/data/experimental:sampling_dataset_op_test PASSED in 1.7s //tensorflow/core/kernels/data/experimental:save_dataset_op_test PASSED in 1.3s //tensorflow/core/kernels/data/experimental:unique_dataset_op_test PASSED in 1.9s //tensorflow/core/kernels/image:adjust_contrast_op_benchmark_test_cpu PASSED in 2.1s //tensorflow/core/kernels/image:adjust_contrast_op_test PASSED in 1.3s //tensorflow/core/kernels/image:colorspace_op_test PASSED in 0.9s //tensorflow/core/kernels/image:crop_and_resize_op_benchmark_test_cpu PASSED in 0.5s //tensorflow/core/kernels/image:crop_and_resize_op_test PASSED in 1.6s //tensorflow/core/kernels/image:encode_jpeg_op_test PASSED in 0.8s //tensorflow/core/kernels/image:mirror_pad_op_benchmark_test_cpu PASSED in 0.6s //tensorflow/core/kernels/image:mirror_pad_op_test PASSED in 0.9s //tensorflow/core/kernels/image:non_max_suppression_op_benchmark_test PASSED in 0.6s //tensorflow/core/kernels/image:non_max_suppression_op_test PASSED in 0.6s //tensorflow/core/kernels/image:resize_area_op_test PASSED in 1.3s //tensorflow/core/kernels/image:resize_benchmark_test_cpu PASSED in 0.8s //tensorflow/core/kernels/image:resize_bicubic_op_test PASSED in 3.6s //tensorflow/core/kernels/image:resize_ops_test_cpu PASSED in 2.7s //tensorflow/core/kernels/image:sampling_kernels_test PASSED in 1.3s //tensorflow/core/kernels/image:scale_and_translate_op_test PASSED in 1.8s //tensorflow/core/kernels/linalg:banded_triangular_solve_op_test_cpu PASSED in 1.7s //tensorflow/core/kernels/linalg:matrix_triangular_solve_op_test_cpu PASSED in 0.8s //tensorflow/core/kernels/mkl:mkl_conv_ops_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_dequantize_op_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_fused_batch_norm_op_test PASSED in 1.0s //tensorflow/core/kernels/mkl:mkl_fused_ops_test PASSED in 3.4s //tensorflow/core/kernels/mkl:mkl_matmul_op_benchmark PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_qmatmul_op_test PASSED in 0.4s //tensorflow/core/kernels/mkl:mkl_quantize_op_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_quantized_concat_op_test PASSED in 0.2s //tensorflow/core/kernels/mkl:mkl_quantized_conv_ops_perchannel_test PASSED in 0.4s //tensorflow/core/kernels/mkl:mkl_quantized_conv_ops_test PASSED in 1.0s //tensorflow/core/kernels/mkl:mkl_quantized_pooling_ops_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_relu_op_test PASSED in 0.4s //tensorflow/core/kernels/mkl:mkl_requantize_ops_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_swish_op_test PASSED in 0.2s //tensorflow/core/kernels/mkl:onednn_nn_ops_benchmark PASSED in 0.6s //tensorflow/core/kernels/sparse:kernels_test PASSED in 1.6s //tensorflow/core/kernels/uniform_quant_ops:math_utils_test PASSED in 0.4s //tensorflow/core/kernels/uniform_quant_ops:tensor_utils_test PASSED in 0.1s //tensorflow/core/kernels/uniform_quant_ops:uniform_dequantize_op_test PASSED in 0.8s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantize_op_test PASSED in 0.9s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantized_add_op_test PASSED in 1.1s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantized_clip_by_value_op_test PASSED in 1.0s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantized_convolution_ops_test PASSED in 1.2s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantized_dot_ops_test PASSED in 0.6s //tensorflow/core/kernels/uniform_quant_ops:uniform_requantize_op_test PASSED in 0.8s //tensorflow/core/lib/db:sqlite_test PASSED in 0.1s //tensorflow/core/lib/gif:lib_gif_io_test PASSED in 1.8s //tensorflow/core/lib/jpeg:lib_jpeg_jpeg_mem_unittest PASSED in 1.5s //tensorflow/core/ops:cudnn_rnn_ops_test_cc PASSED in 0.6s //tensorflow/core/ops:ops_array_grad_test PASSED in 2.4s //tensorflow/core/ops:ops_math_grad_test PASSED in 4.8s //tensorflow/core/ops:ops_tests PASSED in 1.2s //tensorflow/core/ops/compat:backwards_compatibility_test PASSED in 0.5s //tensorflow/core/platform:__tensorflow_tsl_platform_profile_utils_cpu_utils_test PASSED in 0.4s //tensorflow/core/platform:enable_tf2_utils_test PASSED in 0.3s //tensorflow/core/platform:env_test PASSED in 4.6s //tensorflow/core/platform:fake_python_env_test PASSED in 0.4s //tensorflow/core/platform:file_system_test PASSED in 1.2s //tensorflow/core/platform:platform_strings_test PASSED in 0.2s //tensorflow/core/platform:ram_file_system_test PASSED in 27.2s //tensorflow/core/platform:resource_loader_test PASSED in 0.1s //tensorflow/core/platform:vmodule_benchmark_test PASSED in 0.5s //tensorflow/core/platform:vmodule_test PASSED in 0.7s //tensorflow/core/profiler/backends/cpu:host_tracer_test PASSED in 0.9s //tensorflow/core/profiler/convert:hlo_proto_to_graph_view_test PASSED in 0.2s //tensorflow/core/profiler/convert:hlo_proto_to_memory_visualization_utils_test PASSED in 0.3s //tensorflow/core/profiler/convert:op_stats_to_pod_stats_test PASSED in 0.1s //tensorflow/core/profiler/convert:op_stats_to_pod_viewer_test PASSED in 0.3s //tensorflow/core/profiler/convert:op_stats_to_tf_stats_test PASSED in 0.5s //tensorflow/core/profiler/convert:xplane_to_kernel_stats_db_test PASSED in 0.1s //tensorflow/core/profiler/convert:xplane_to_memory_profile_test PASSED in 0.8s //tensorflow/core/profiler/convert:xplane_to_op_metrics_db_test PASSED in 0.5s //tensorflow/core/profiler/convert:xplane_to_op_stats_test PASSED in 0.5s //tensorflow/core/profiler/convert:xplane_to_step_events_test PASSED in 0.4s //tensorflow/core/profiler/convert:xplane_to_tf_functions_test PASSED in 0.6s //tensorflow/core/profiler/convert:xplane_to_tool_names_test PASSED in 0.7s //tensorflow/core/profiler/convert/trace_viewer:trace_viewer_visibility_test PASSED in 0.3s //tensorflow/core/profiler/internal:tfprof_show_test PASSED in 1.1s //tensorflow/core/profiler/internal:tfprof_stats_test PASSED in 1.6s //tensorflow/core/profiler/internal:tfprof_tensor_test PASSED in 0.8s //tensorflow/core/profiler/internal:tfprof_timeline_test PASSED in 1.5s //tensorflow/core/profiler/internal/advisor:tfprof_advisor_test PASSED in 1.3s //tensorflow/core/profiler/lib:profiler_disabled_test PASSED in 0.1s //tensorflow/core/profiler/utils:derived_timeline_test PASSED in 0.6s //tensorflow/core/profiler/utils:kernel_stats_utils_test PASSED in 1.1s //tensorflow/core/profiler/utils:op_metrics_db_utils_test PASSED in 0.1s //tensorflow/core/profiler/utils:step_intersection_test PASSED in 0.1s //tensorflow/core/summary:schema_test PASSED in 0.4s //tensorflow/core/summary:summary_db_writer_test PASSED in 0.5s //tensorflow/core/summary:summary_file_writer_test PASSED in 0.1s //tensorflow/core/tfrt/common:pjrt_cpu_client_registration_test PASSED in 9.0s //tensorflow/core/tfrt/common:pjrt_state_test PASSED in 8.1s //tensorflow/core/tfrt/common:pjrt_util_test PASSED in 8.2s //tensorflow/core/tfrt/fallback:cost_recorder_test PASSED in 0.2s //tensorflow/core/tfrt/fallback:fallback_state_test PASSED in 0.5s //tensorflow/core/transforms:eval_utils_test PASSED in 2.4s //tensorflow/core/transforms:graph_transform_wrapper_test PASSED in 0.3s //tensorflow/core/util:bcast_test PASSED in 0.8s //tensorflow/core/util:command_line_flags_test PASSED in 1.4s //tensorflow/core/util:debug_data_dumper_test PASSED in 1.3s //tensorflow/core/util:debug_events_writer_test PASSED in 1.0s //tensorflow/core/util:dump_graph_test PASSED in 0.7s //tensorflow/core/util:equal_graph_def_test PASSED in 1.2s //tensorflow/core/util:events_writer_test PASSED in 3.7s //tensorflow/core/util:example_proto_fast_parsing_test PASSED in 1.5s //tensorflow/core/util:example_proto_helper_test PASSED in 1.0s //tensorflow/core/util:exec_on_stall_test PASSED in 2.7s //tensorflow/core/util:fake_clock_env_test PASSED in 2.6s //tensorflow/core/util:incremental_barrier_test PASSED in 0.1s //tensorflow/core/util:matmul_bcast_test PASSED in 1.1s //tensorflow/core/util:memmapped_file_system_test PASSED in 2.3s //tensorflow/core/util:overflow_test PASSED in 0.2s //tensorflow/core/util:presized_cuckoo_map_test PASSED in 2.4s //tensorflow/core/util:ragged_to_dense_util_test PASSED in 0.8s //tensorflow/core/util:reffed_status_callback_test PASSED in 1.1s //tensorflow/core/util:reporter_test PASSED in 1.0s //tensorflow/core/util:saved_tensor_slice_util_test PASSED in 2.9s //tensorflow/core/util:semver_test PASSED in 1.2s //tensorflow/core/util:stat_summarizer_test PASSED in 1.1s //tensorflow/core/util:strided_slice_op_test PASSED in 1.0s //tensorflow/core/util:tensor_format_test PASSED in 1.7s //tensorflow/core/util:tensor_slice_reader_test PASSED in 2.1s //tensorflow/core/util:tensor_slice_set_test PASSED in 0.8s //tensorflow/core/util:tensor_slice_util_test PASSED in 1.4s //tensorflow/core/util:tensor_slice_writer_test PASSED in 2.5s //tensorflow/core/util:work_sharder_test PASSED in 1.3s //tensorflow/core/util/ctc:ctc_beam_search_test PASSED in 0.4s //tensorflow/core/util/proto:descriptor_pool_registry_test PASSED in 1.5s //tensorflow/core/util/proto:proto_utils_test PASSED in 1.0s //tensorflow/core/util/quantization:uniform_quant_ops_params_test PASSED in 1.2s //tensorflow/core/util/sparse:sparse_tensor_test PASSED in 0.2s //tensorflow/core/util/tensor_bundle:tensor_bundle_test PASSED in 32.3s //tensorflow/dtensor/mlir:dtensor_location_test PASSED in 0.4s //tensorflow/dtensor/mlir:group_assignment_test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:annotate_global_shape.mlir.test PASSED in 1.5s //tensorflow/dtensor/mlir/tests:cluster_function_conversion.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:constant_folding.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:designate_resource_handle_mesh.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:device_mesh_cluster_coarsening.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:dtensor_all_gather.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:dtensor_all_scatter.mlir.test PASSED in 1.1s //tensorflow/dtensor/mlir/tests:dtensor_allreduce_combine_optimization.mlir.test PASSED in 1.0s //tensorflow/dtensor/mlir/tests:dtensor_allreduce_lowering.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:dtensor_allreduce_scatter_optimization.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:dtensor_allreduce_sum_optimization.mlir.test PASSED in 1.2s //tensorflow/dtensor/mlir/tests:dtensor_alltoall_lowering.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:dtensor_layout_must_execute.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:dtensor_layout_to_xla_sharding_op.mlir.test PASSED in 1.1s //tensorflow/dtensor/mlir/tests:dtensor_mixed_precision_reduce.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:dtensor_reduce_scatter_lowering.mlir.test PASSED in 0.9s //tensorflow/dtensor/mlir/tests:dtensor_remove_dtensorlayout.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:dtensor_replace_auxiliary_layout_op.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:dtensor_replace_relayout_with_identity.mlir.test PASSED in 0.9s //tensorflow/dtensor/mlir/tests:dtensor_set_hlo_sharding.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:dtensor_set_hlo_sharding_default.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:dtensor_xla_spmd_integration.mlir.test PASSED in 1.1s //tensorflow/dtensor/mlir/tests:elide_identity_before_copy_to_mesh.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:function_renaming.mlir.test PASSED in 1.4s //tensorflow/dtensor/mlir/tests:handle_cross_cluster_dependencies.mlir.test PASSED in 1.2s //tensorflow/dtensor/mlir/tests:handle_sparsetensors.mlir.test PASSED in 1.8s //tensorflow/dtensor/mlir/tests:layout_propagation_v2.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:lower_send_recv.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:merge_clusters.mlir.test PASSED in 1.4s //tensorflow/dtensor/mlir/tests:mesh_propagation.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:multi_device_expansion.mlir.test PASSED in 1.4s //tensorflow/dtensor/mlir/tests:op_to_device_cluster.mlir.test PASSED in 0.9s //tensorflow/dtensor/mlir/tests:propagate_default_layout.mlir.test PASSED in 1.1s //tensorflow/dtensor/mlir/tests:propagate_device_id_to_function.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:restore_and_assign.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:restore_shape_inference.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:set_default_sharding.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:sparse_expansion.mlir.test PASSED in 1.1s //tensorflow/dtensor/mlir/tests:spmd_batchparallel.mlir.test PASSED in 0.9s //tensorflow/dtensor/mlir/tests:spmd_concat.mlir.test PASSED in 1.5s //tensorflow/dtensor/mlir/tests:spmd_conv.mlir.test PASSED in 1.0s //tensorflow/dtensor/mlir/tests:spmd_einsum.mlir.test PASSED in 1.1s //tensorflow/dtensor/mlir/tests:spmd_expansion.mlir.test PASSED in 1.7s //tensorflow/dtensor/mlir/tests:spmd_io_ops.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:spmd_iterator.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:spmd_matmul.mlir.test PASSED in 0.9s //tensorflow/dtensor/mlir/tests:spmd_random.mlir.test PASSED in 1.0s //tensorflow/dtensor/mlir/tests:spmd_save_restore.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:spmd_segment_sum.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:spmd_slice.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:spmd_softmax_loss.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:spmd_squeeze.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:spmd_var_handle.mlir.test PASSED in 1.2s //tensorflow/dtensor/mlir/tests:tf_dtensor_ops.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:tpu_add_resource_device_attribute.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:tpu_integration.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:undo_merge_const_across_mesh.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:update_tpu_metadata.mlir.test PASSED in 0.6s //tensorflow/dtensor/python/tests:collective_combine_all_reduce_test_cpu PASSED in 16.5s //tensorflow/dtensor/python/tests:collective_test_cpu PASSED in 22.5s //tensorflow/dtensor/python/tests:config_test_cpu PASSED in 8.2s //tensorflow/dtensor/python/tests:device_test_cpu PASSED in 41.5s //tensorflow/dtensor/python/tests:layout_test_cpu PASSED in 12.7s //tensorflow/dtensor/python/tests:multi_client_test_cpu PASSED in 15.8s //tensorflow/dtensor/python/tests:numpy_util_test_cpu PASSED in 9.0s //tensorflow/dtensor/tests:executable_manager_test PASSED in 38.4s //tensorflow/dtensor/tests:layout_to_xla_sharding_test PASSED in 0.3s //tensorflow/dtensor/tests:spmd_expander_test PASSED in 5.4s //tensorflow/dtensor/tests:tensor_layout_test PASSED in 0.2s //tensorflow/examples/adding_an_op:fact_test PASSED in 15.2s //tensorflow/examples/adding_an_op:zero_out_1_test PASSED in 16.0s //tensorflow/examples/adding_an_op:zero_out_2_test PASSED in 13.9s //tensorflow/examples/adding_an_op:zero_out_3_test PASSED in 14.1s //tensorflow/examples/custom_ops_doc/multiplex_1:multiplex_1_test PASSED in 15.1s //tensorflow/examples/custom_ops_doc/multiplex_2:multiplex_2_test_cpu PASSED in 14.5s //tensorflow/examples/custom_ops_doc/multiplex_3:multiplex_3_test PASSED in 15.0s //tensorflow/examples/custom_ops_doc/multiplex_4:multiplex_4_test PASSED in 14.5s //tensorflow/examples/custom_ops_doc/simple_hash_table:simple_hash_table_test PASSED in 15.5s //tensorflow/examples/custom_ops_doc/sleep:sleep_test PASSED in 16.4s //tensorflow/examples/speech_commands:accuracy_utils_test PASSED in 3.3s //tensorflow/examples/speech_commands:models_test PASSED in 16.0s //tensorflow/examples/speech_commands:recognize_commands_test PASSED in 2.9s //tensorflow/examples/wav_to_spectrogram:wav_to_spectrogram_test PASSED in 3.2s //tensorflow/js:ts_op_gen_test PASSED in 0.2s //tensorflow/python:array_grad_test_cpu PASSED in 10.5s //tensorflow/python:autograph_ops_test PASSED in 8.4s //tensorflow/python:batch_norm_benchmark_cpu PASSED in 6.8s //tensorflow/python:bincount_ops_test_cpu PASSED in 13.4s //tensorflow/python:bitwise_ops_test_cpu PASSED in 12.7s //tensorflow/python:clip_ops_test PASSED in 8.9s //tensorflow/python:clustering_ops_test PASSED in 21.9s //tensorflow/python:collective_ops_benchmark_cpu PASSED in 9.5s //tensorflow/python:collective_ops_gpu_test_2gpu PASSED in 11.4s //tensorflow/python:collective_ops_gpu_test_cpu PASSED in 8.0s //tensorflow/python:collective_ops_test PASSED in 16.1s //tensorflow/python:collective_ops_xla_test PASSED in 7.7s //tensorflow/python:compiled_collective_ops_gpu_test_2gpu PASSED in 7.5s //tensorflow/python:compiled_collective_ops_gpu_test_cpu PASSED in 10.3s //tensorflow/python:concat_benchmark_cpu PASSED in 6.8s //tensorflow/python:control_flow_ops_benchmark_cpu PASSED in 7.1s //tensorflow/python:control_flow_v2_enable_test PASSED in 7.7s //tensorflow/python:control_flow_v2_toggles_test PASSED in 10.2s //tensorflow/python:dequantize_op_test PASSED in 7.5s //tensorflow/python:embedding_ops_test_cpu PASSED in 9.6s //tensorflow/python:factory_ops_test_cpu PASSED in 7.2s //tensorflow/python:functional_ops_test PASSED in 7.0s //tensorflow/python:gradient_checker_v2_test_cpu PASSED in 29.2s //tensorflow/python:gradients_test_cpu PASSED in 14.7s //tensorflow/python:init_ops_test_cpu PASSED in 16.6s //tensorflow/python:init_ops_v2_test_cpu PASSED in 13.6s //tensorflow/python:math_grad_test_cpu PASSED in 17.5s //tensorflow/python:math_ops_linspace_test_cpu PASSED in 7.8s //tensorflow/python:math_ops_test_cpu PASSED in 29.4s //tensorflow/python:matmul_benchmark_cpu PASSED in 10.0s //tensorflow/python:nn_grad_test_cpu PASSED in 12.3s //tensorflow/python:nn_loss_scaling_utilities_test PASSED in 14.7s //tensorflow/python:nn_test_cpu PASSED in 57.5s //tensorflow/python:nn_xent_test_cpu PASSED in 9.2s //tensorflow/python:op_selector_test PASSED in 7.9s //tensorflow/python:ops/array_ops_test PASSED in 7.4s //tensorflow/python:quantized_conv_ops_test PASSED in 9.5s //tensorflow/python:quantized_ops_test PASSED in 7.7s //tensorflow/python:raw_ops_test_cpu PASSED in 8.4s //tensorflow/python:rnn_grad_test_cpu PASSED in 9.7s //tensorflow/python:script_ops_test PASSED in 7.4s //tensorflow/python:sort_ops_test PASSED in 9.9s //tensorflow/python:sparse_ops_test PASSED in 20.2s //tensorflow/python:split_benchmark_cpu PASSED in 7.3s //tensorflow/python:tensor_array_ops_test PASSED in 8.3s //tensorflow/python:transpose_benchmark_cpu PASSED in 7.3s //tensorflow/python:variable_spec_test PASSED in 7.8s //tensorflow/python/autograph/converters:asserts_test PASSED in 9.8s //tensorflow/python/autograph/converters:break_statements_test PASSED in 9.4s //tensorflow/python/autograph/converters:call_trees_test PASSED in 7.7s //tensorflow/python/autograph/converters:conditional_expressions_test PASSED in 7.2s //tensorflow/python/autograph/converters:continue_statements_test PASSED in 9.0s //tensorflow/python/autograph/converters:control_flow_test PASSED in 14.2s //tensorflow/python/autograph/converters:directives_test PASSED in 6.9s //tensorflow/python/autograph/converters:functions_test PASSED in 7.2s //tensorflow/python/autograph/converters:list_comprehensions_test PASSED in 8.2s //tensorflow/python/autograph/converters:lists_test PASSED in 6.6s //tensorflow/python/autograph/converters:logical_expressions_test PASSED in 6.8s //tensorflow/python/autograph/converters:return_statements_test PASSED in 10.3s //tensorflow/python/autograph/converters:slices_test PASSED in 7.3s //tensorflow/python/autograph/converters:variables_test PASSED in 8.0s //tensorflow/python/autograph/core:converter_test PASSED in 7.6s //tensorflow/python/autograph/core:function_wrappers_test PASSED in 8.7s //tensorflow/python/autograph/impl:api_test PASSED in 16.0s //tensorflow/python/autograph/impl:conversion_test PASSED in 7.0s //tensorflow/python/autograph/lang:special_functions_test PASSED in 9.7s //tensorflow/python/autograph/operators:conditional_expressions_test PASSED in 6.5s //tensorflow/python/autograph/operators:control_flow_test PASSED in 20.4s //tensorflow/python/autograph/operators:data_structures_test PASSED in 9.8s //tensorflow/python/autograph/operators:exceptions_test PASSED in 8.3s //tensorflow/python/autograph/operators:logical_test PASSED in 9.6s //tensorflow/python/autograph/operators:py_builtins_test PASSED in 20.0s //tensorflow/python/autograph/operators:slices_test PASSED in 6.8s //tensorflow/python/autograph/operators:variables_test PASSED in 7.2s //tensorflow/python/autograph/pyct:anno_test PASSED in 9.8s //tensorflow/python/autograph/pyct:ast_util_test PASSED in 10.0s //tensorflow/python/autograph/pyct:cache_test PASSED in 8.5s //tensorflow/python/autograph/pyct:cfg_test PASSED in 6.8s //tensorflow/python/autograph/pyct:error_utils_test PASSED in 6.1s //tensorflow/python/autograph/pyct:inspect_utils_test PASSED in 9.7s //tensorflow/python/autograph/pyct:loader_test PASSED in 7.3s //tensorflow/python/autograph/pyct:naming_test PASSED in 7.1s //tensorflow/python/autograph/pyct:origin_info_test PASSED in 6.7s //tensorflow/python/autograph/pyct:parser_test PASSED in 7.0s //tensorflow/python/autograph/pyct:pretty_printer_test PASSED in 6.4s //tensorflow/python/autograph/pyct:qual_names_test PASSED in 6.4s //tensorflow/python/autograph/pyct:templates_test PASSED in 8.2s //tensorflow/python/autograph/pyct:transformer_test PASSED in 7.0s //tensorflow/python/autograph/pyct:transpiler_test PASSED in 7.3s //tensorflow/python/autograph/pyct/static_analysis:activity_test PASSED in 8.2s //tensorflow/python/autograph/pyct/static_analysis:liveness_test PASSED in 7.3s //tensorflow/python/autograph/pyct/static_analysis:reaching_definitions_test PASSED in 7.3s //tensorflow/python/autograph/pyct/static_analysis:reaching_fndefs_test PASSED in 7.4s //tensorflow/python/autograph/pyct/static_analysis:type_inference_test PASSED in 7.4s //tensorflow/python/autograph/tests:assertion_test PASSED in 16.3s //tensorflow/python/autograph/tests:basic_ifexp_test PASSED in 17.2s //tensorflow/python/autograph/tests:call_to_builtin_function_test PASSED in 17.1s //tensorflow/python/autograph/tests:call_to_lambda_function_test PASSED in 15.6s //tensorflow/python/autograph/tests:call_to_named_tuple_test PASSED in 14.5s //tensorflow/python/autograph/tests:call_to_numpy_function_test PASSED in 20.2s //tensorflow/python/autograph/tests:call_to_print_function_test PASSED in 17.7s //tensorflow/python/autograph/tests:call_to_tf_api_test PASSED in 14.4s //tensorflow/python/autograph/tests:call_to_user_function_test PASSED in 19.6s //tensorflow/python/autograph/tests:composite_names_in_control_flow_test PASSED in 27.0s //tensorflow/python/autograph/tests:cond_basic_test PASSED in 25.8s //tensorflow/python/autograph/tests:datasets_test PASSED in 19.8s //tensorflow/python/autograph/tests:early_return_test PASSED in 21.2s //tensorflow/python/autograph/tests:ext_slice_test PASSED in 14.4s //tensorflow/python/autograph/tests:generator_test PASSED in 17.1s //tensorflow/python/autograph/tests:logical_expression_test PASSED in 16.8s //tensorflow/python/autograph/tests:loop_basic_test PASSED in 70.1s //tensorflow/python/autograph/tests:loop_control_flow_illegal_cases_test PASSED in 15.8s //tensorflow/python/autograph/tests:loop_created_variables_test PASSED in 24.4s //tensorflow/python/autograph/tests:loop_scoping_test PASSED in 20.3s //tensorflow/python/autograph/tests:loop_with_function_call_test PASSED in 24.8s //tensorflow/python/autograph/tests:loop_with_variable_type_illegal_cases_test PASSED in 21.8s //tensorflow/python/autograph/tests:loop_with_variable_type_test PASSED in 34.8s //tensorflow/python/autograph/tests:nested_control_flow_test PASSED in 59.7s //tensorflow/python/autograph/tests:type_annotations_test PASSED in 14.6s //tensorflow/python/autograph/utils:context_managers_test PASSED in 6.9s //tensorflow/python/autograph/utils:misc_test PASSED in 9.4s //tensorflow/python/autograph/utils:tensor_list_test PASSED in 6.8s //tensorflow/python/autograph/utils:tensors_test PASSED in 7.2s //tensorflow/python/checkpoint:benchmarks_test PASSED in 8.0s //tensorflow/python/checkpoint:checkpoint_management_test_cpu PASSED in 19.8s //tensorflow/python/checkpoint:checkpoint_metrics_test PASSED in 15.4s //tensorflow/python/checkpoint:checkpoint_test PASSED in 29.6s //tensorflow/python/checkpoint:checkpoint_view_test PASSED in 8.9s //tensorflow/python/checkpoint:checkpoint_with_v1_optimizers_test PASSED in 10.8s //tensorflow/python/checkpoint:functional_saver_test_cpu PASSED in 11.0s //tensorflow/python/checkpoint:restore_test PASSED in 11.6s //tensorflow/python/checkpoint:save_util_v1_test PASSED in 7.8s //tensorflow/python/checkpoint:saveable_compat_test PASSED in 10.0s //tensorflow/python/checkpoint:tensor_callable_test PASSED in 8.6s //tensorflow/python/checkpoint:trackable_view_test PASSED in 8.6s //tensorflow/python/client:device_lib_test_cpu PASSED in 9.0s //tensorflow/python/client:events_writer_test PASSED in 8.2s //tensorflow/python/client:session_benchmark_cpu PASSED in 7.8s //tensorflow/python/client:session_list_devices_test PASSED in 7.3s //tensorflow/python/client:session_partial_run_test PASSED in 18.8s //tensorflow/python/client:timeline_test_cpu PASSED in 7.1s //tensorflow/python/client:virtual_gpu_test_cpu PASSED in 7.7s //tensorflow/python/compat:compat_test PASSED in 7.6s //tensorflow/python/compat:disable_v2_behavior_test PASSED in 7.6s //tensorflow/python/compiler/mlir:mlir_test PASSED in 9.7s //tensorflow/python/compiler/tensorrt:trt_convert_test_cpu PASSED in 8.4s //tensorflow/python/compiler/tensorrt/test:batch_matmul_test_cpu PASSED in 9.2s //tensorflow/python/compiler/tensorrt/test:biasadd_matmul_test_cpu PASSED in 8.1s //tensorflow/python/compiler/tensorrt/test:binary_tensor_weight_broadcast_test_cpu PASSED in 11.3s //tensorflow/python/compiler/tensorrt/test:bool_test_cpu PASSED in 8.0s //tensorflow/python/compiler/tensorrt/test:cast_test_cpu PASSED in 14.3s //tensorflow/python/compiler/tensorrt/test:concatenation_test_cpu PASSED in 13.9s //tensorflow/python/compiler/tensorrt/test:const_broadcast_test_cpu PASSED in 8.0s //tensorflow/python/compiler/tensorrt/test:data_dependent_shape_test_cpu PASSED in 14.1s //tensorflow/python/compiler/tensorrt/test:dynamic_input_shapes_test_cpu PASSED in 8.0s //tensorflow/python/compiler/tensorrt/test:identity_output_test_cpu PASSED in 7.7s //tensorflow/python/compiler/tensorrt/test:int32_test_cpu PASSED in 8.3s //tensorflow/python/compiler/tensorrt/test:lru_cache_test_cpu PASSED in 8.9s //tensorflow/python/compiler/tensorrt/test:memory_alignment_test_cpu PASSED in 7.5s //tensorflow/python/compiler/tensorrt/test:multi_connection_neighbor_engine_test_cpu PASSED in 7.2s //tensorflow/python/compiler/tensorrt/test:neighboring_engine_test_cpu PASSED in 9.4s //tensorflow/python/compiler/tensorrt/test:quantization_test_cpu PASSED in 8.6s //tensorflow/python/compiler/tensorrt/test:rank_two_test_cpu PASSED in 8.1s //tensorflow/python/compiler/tensorrt/test:reshape_transpose_test_cpu PASSED in 11.6s //tensorflow/python/compiler/tensorrt/test:topk_test_cpu PASSED in 7.3s //tensorflow/python/compiler/tensorrt/test:trt_engine_op_shape_test_cpu PASSED in 9.3s //tensorflow/python/compiler/tensorrt/test:trt_mode_test_cpu PASSED in 8.2s //tensorflow/python/compiler/tensorrt/test:unary_test_cpu PASSED in 9.7s //tensorflow/python/compiler/tensorrt/test:vgg_block_nchw_test_cpu PASSED in 9.5s //tensorflow/python/compiler/tensorrt/test:vgg_block_test_cpu PASSED in 11.1s //tensorflow/python/compiler/xla:jit_compile_test_cpu PASSED in 12.8s //tensorflow/python/compiler/xla:jit_test_cpu PASSED in 17.9s //tensorflow/python/compiler/xla:xla_test_cpu PASSED in 16.3s //tensorflow/python/compiler/xla/experimental:xla_sharding_test PASSED in 8.1s //tensorflow/python/data/benchmarks:batch_benchmark PASSED in 12.8s //tensorflow/python/data/benchmarks:filter_benchmark PASSED in 7.4s //tensorflow/python/data/benchmarks:from_tensor_slices_benchmark PASSED in 7.7s //tensorflow/python/data/benchmarks:interleave_benchmark PASSED in 9.5s //tensorflow/python/data/benchmarks:list_files_benchmark PASSED in 8.5s //tensorflow/python/data/benchmarks:map_benchmark PASSED in 9.3s //tensorflow/python/data/benchmarks:meta_benchmark PASSED in 8.6s //tensorflow/python/data/benchmarks:prefetch_benchmark PASSED in 14.3s //tensorflow/python/data/benchmarks:range_benchmark PASSED in 7.0s //tensorflow/python/data/experimental/benchmarks:autotune_benchmark PASSED in 8.5s //tensorflow/python/data/experimental/benchmarks:csv_dataset_benchmark PASSED in 7.2s //tensorflow/python/data/experimental/benchmarks:map_and_batch_benchmark PASSED in 7.3s //tensorflow/python/data/experimental/benchmarks:map_defun_benchmark PASSED in 7.0s //tensorflow/python/data/experimental/benchmarks:matching_files_benchmark PASSED in 7.3s //tensorflow/python/data/experimental/benchmarks:optimize_benchmark PASSED in 10.1s //tensorflow/python/data/experimental/benchmarks:parameter_value_benchmark PASSED in 11.1s //tensorflow/python/data/experimental/benchmarks:rejection_resample_benchmark PASSED in 8.3s //tensorflow/python/data/experimental/benchmarks:snapshot_dataset_benchmark PASSED in 6.9s //tensorflow/python/data/experimental/benchmarks:unbatch_benchmark PASSED in 6.6s //tensorflow/python/data/experimental/kernel_tests:assert_cardinality_test PASSED in 38.5s //tensorflow/python/data/experimental/kernel_tests:assert_next_test PASSED in 9.1s //tensorflow/python/data/experimental/kernel_tests:assert_prev_test PASSED in 12.5s //tensorflow/python/data/experimental/kernel_tests:checkpoint_input_pipeline_hook_test PASSED in 15.8s //tensorflow/python/data/experimental/kernel_tests:compression_ops_test PASSED in 17.2s //tensorflow/python/data/experimental/kernel_tests:copy_to_device_test_cpu PASSED in 22.7s //tensorflow/python/data/experimental/kernel_tests:dense_to_sparse_batch_test PASSED in 30.4s //tensorflow/python/data/experimental/kernel_tests:from_list_test PASSED in 38.8s //tensorflow/python/data/experimental/kernel_tests:io_test PASSED in 38.9s //tensorflow/python/data/experimental/kernel_tests:lookup_ops_test PASSED in 8.4s //tensorflow/python/data/experimental/kernel_tests:make_csv_dataset_test PASSED in 32.6s //tensorflow/python/data/experimental/kernel_tests:make_saveable_from_iterator_test PASSED in 7.3s //tensorflow/python/data/experimental/kernel_tests:make_tf_record_dataset_test PASSED in 48.1s //tensorflow/python/data/experimental/kernel_tests:map_defun_op_test PASSED in 7.7s //tensorflow/python/data/experimental/kernel_tests:matching_files_dataset_test PASSED in 36.9s //tensorflow/python/data/experimental/kernel_tests:model_dataset_test PASSED in 10.7s //tensorflow/python/data/experimental/kernel_tests:non_serializable_test PASSED in 10.4s //tensorflow/python/data/experimental/kernel_tests:prefetch_to_device_test_cpu PASSED in 15.4s //tensorflow/python/data/experimental/kernel_tests:prefetch_with_slack_test PASSED in 13.4s //tensorflow/python/data/experimental/kernel_tests:shuffle_and_repeat_test PASSED in 19.5s //tensorflow/python/data/experimental/kernel_tests:sleep_test PASSED in 8.0s //tensorflow/python/data/experimental/kernel_tests:tf_record_writer_test PASSED in 10.9s //tensorflow/python/data/experimental/kernel_tests:variant_test PASSED in 12.3s //tensorflow/python/data/experimental/kernel_tests:wrap_unwrap_test_cpu PASSED in 6.7s //tensorflow/python/data/experimental/kernel_tests/optimization:filter_fusion_test PASSED in 31.0s //tensorflow/python/data/experimental/kernel_tests/optimization:filter_parallelization_test PASSED in 81.0s //tensorflow/python/data/experimental/kernel_tests/optimization:grappler_test_cpu PASSED in 9.5s //tensorflow/python/data/experimental/kernel_tests/optimization:make_deterministic_test PASSED in 23.9s //tensorflow/python/data/experimental/kernel_tests/optimization:map_and_batch_fusion_test PASSED in 9.8s //tensorflow/python/data/experimental/kernel_tests/optimization:map_and_filter_fusion_test PASSED in 26.5s //tensorflow/python/data/experimental/kernel_tests/optimization:map_fusion_test PASSED in 30.8s //tensorflow/python/data/experimental/kernel_tests/optimization:map_parallelization_test PASSED in 15.9s //tensorflow/python/data/experimental/kernel_tests/optimization:noop_elimination_test PASSED in 10.5s //tensorflow/python/data/experimental/kernel_tests/service:multi_device_test PASSED in 22.9s //tensorflow/python/data/experimental/service:server_lib_test PASSED in 9.3s //tensorflow/python/data/kernel_tests:as_numpy_iterator_test PASSED in 9.0s //tensorflow/python/data/kernel_tests:bucket_by_sequence_length_test PASSED in 28.0s //tensorflow/python/data/kernel_tests:cache_test PASSED in 23.5s //tensorflow/python/data/kernel_tests:cardinality_test PASSED in 18.1s //tensorflow/python/data/kernel_tests:checkpoint_test PASSED in 21.3s //tensorflow/python/data/kernel_tests:concatenate_test PASSED in 24.3s //tensorflow/python/data/kernel_tests:counter_test PASSED in 39.7s //tensorflow/python/data/kernel_tests:dataset_spec_test PASSED in 8.0s //tensorflow/python/data/kernel_tests:dataset_test PASSED in 34.1s //tensorflow/python/data/kernel_tests:enumerate_test PASSED in 24.0s //tensorflow/python/data/kernel_tests:from_sparse_tensor_slices_test PASSED in 9.9s //tensorflow/python/data/kernel_tests:from_tensor_slices_test PASSED in 31.4s //tensorflow/python/data/kernel_tests:from_tensors_test PASSED in 24.1s //tensorflow/python/data/kernel_tests:get_single_element_test PASSED in 11.5s //tensorflow/python/data/kernel_tests:ignore_errors_test PASSED in 22.9s //tensorflow/python/data/kernel_tests:io_test PASSED in 42.0s //tensorflow/python/data/kernel_tests:iterator_test_cpu PASSED in 19.7s //tensorflow/python/data/kernel_tests:len_test PASSED in 7.7s //tensorflow/python/data/kernel_tests:list_files_test PASSED in 10.5s //tensorflow/python/data/kernel_tests:optional_test_cpu PASSED in 10.1s //tensorflow/python/data/kernel_tests:options_test PASSED in 14.2s //tensorflow/python/data/kernel_tests:placement_test_cpu PASSED in 9.0s //tensorflow/python/data/kernel_tests:prefetch_test PASSED in 61.2s //tensorflow/python/data/kernel_tests:random_test PASSED in 22.9s //tensorflow/python/data/kernel_tests:range_test PASSED in 58.2s //tensorflow/python/data/kernel_tests:rebatch_test PASSED in 9.3s //tensorflow/python/data/kernel_tests:reduce_test_cpu PASSED in 26.8s //tensorflow/python/data/kernel_tests:scan_test_cpu PASSED in 61.2s //tensorflow/python/data/kernel_tests:sparse_batch_test PASSED in 16.3s //tensorflow/python/data/kernel_tests:unbatch_test PASSED in 53.8s //tensorflow/python/data/util:convert_test PASSED in 9.6s //tensorflow/python/data/util:nest_test PASSED in 7.3s //tensorflow/python/data/util:options_test PASSED in 6.9s //tensorflow/python/data/util:random_seed_test PASSED in 12.1s //tensorflow/python/data/util:sparse_test PASSED in 7.1s //tensorflow/python/data/util:structure_test PASSED in 9.0s //tensorflow/python/data/util:traverse_test PASSED in 7.8s //tensorflow/python/debug/cli:analyzer_cli_test_cpu PASSED in 9.8s //tensorflow/python/debug/cli:cli_config_test PASSED in 7.0s //tensorflow/python/debug/cli:cli_shared_test PASSED in 8.1s //tensorflow/python/debug/cli:command_parser_test PASSED in 7.3s //tensorflow/python/debug/cli:curses_ui_test PASSED in 7.8s //tensorflow/python/debug/cli:debugger_cli_common_test PASSED in 9.5s //tensorflow/python/debug/cli:evaluator_test PASSED in 6.5s //tensorflow/python/debug/cli:profile_analyzer_cli_test PASSED in 7.6s //tensorflow/python/debug/cli:readline_ui_test PASSED in 8.9s //tensorflow/python/debug/cli:tensor_format_test PASSED in 11.3s //tensorflow/python/debug/lib:check_numerics_callback_test_cpu PASSED in 12.4s //tensorflow/python/debug/lib:common_test PASSED in 6.8s //tensorflow/python/debug/lib:debug_data_test PASSED in 7.0s //tensorflow/python/debug/lib:debug_events_monitors_test PASSED in 8.9s //tensorflow/python/debug/lib:debug_events_writer_test PASSED in 8.0s //tensorflow/python/debug/lib:debug_gradients_test_cpu PASSED in 7.8s //tensorflow/python/debug/lib:debug_graph_reconstruction_test_cpu PASSED in 10.1s //tensorflow/python/debug/lib:debug_graphs_test PASSED in 6.1s //tensorflow/python/debug/lib:debug_grappler_test_cpu PASSED in 8.3s //tensorflow/python/debug/lib:debug_utils_test PASSED in 6.1s //tensorflow/python/debug/lib:debug_v2_ops_test_cpu PASSED in 21.2s //tensorflow/python/debug/lib:profiling_test PASSED in 6.9s //tensorflow/python/debug/lib:session_debug_file_test_cpu PASSED in 13.2s //tensorflow/python/debug/lib:session_debug_multi_gpu_test_cpu PASSED in 7.5s //tensorflow/python/debug/lib:source_utils_test PASSED in 9.1s //tensorflow/python/debug/wrappers:disk_usage_test PASSED in 9.1s //tensorflow/python/debug/wrappers:dumping_wrapper_test PASSED in 7.3s //tensorflow/python/debug/wrappers:framework_test PASSED in 7.1s //tensorflow/python/debug/wrappers:local_cli_wrapper_test PASSED in 7.8s //tensorflow/python/distribute:checkpoint_utils_test_2gpu PASSED in 9.4s //tensorflow/python/distribute:checkpoint_utils_test_cpu PASSED in 17.5s //tensorflow/python/distribute:checkpointing_test_2gpu PASSED in 8.5s //tensorflow/python/distribute:checkpointing_test_cpu PASSED in 9.9s //tensorflow/python/distribute:collective_all_reduce_strategy_test_2gpu PASSED in 66.8s //tensorflow/python/distribute:collective_all_reduce_strategy_test_cpu PASSED in 67.0s //tensorflow/python/distribute:collective_all_reduce_strategy_test_xla_2gpu PASSED in 36.2s //tensorflow/python/distribute:collective_util_test PASSED in 7.1s //tensorflow/python/distribute:combinations_test_2gpu PASSED in 24.0s //tensorflow/python/distribute:combinations_test_cpu PASSED in 19.0s //tensorflow/python/distribute:cross_device_utils_test_cpu PASSED in 8.8s //tensorflow/python/distribute:custom_training_loop_gradient_test_2gpu PASSED in 10.5s //tensorflow/python/distribute:custom_training_loop_gradient_test_cpu PASSED in 10.3s //tensorflow/python/distribute:device_util_test_cpu PASSED in 8.8s //tensorflow/python/distribute:distribute_coordinator_test PASSED in 15.9s //tensorflow/python/distribute:distribute_lib_test PASSED in 11.2s //tensorflow/python/distribute:distribute_utils_test_2gpu PASSED in 8.4s //tensorflow/python/distribute:distribute_utils_test_cpu PASSED in 8.6s //tensorflow/python/distribute:input_ops_test_cpu PASSED in 20.1s //tensorflow/python/distribute:metrics_v1_test_2gpu PASSED in 33.8s //tensorflow/python/distribute:metrics_v1_test_cpu PASSED in 27.2s //tensorflow/python/distribute:mirrored_values_test_2gpu PASSED in 10.6s //tensorflow/python/distribute:mirrored_values_test_cpu PASSED in 8.7s //tensorflow/python/distribute:mirrored_variable_test_2gpu PASSED in 26.9s //tensorflow/python/distribute:mirrored_variable_test_cpu PASSED in 22.0s //tensorflow/python/distribute:multi_process_runner_no_init_test PASSED in 11.5s //tensorflow/python/distribute:multi_worker_continuous_run_test_cpu PASSED in 25.0s //tensorflow/python/distribute:multi_worker_util_test PASSED in 11.0s //tensorflow/python/distribute:numpy_dataset_test PASSED in 6.3s //tensorflow/python/distribute:one_device_strategy_test_cpu PASSED in 30.2s //tensorflow/python/distribute:packed_distributed_variable_test PASSED in 7.9s //tensorflow/python/distribute:parameter_server_strategy_test_2gpu PASSED in 34.9s //tensorflow/python/distribute:parameter_server_strategy_test_cpu PASSED in 35.5s //tensorflow/python/distribute:parameter_server_strategy_v2_test_2gpu PASSED in 21.9s //tensorflow/python/distribute:parameter_server_strategy_v2_test_cpu PASSED in 26.3s //tensorflow/python/distribute:per_replica_test_2gpu PASSED in 8.0s //tensorflow/python/distribute:per_replica_test_cpu PASSED in 9.6s //tensorflow/python/distribute:ps_values_test_2gpu PASSED in 8.4s //tensorflow/python/distribute:ps_values_test_cpu PASSED in 10.3s //tensorflow/python/distribute:remote_mirrored_strategy_eager_test_cpu PASSED in 10.4s //tensorflow/python/distribute:sharded_variable_test PASSED in 22.5s //tensorflow/python/distribute:shared_variable_creator_test PASSED in 9.6s //tensorflow/python/distribute:strategy_combinations_test_cpu PASSED in 46.8s //tensorflow/python/distribute:template_mirrored_strategy_test_cpu PASSED in 8.8s //tensorflow/python/distribute:test_util_test_2gpu PASSED in 19.2s //tensorflow/python/distribute:test_util_test_cpu PASSED in 17.6s //tensorflow/python/distribute:tf_function_test_2gpu PASSED in 12.3s //tensorflow/python/distribute:tf_function_test_cpu PASSED in 14.8s //tensorflow/python/distribute:values_v2_test_cpu PASSED in 12.3s //tensorflow/python/distribute:warm_starting_util_test_2gpu PASSED in 11.6s //tensorflow/python/distribute:warm_starting_util_test_cpu PASSED in 10.4s //tensorflow/python/distribute/cluster_resolver:base_cluster_resolver_py_test PASSED in 7.1s //tensorflow/python/distribute/cluster_resolver:gce_cluster_resolver_py_test PASSED in 10.8s //tensorflow/python/distribute/cluster_resolver:kubernetes_cluster_resolver_py_test PASSED in 7.2s //tensorflow/python/distribute/cluster_resolver:sagemaker_cluster_resolver_py_test PASSED in 8.4s //tensorflow/python/distribute/cluster_resolver:slurm_cluster_resolver_py_test PASSED in 7.2s //tensorflow/python/distribute/cluster_resolver:tfconfig_cluster_resolver_py_test PASSED in 8.0s //tensorflow/python/distribute/cluster_resolver/tpu:tpu_cluster_resolver_py_test PASSED in 9.5s //tensorflow/python/distribute/coordinator:metric_utils_test PASSED in 13.5s //tensorflow/python/distribute/coordinator:watchdog_test PASSED in 62.6s //tensorflow/python/distribute/experimental:dtensor_util_test_cpu PASSED in 10.0s //tensorflow/python/distribute/experimental:mirrored_strategy_test_cpu PASSED in 33.7s //tensorflow/python/distribute/experimental:multi_worker_mirrored_strategy_test_cpu PASSED in 12.6s //tensorflow/python/distribute/integration_test:saved_model_test_cpu PASSED in 49.1s //tensorflow/python/distribute/parallel_device:parallel_device_test_cpu PASSED in 10.9s //tensorflow/python/distribute/v1:all_reduce_test PASSED in 43.9s //tensorflow/python/distribute/v1:cross_device_ops_test_2gpu PASSED in 84.9s //tensorflow/python/distribute/v1:cross_device_ops_test_cpu PASSED in 73.7s //tensorflow/python/dlpack:dlpack_test_cpu PASSED in 10.9s //tensorflow/python/eager:backprop_test_cpu PASSED in 119.6s //tensorflow/python/eager:benchmarks_test_cpu PASSED in 7.6s //tensorflow/python/eager:cancellation_test_cpu PASSED in 7.0s //tensorflow/python/eager:context_test_cpu PASSED in 7.9s //tensorflow/python/eager:core_test_cpu PASSED in 25.0s //tensorflow/python/eager:gradient_input_output_exclusions_test PASSED in 35.9s //tensorflow/python/eager:graph_only_ops_test_cpu PASSED in 7.3s //tensorflow/python/eager:lift_to_graph_test PASSED in 8.8s //tensorflow/python/eager:monitoring_test_cpu PASSED in 9.2s //tensorflow/python/eager:ops_test_cpu PASSED in 11.4s //tensorflow/python/eager:profiler_client_test PASSED in 7.1s //tensorflow/python/eager:profiler_test_cpu PASSED in 8.8s //tensorflow/python/eager:pywrap_tfe_test PASSED in 20.0s //tensorflow/python/eager:record_test PASSED in 7.9s //tensorflow/python/eager:remote_benchmarks_test_cpu PASSED in 9.8s //tensorflow/python/eager:run_eager_op_as_function_test_cpu PASSED in 8.6s //tensorflow/python/eager:run_eager_op_as_function_xla_test_cpu PASSED in 7.9s //tensorflow/python/eager:small_constants_optimizer_test_cpu PASSED in 212.0s //tensorflow/python/eager:tensor_test_cpu PASSED in 12.7s //tensorflow/python/eager:wrap_function_device_test_cpu PASSED in 8.3s //tensorflow/python/eager:wrap_function_test PASSED in 9.1s //tensorflow/python/eager/benchmarks:kpi_benchmark_test_cpu PASSED in 14.8s //tensorflow/python/eager/memory_tests:remote_memory_test_cpu PASSED in 7.7s //tensorflow/python/eager/polymorphic_function:argument_naming_test_cpu PASSED in 8.9s //tensorflow/python/eager/polymorphic_function:collection_test_cpu PASSED in 8.8s //tensorflow/python/eager/polymorphic_function:compiler_ir_test_cpu PASSED in 8.1s //tensorflow/python/eager/polymorphic_function:compiler_ir_test_cpu_mlir_bridge_test PASSED in 8.6s //tensorflow/python/eager/polymorphic_function:function_spec_test PASSED in 7.6s //tensorflow/python/eager/polymorphic_function:polymorphic_function_xla_jit_test_cpu PASSED in 25.8s //tensorflow/python/eager/polymorphic_function:polymorphic_function_xla_jit_test_cpu_mlir_bridge_test PASSED in 43.9s //tensorflow/python/eager/polymorphic_function:polymorphic_function_xla_test_cpu PASSED in 7.4s //tensorflow/python/eager/polymorphic_function:quarantine_test PASSED in 25.1s //tensorflow/python/feature_column:sequence_feature_column_integration_test PASSED in 9.6s //tensorflow/python/feature_column:serialization_test PASSED in 10.3s //tensorflow/python/framework:auto_control_deps_test PASSED in 22.7s //tensorflow/python/framework:c_api_util_test PASSED in 7.4s //tensorflow/python/framework:common_shapes_test PASSED in 7.3s //tensorflow/python/framework:composite_tensor_test PASSED in 9.2s //tensorflow/python/framework:config_test_2gpu PASSED in 11.0s //tensorflow/python/framework:config_test_cpu PASSED in 13.2s //tensorflow/python/framework:constant_op_test PASSED in 9.2s //tensorflow/python/framework:device_spec_test PASSED in 7.3s //tensorflow/python/framework:device_test PASSED in 6.7s //tensorflow/python/framework:dtypes_test PASSED in 15.0s //tensorflow/python/framework:error_interpolation_test PASSED in 8.3s //tensorflow/python/framework:errors_test PASSED in 7.2s //tensorflow/python/framework:extension_type_field_test PASSED in 8.4s //tensorflow/python/framework:extension_type_test PASSED in 23.9s //tensorflow/python/framework:file_system_test PASSED in 8.7s //tensorflow/python/framework:function_def_to_graph_test PASSED in 8.5s //tensorflow/python/framework:graph_building_benchmark_cpu PASSED in 7.8s //tensorflow/python/framework:graph_util_test PASSED in 8.8s //tensorflow/python/framework:immutable_dict_test PASSED in 7.1s //tensorflow/python/framework:importer_test PASSED in 9.6s //tensorflow/python/framework:indexed_slices_test PASSED in 8.3s //tensorflow/python/framework:kernels_test PASSED in 9.3s //tensorflow/python/framework:meta_graph_test PASSED in 13.0s //tensorflow/python/framework:node_file_writer_test_cpu PASSED in 8.6s //tensorflow/python/framework:offset_counter_helper_test PASSED in 0.1s //tensorflow/python/framework:op_allowlist_namespace_test PASSED in 2.2s //tensorflow/python/framework:op_callbacks_test_cpu PASSED in 9.6s //tensorflow/python/framework:op_def_library_test PASSED in 8.3s //tensorflow/python/framework:op_def_util_test PASSED in 8.7s //tensorflow/python/framework:ops_enable_eager_test PASSED in 2.7s //tensorflow/python/framework:ops_test PASSED in 24.2s //tensorflow/python/framework:proto_test PASSED in 7.9s //tensorflow/python/framework:py_context_manager_test PASSED in 7.7s //tensorflow/python/framework:python_api_dispatcher_test PASSED in 9.2s //tensorflow/python/framework:python_api_info_test PASSED in 7.6s //tensorflow/python/framework:python_api_parameter_converter_test PASSED in 10.0s //tensorflow/python/framework:python_op_gen_annotation_test PASSED in 5.1s //tensorflow/python/framework:python_op_gen_annotator_test PASSED in 0.1s //tensorflow/python/framework:python_tensor_converter_test PASSED in 7.9s //tensorflow/python/framework:random_seed_test PASSED in 7.6s //tensorflow/python/framework:registry_test PASSED in 7.2s //tensorflow/python/framework:smart_cond_test PASSED in 7.7s //tensorflow/python/framework:sparse_tensor_test PASSED in 8.4s //tensorflow/python/framework:subscribe_test PASSED in 9.4s //tensorflow/python/framework:tensor_shape_test PASSED in 8.6s //tensorflow/python/framework:tensor_test PASSED in 8.8s //tensorflow/python/framework:tensor_util_test PASSED in 10.7s //tensorflow/python/framework:test_combinations_test PASSED in 6.8s //tensorflow/python/framework:test_util_test_cpu PASSED in 19.6s //tensorflow/python/framework:tf2_test PASSED in 7.0s //tensorflow/python/framework:traceable_stack_test PASSED in 7.8s //tensorflow/python/framework:type_spec_test PASSED in 7.5s //tensorflow/python/framework:versions_test PASSED in 8.2s //tensorflow/python/framework/experimental:graph_building_test_cpu PASSED in 7.8s //tensorflow/python/framework/experimental:unified_api_test_cpu PASSED in 12.3s //tensorflow/python/grappler:arithmetic_optimizer_test_cpu PASSED in 7.7s //tensorflow/python/grappler:auto_mixed_precision_test_cpu PASSED in 12.2s //tensorflow/python/grappler:constant_folding_test_cpu PASSED in 8.2s //tensorflow/python/grappler:cost_analyzer_test PASSED in 9.3s //tensorflow/python/grappler:datasets_test PASSED in 9.5s //tensorflow/python/grappler:item_test PASSED in 6.2s //tensorflow/python/grappler:memory_optimizer_test PASSED in 15.8s //tensorflow/python/grappler:model_analyzer_test PASSED in 9.1s //tensorflow/python/grappler:remapper_test_cpu PASSED in 8.6s //tensorflow/python/grappler:tf_optimizer_test PASSED in 8.7s //tensorflow/python/kernel_tests:benchmark_test_cpu PASSED in 10.3s //tensorflow/python/kernel_tests:check_ops_test_cpu PASSED in 21.8s //tensorflow/python/kernel_tests:collective_ops_multi_worker_test PASSED in 33.1s //tensorflow/python/kernel_tests:composite_tensor_ops_test PASSED in 8.9s //tensorflow/python/kernel_tests:critical_section_test_cpu PASSED in 20.0s //tensorflow/python/kernel_tests:garbage_collection_test PASSED in 9.7s //tensorflow/python/kernel_tests:gradient_correctness_test_cpu PASSED in 15.4s //tensorflow/python/kernel_tests:histogram_ops_test_cpu PASSED in 8.6s //tensorflow/python/kernel_tests:logging_ops_test_cpu PASSED in 9.6s //tensorflow/python/kernel_tests:numerics_test_cpu PASSED in 7.8s //tensorflow/python/kernel_tests:template_test PASSED in 13.5s //tensorflow/python/kernel_tests:trace_op_test_cpu PASSED in 7.9s //tensorflow/python/kernel_tests/array_ops:batch_gather_op_test_cpu PASSED in 9.5s //tensorflow/python/kernel_tests/array_ops:batch_scatter_ops_test PASSED in 9.4s //tensorflow/python/kernel_tests/array_ops:batchtospace_op_test_cpu PASSED in 12.6s //tensorflow/python/kernel_tests/array_ops:bcast_ops_test PASSED in 8.1s //tensorflow/python/kernel_tests/array_ops:bitcast_op_test_cpu PASSED in 11.8s //tensorflow/python/kernel_tests/array_ops:broadcast_to_ops_test_cpu PASSED in 39.2s //tensorflow/python/kernel_tests/array_ops:cast_op_test_cpu PASSED in 9.4s //tensorflow/python/kernel_tests/array_ops:constant_op_eager_test_cpu PASSED in 7.5s //tensorflow/python/kernel_tests/array_ops:constant_op_test_cpu PASSED in 12.8s //tensorflow/python/kernel_tests/array_ops:denormal_test_cpu PASSED in 7.3s //tensorflow/python/kernel_tests/array_ops:depthtospace_op_test_cpu PASSED in 10.7s //tensorflow/python/kernel_tests/array_ops:edit_distance_op_test PASSED in 8.0s //tensorflow/python/kernel_tests/array_ops:fingerprint_op_test PASSED in 11.9s //tensorflow/python/kernel_tests/array_ops:gather_nd_op_test_cpu PASSED in 9.0s //tensorflow/python/kernel_tests/array_ops:identity_n_op_py_test PASSED in 6.7s //tensorflow/python/kernel_tests/array_ops:identity_op_py_test PASSED in 8.2s //tensorflow/python/kernel_tests/array_ops:large_concat_op_test_cpu PASSED in 11.3s //tensorflow/python/kernel_tests/array_ops:manip_ops_test_cpu PASSED in 9.4s //tensorflow/python/kernel_tests/array_ops:one_hot_op_test_cpu PASSED in 8.5s //tensorflow/python/kernel_tests/array_ops:pad_op_test_cpu PASSED in 15.3s //tensorflow/python/kernel_tests/array_ops:reshape_op_test_cpu PASSED in 7.5s //tensorflow/python/kernel_tests/array_ops:reverse_sequence_op_test_cpu PASSED in 15.3s //tensorflow/python/kernel_tests/array_ops:scalar_test_cpu PASSED in 13.5s //tensorflow/python/kernel_tests/array_ops:shape_ops_test_cpu PASSED in 14.0s //tensorflow/python/kernel_tests/array_ops:slice_op_test_cpu PASSED in 11.6s //tensorflow/python/kernel_tests/array_ops:spacetobatch_op_test_cpu PASSED in 14.9s //tensorflow/python/kernel_tests/array_ops:spacetodepth_op_test_cpu PASSED in 9.1s //tensorflow/python/kernel_tests/array_ops:stack_op_test_cpu PASSED in 20.5s //tensorflow/python/kernel_tests/array_ops:unique_op_test_cpu PASSED in 8.1s //tensorflow/python/kernel_tests/array_ops:unstack_op_test_cpu PASSED in 11.4s //tensorflow/python/kernel_tests/array_ops:where_op_test_cpu PASSED in 15.6s //tensorflow/python/kernel_tests/control_flow:cond_v2_test_cpu PASSED in 55.1s //tensorflow/python/kernel_tests/control_flow:control_flow_util_test PASSED in 7.4s //tensorflow/python/kernel_tests/control_flow:control_flow_util_v2_test PASSED in 8.9s //tensorflow/python/kernel_tests/control_flow:py_func_test_cpu PASSED in 16.6s //tensorflow/python/kernel_tests/control_flow:scan_ops_test_cpu PASSED in 70.6s //tensorflow/python/kernel_tests/control_flow:while_v2_test_cpu PASSED in 77.7s //tensorflow/python/kernel_tests/custom_ops:ackermann_test PASSED in 10.8s //tensorflow/python/kernel_tests/custom_ops:duplicate_op_test PASSED in 8.4s //tensorflow/python/kernel_tests/custom_ops:invalid_op_test PASSED in 7.6s //tensorflow/python/kernel_tests/data_structures:conditional_accumulator_test PASSED in 9.3s //tensorflow/python/kernel_tests/data_structures:dynamic_partition_op_test_2gpu PASSED in 22.9s //tensorflow/python/kernel_tests/data_structures:dynamic_partition_op_test_cpu PASSED in 14.1s //tensorflow/python/kernel_tests/data_structures:dynamic_stitch_op_test_cpu PASSED in 10.6s //tensorflow/python/kernel_tests/data_structures:fifo_queue_test PASSED in 12.4s //tensorflow/python/kernel_tests/data_structures:list_ops_test_cpu PASSED in 24.6s //tensorflow/python/kernel_tests/data_structures:listdiff_op_test PASSED in 10.0s //tensorflow/python/kernel_tests/data_structures:lookup_ops_test PASSED in 27.3s //tensorflow/python/kernel_tests/data_structures:map_ops_test PASSED in 13.7s //tensorflow/python/kernel_tests/data_structures:padding_fifo_queue_test_cpu PASSED in 7.3s //tensorflow/python/kernel_tests/data_structures:priority_queue_test PASSED in 8.2s //tensorflow/python/kernel_tests/data_structures:stack_ops_test_cpu PASSED in 7.7s //tensorflow/python/kernel_tests/data_structures:stage_op_test_cpu PASSED in 14.0s //tensorflow/python/kernel_tests/distributions:bernoulli_test_cpu PASSED in 13.8s //tensorflow/python/kernel_tests/distributions:bijector_test_cpu PASSED in 9.0s //tensorflow/python/kernel_tests/distributions:categorical_test_cpu PASSED in 13.3s //tensorflow/python/kernel_tests/distributions:dirichlet_multinomial_test_cpu PASSED in 20.9s //tensorflow/python/kernel_tests/distributions:dirichlet_test_cpu PASSED in 15.8s //tensorflow/python/kernel_tests/distributions:exponential_test_cpu PASSED in 11.2s //tensorflow/python/kernel_tests/distributions:gamma_test_cpu PASSED in 59.3s //tensorflow/python/kernel_tests/distributions:identity_bijector_test_cpu PASSED in 9.7s //tensorflow/python/kernel_tests/distributions:kullback_leibler_test_cpu PASSED in 10.4s //tensorflow/python/kernel_tests/distributions:laplace_test_cpu PASSED in 38.8s //tensorflow/python/kernel_tests/distributions:multinomial_test_cpu PASSED in 7.3s //tensorflow/python/kernel_tests/distributions:normal_test_cpu PASSED in 32.4s //tensorflow/python/kernel_tests/distributions:special_math_test_cpu PASSED in 20.5s //tensorflow/python/kernel_tests/distributions:uniform_test_cpu PASSED in 13.0s //tensorflow/python/kernel_tests/image_ops:attention_ops_test PASSED in 12.2s //tensorflow/python/kernel_tests/image_ops:decode_bmp_op_test PASSED in 7.3s //tensorflow/python/kernel_tests/image_ops:decode_compressed_op_test PASSED in 8.5s //tensorflow/python/kernel_tests/image_ops:decode_image_op_test PASSED in 8.8s //tensorflow/python/kernel_tests/image_ops:decode_jpeg_op_test PASSED in 8.4s //tensorflow/python/kernel_tests/image_ops:decode_png_op_test PASSED in 7.1s //tensorflow/python/kernel_tests/image_ops:decode_raw_op_test PASSED in 8.5s //tensorflow/python/kernel_tests/image_ops:draw_bounding_box_op_test_cpu PASSED in 7.5s //tensorflow/python/kernel_tests/image_ops:extract_image_patches_op_test_cpu PASSED in 7.9s //tensorflow/python/kernel_tests/image_ops:extract_volume_patches_op_test_cpu PASSED in 13.6s //tensorflow/python/kernel_tests/io_ops:checkpoint_ops_test PASSED in 10.2s //tensorflow/python/kernel_tests/io_ops:decode_csv_op_test PASSED in 13.4s //tensorflow/python/kernel_tests/io_ops:io_ops_test PASSED in 8.4s //tensorflow/python/kernel_tests/io_ops:parse_single_example_op_test PASSED in 14.8s //tensorflow/python/kernel_tests/io_ops:parsing_ops_test PASSED in 25.3s //tensorflow/python/kernel_tests/io_ops:reader_ops_test PASSED in 12.2s //tensorflow/python/kernel_tests/io_ops:record_input_test PASSED in 82.8s //tensorflow/python/kernel_tests/io_ops:save_restore_ops_test PASSED in 8.9s //tensorflow/python/kernel_tests/linalg:determinant_op_test_cpu PASSED in 7.3s //tensorflow/python/kernel_tests/linalg:linear_operator_addition_test_cpu PASSED in 9.7s //tensorflow/python/kernel_tests/linalg:linear_operator_algebra_test_cpu PASSED in 7.4s //tensorflow/python/kernel_tests/linalg:linear_operator_test_cpu PASSED in 11.5s //tensorflow/python/kernel_tests/linalg:lu_op_test_cpu PASSED in 11.8s //tensorflow/python/kernel_tests/linalg:matrix_inverse_op_test_cpu PASSED in 11.5s //tensorflow/python/kernel_tests/linalg:matrix_logarithm_op_test PASSED in 87.4s //tensorflow/python/kernel_tests/linalg:matrix_solve_ls_op_test_cpu PASSED in 14.3s //tensorflow/python/kernel_tests/linalg:matrix_solve_op_test_cpu PASSED in 36.7s //tensorflow/python/kernel_tests/linalg:matrix_square_root_op_test_cpu PASSED in 10.4s //tensorflow/python/kernel_tests/linalg:slicing_test_cpu PASSED in 18.7s //tensorflow/python/kernel_tests/linalg/sparse:conjugate_gradient_test_cpu PASSED in 15.8s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_test_cpu PASSED in 7.2s //tensorflow/python/kernel_tests/math_ops:aggregate_ops_test_cpu PASSED in 10.1s //tensorflow/python/kernel_tests/math_ops:argmax_op_test_cpu PASSED in 9.6s //tensorflow/python/kernel_tests/math_ops:banded_triangular_solve_op_test_cpu PASSED in 21.3s //tensorflow/python/kernel_tests/math_ops:basic_gpu_test_cpu PASSED in 8.2s //tensorflow/python/kernel_tests/math_ops:bincount_op_test_cpu PASSED in 10.2s //tensorflow/python/kernel_tests/math_ops:bucketize_op_test_cpu PASSED in 8.0s //tensorflow/python/kernel_tests/math_ops:clip_ops_test PASSED in 10.2s //tensorflow/python/kernel_tests/math_ops:confusion_matrix_test PASSED in 13.8s //tensorflow/python/kernel_tests/math_ops:cross_grad_test_cpu PASSED in 9.1s //tensorflow/python/kernel_tests/math_ops:cumulative_logsumexp_test_cpu PASSED in 9.3s //tensorflow/python/kernel_tests/math_ops:in_topk_op_test_cpu PASSED in 7.3s //tensorflow/python/kernel_tests/math_ops:reduce_benchmark_test_cpu PASSED in 9.5s //tensorflow/python/kernel_tests/math_ops:segment_reduction_ops_d9m_test_cpu PASSED in 7.4s //tensorflow/python/kernel_tests/math_ops:sets_test PASSED in 33.8s //tensorflow/python/kernel_tests/math_ops:topk_op_test_cpu PASSED in 15.3s //tensorflow/python/kernel_tests/math_ops:zero_division_test_cpu PASSED in 9.7s //tensorflow/python/kernel_tests/nn_ops:betainc_op_test_cpu PASSED in 12.9s //tensorflow/python/kernel_tests/nn_ops:bias_op_test_cpu PASSED in 124.8s //tensorflow/python/kernel_tests/nn_ops:conv1d_test_cpu PASSED in 6.3s //tensorflow/python/kernel_tests/nn_ops:conv1d_transpose_test_cpu PASSED in 9.1s //tensorflow/python/kernel_tests/nn_ops:conv2d_transpose_test_cpu PASSED in 14.3s //tensorflow/python/kernel_tests/nn_ops:conv3d_backprop_filter_v2_grad_test_cpu PASSED in 32.9s //tensorflow/python/kernel_tests/nn_ops:conv3d_transpose_test_cpu PASSED in 11.5s //tensorflow/python/kernel_tests/nn_ops:ctc_decoder_ops_test PASSED in 10.4s //tensorflow/python/kernel_tests/nn_ops:ctc_loss_op_test_cpu PASSED in 85.7s //tensorflow/python/kernel_tests/nn_ops:cudnn_d9m_test_cpu PASSED in 6.9s //tensorflow/python/kernel_tests/nn_ops:cudnn_deterministic_ops_test_cpu PASSED in 7.9s //tensorflow/python/kernel_tests/nn_ops:losses_test PASSED in 32.8s //tensorflow/python/kernel_tests/nn_ops:lrn_op_test_cpu PASSED in 12.3s //tensorflow/python/kernel_tests/nn_ops:morphological_ops_test_cpu PASSED in 12.1s //tensorflow/python/kernel_tests/nn_ops:nth_element_op_test_cpu PASSED in 8.9s //tensorflow/python/kernel_tests/nn_ops:pool_test_cpu PASSED in 41.5s //tensorflow/python/kernel_tests/nn_ops:pooling_ops_3d_test_cpu PASSED in 28.1s //tensorflow/python/kernel_tests/nn_ops:relu_op_test_cpu PASSED in 9.8s //tensorflow/python/kernel_tests/nn_ops:softmax_op_test_cpu PASSED in 9.9s //tensorflow/python/kernel_tests/nn_ops:softplus_op_test_cpu PASSED in 9.4s //tensorflow/python/kernel_tests/nn_ops:softsign_op_test_cpu PASSED in 12.1s //tensorflow/python/kernel_tests/nn_ops:xent_op_d9m_test_cpu PASSED in 214.8s //tensorflow/python/kernel_tests/nn_ops:xent_op_test_cpu PASSED in 9.8s //tensorflow/python/kernel_tests/proto:descriptor_source_test PASSED in 7.1s //tensorflow/python/kernel_tests/proto:encode_proto_op_test PASSED in 8.4s //tensorflow/python/kernel_tests/quantization_ops:quantization_ops_test PASSED in 8.0s //tensorflow/python/kernel_tests/random:candidate_sampler_ops_test PASSED in 6.9s //tensorflow/python/kernel_tests/random:multinomial_op_test_cpu PASSED in 9.3s //tensorflow/python/kernel_tests/random:parameterized_truncated_normal_op_test_cpu PASSED in 16.5s //tensorflow/python/kernel_tests/random:random_crop_test_cpu PASSED in 14.6s //tensorflow/python/kernel_tests/random:random_grad_test_cpu PASSED in 12.4s //tensorflow/python/kernel_tests/random:random_ops_test_cpu PASSED in 25.3s //tensorflow/python/kernel_tests/random:random_poisson_test_cpu PASSED in 14.2s //tensorflow/python/kernel_tests/random:random_shuffle_queue_test PASSED in 8.3s //tensorflow/python/kernel_tests/random:stateful_random_ops_test_cpu PASSED in 27.8s //tensorflow/python/kernel_tests/signal:mel_ops_test_cpu PASSED in 18.0s //tensorflow/python/kernel_tests/signal:mfcc_ops_test_cpu PASSED in 8.0s //tensorflow/python/kernel_tests/signal:reconstruction_ops_test_cpu PASSED in 16.5s //tensorflow/python/kernel_tests/signal:shape_ops_test_cpu PASSED in 28.5s //tensorflow/python/kernel_tests/sparse_ops:sparse_add_op_test PASSED in 10.7s //tensorflow/python/kernel_tests/sparse_ops:sparse_concat_op_test PASSED in 9.0s //tensorflow/python/kernel_tests/sparse_ops:sparse_conditional_accumulator_test PASSED in 9.6s //tensorflow/python/kernel_tests/sparse_ops:sparse_cross_op_test PASSED in 11.8s //tensorflow/python/kernel_tests/sparse_ops:sparse_matmul_op_test_cpu PASSED in 58.8s //tensorflow/python/kernel_tests/sparse_ops:sparse_reorder_op_test PASSED in 9.5s //tensorflow/python/kernel_tests/sparse_ops:sparse_reshape_op_test PASSED in 9.3s //tensorflow/python/kernel_tests/sparse_ops:sparse_serialization_ops_test PASSED in 8.7s //tensorflow/python/kernel_tests/sparse_ops:sparse_slice_op_test PASSED in 12.2s //tensorflow/python/kernel_tests/sparse_ops:sparse_split_op_test_cpu PASSED in 8.3s //tensorflow/python/kernel_tests/sparse_ops:sparse_tensor_dense_matmul_grad_test_cpu PASSED in 17.1s //tensorflow/python/kernel_tests/sparse_ops:sparse_tensor_dense_matmul_op_d9m_test_cpu PASSED in 36.4s //tensorflow/python/kernel_tests/sparse_ops:sparse_tensor_dense_matmul_op_test_cpu PASSED in 39.6s //tensorflow/python/kernel_tests/sparse_ops:sparse_tensors_map_ops_test PASSED in 20.5s //tensorflow/python/kernel_tests/sparse_ops:sparse_to_dense_op_py_test_cpu PASSED in 7.9s //tensorflow/python/kernel_tests/sparse_ops:sparse_xent_op_d9m_test_cpu PASSED in 112.2s //tensorflow/python/kernel_tests/sparse_ops:sparse_xent_op_test_cpu PASSED in 11.3s //tensorflow/python/kernel_tests/sparse_ops:sparsemask_op_test PASSED in 7.4s //tensorflow/python/kernel_tests/strings_ops:as_string_op_test PASSED in 7.9s //tensorflow/python/kernel_tests/strings_ops:base64_ops_test PASSED in 15.0s //tensorflow/python/kernel_tests/strings_ops:reduce_join_op_test_cpu PASSED in 12.9s //tensorflow/python/kernel_tests/strings_ops:regex_full_match_op_test PASSED in 8.9s //tensorflow/python/kernel_tests/strings_ops:regex_replace_op_test PASSED in 9.5s //tensorflow/python/kernel_tests/strings_ops:string_bytes_split_op_test PASSED in 8.8s //tensorflow/python/kernel_tests/strings_ops:string_format_op_test PASSED in 9.9s //tensorflow/python/kernel_tests/strings_ops:string_join_op_test PASSED in 9.7s //tensorflow/python/kernel_tests/strings_ops:string_length_op_test PASSED in 8.0s //tensorflow/python/kernel_tests/strings_ops:string_lower_op_test PASSED in 9.3s //tensorflow/python/kernel_tests/strings_ops:string_split_op_test PASSED in 12.4s //tensorflow/python/kernel_tests/strings_ops:string_strip_op_test PASSED in 8.0s //tensorflow/python/kernel_tests/strings_ops:string_to_hash_bucket_op_test_cpu PASSED in 9.1s //tensorflow/python/kernel_tests/strings_ops:string_to_number_op_test_cpu PASSED in 12.3s //tensorflow/python/kernel_tests/strings_ops:string_upper_op_test PASSED in 9.7s //tensorflow/python/kernel_tests/strings_ops:substr_op_test PASSED in 10.0s //tensorflow/python/kernel_tests/strings_ops:unicode_decode_op_test PASSED in 21.7s //tensorflow/python/kernel_tests/strings_ops:unicode_encode_op_test PASSED in 12.4s //tensorflow/python/kernel_tests/strings_ops:unicode_script_op_test PASSED in 8.0s //tensorflow/python/kernel_tests/strings_ops:unicode_transcode_op_test PASSED in 9.1s //tensorflow/python/kernel_tests/strings_ops:unsorted_segment_join_op_test_cpu PASSED in 10.2s //tensorflow/python/kernel_tests/summary_ops:summary_ops_test_cpu PASSED in 21.8s //tensorflow/python/kernel_tests/summary_ops:summary_v1_audio_op_test_cpu PASSED in 8.8s //tensorflow/python/kernel_tests/summary_ops:summary_v1_image_op_test_cpu PASSED in 7.6s //tensorflow/python/kernel_tests/summary_ops:summary_v1_ops_test PASSED in 9.3s //tensorflow/python/kernel_tests/summary_ops:summary_v1_tensor_op_test PASSED in 7.9s //tensorflow/python/kernel_tests/v1_compat_tests:array_ops_test_cpu PASSED in 9.0s //tensorflow/python/kernel_tests/v1_compat_tests:dense_update_ops_test_cpu PASSED in 7.2s //tensorflow/python/kernel_tests/v1_compat_tests:identity_op_py_test PASSED in 7.2s //tensorflow/python/kernel_tests/v1_compat_tests:scatter_nd_ops_test_cpu PASSED in 9.2s //tensorflow/python/kernel_tests/v1_compat_tests:session_ops_test_cpu PASSED in 8.0s //tensorflow/python/kernel_tests/v1_compat_tests:stack_op_test_cpu PASSED in 7.6s //tensorflow/python/kernel_tests/variables:dense_update_ops_no_tsan_test_cpu PASSED in 7.6s //tensorflow/python/kernel_tests/variables:dense_update_ops_test_cpu PASSED in 8.5s //tensorflow/python/kernel_tests/variables:partitioned_variables_test PASSED in 9.7s //tensorflow/python/kernel_tests/variables:resource_variable_ops_test_cpu PASSED in 75.5s //tensorflow/python/kernel_tests/variables:variable_ops_test_cpu PASSED in 8.7s //tensorflow/python/kernel_tests/variables:variable_scope_test PASSED in 42.7s //tensorflow/python/kernel_tests/variables:variables_test PASSED in 11.9s //tensorflow/python/lib/core:custom_float_test PASSED in 8.5s //tensorflow/python/lib/io:file_io_test PASSED in 11.2s //tensorflow/python/lib/io:tf_record_test PASSED in 10.5s //tensorflow/python/module:module_test PASSED in 9.2s //tensorflow/python/ops/losses:util_test PASSED in 7.6s //tensorflow/python/ops/memory_tests:custom_gradient_memory_test_cpu PASSED in 17.9s //tensorflow/python/ops/numpy_ops:np_array_ops_test_cpu PASSED in 73.7s //tensorflow/python/ops/numpy_ops:np_arrays_test_cpu PASSED in 12.2s //tensorflow/python/ops/numpy_ops:np_dtypes_test_cpu PASSED in 9.3s //tensorflow/python/ops/numpy_ops:np_interop_test_cpu PASSED in 38.6s //tensorflow/python/ops/numpy_ops:np_logic_test_cpu PASSED in 11.1s //tensorflow/python/ops/numpy_ops:np_math_ops_test_cpu PASSED in 25.0s //tensorflow/python/ops/numpy_ops:np_random_test_cpu PASSED in 95.3s //tensorflow/python/ops/numpy_ops:np_utils_test_cpu PASSED in 8.2s //tensorflow/python/ops/numpy_ops/integration_test:np_config_test_cpu PASSED in 15.8s //tensorflow/python/ops/numpy_ops/integration_test:public_symbol_test PASSED in 15.0s //tensorflow/python/ops/parallel_for:array_test_cpu PASSED in 35.2s //tensorflow/python/ops/parallel_for:gradients_test_cpu PASSED in 10.5s //tensorflow/python/ops/parallel_for:xla_control_flow_ops_test_cpu PASSED in 50.2s //tensorflow/python/ops/ragged:convert_to_tensor_or_ragged_tensor_op_test PASSED in 10.1s //tensorflow/python/ops/ragged:ragged_batch_gather_op_test PASSED in 41.1s //tensorflow/python/ops/ragged:ragged_bitcast_op_test PASSED in 8.1s //tensorflow/python/ops/ragged:ragged_boolean_mask_op_test PASSED in 16.4s //tensorflow/python/ops/ragged:ragged_concat_op_test PASSED in 12.4s //tensorflow/python/ops/ragged:ragged_const_op_test PASSED in 9.1s //tensorflow/python/ops/ragged:ragged_constant_value_op_test PASSED in 7.7s //tensorflow/python/ops/ragged:ragged_cross_op_test PASSED in 31.0s //tensorflow/python/ops/ragged:ragged_dispatch_test PASSED in 185.6s //tensorflow/python/ops/ragged:ragged_dynamic_partition_op_test_cpu PASSED in 20.0s //tensorflow/python/ops/ragged:ragged_eager_test PASSED in 7.1s //tensorflow/python/ops/ragged:ragged_expand_dims_op_test PASSED in 9.2s //tensorflow/python/ops/ragged:ragged_factory_ops_test_cpu PASSED in 17.5s //tensorflow/python/ops/ragged:ragged_fill_empty_rows_op_test PASSED in 10.8s //tensorflow/python/ops/ragged:ragged_from_sparse_op_test PASSED in 13.2s //tensorflow/python/ops/ragged:ragged_from_tensor_op_test PASSED in 19.9s //tensorflow/python/ops/ragged:ragged_gather_nd_op_test PASSED in 10.1s //tensorflow/python/ops/ragged:ragged_map_flat_values_op_test PASSED in 9.2s //tensorflow/python/ops/ragged:ragged_map_fn_op_test PASSED in 12.3s //tensorflow/python/ops/ragged:ragged_math_ops_test PASSED in 13.4s //tensorflow/python/ops/ragged:ragged_matmul_op_test PASSED in 32.5s //tensorflow/python/ops/ragged:ragged_merge_dims_op_test PASSED in 25.7s //tensorflow/python/ops/ragged:ragged_one_hot_op_test PASSED in 9.9s //tensorflow/python/ops/ragged:ragged_operators_test PASSED in 22.4s //tensorflow/python/ops/ragged:ragged_placeholder_op_test PASSED in 9.9s //tensorflow/python/ops/ragged:ragged_print_op_test PASSED in 14.9s //tensorflow/python/ops/ragged:ragged_range_op_test PASSED in 7.9s //tensorflow/python/ops/ragged:ragged_rank_op_test PASSED in 7.1s //tensorflow/python/ops/ragged:ragged_reduce_op_test PASSED in 34.9s //tensorflow/python/ops/ragged:ragged_resize_image_op_test PASSED in 23.6s //tensorflow/python/ops/ragged:ragged_reverse_op_test PASSED in 8.8s //tensorflow/python/ops/ragged:ragged_row_lengths_op_test PASSED in 18.6s //tensorflow/python/ops/ragged:ragged_row_splits_to_segment_ids_op_test PASSED in 9.1s //tensorflow/python/ops/ragged:ragged_segment_ids_to_row_splits_op_test PASSED in 8.2s //tensorflow/python/ops/ragged:ragged_segment_op_test PASSED in 14.4s //tensorflow/python/ops/ragged:ragged_size_op_test PASSED in 7.4s //tensorflow/python/ops/ragged:ragged_split_op_test PASSED in 38.5s //tensorflow/python/ops/ragged:ragged_squeeze_op_test PASSED in 18.3s //tensorflow/python/ops/ragged:ragged_stack_op_test PASSED in 13.3s //tensorflow/python/ops/ragged:ragged_tensor_bounding_shape_op_test PASSED in 11.7s //tensorflow/python/ops/ragged:ragged_tensor_shape_test PASSED in 89.1s //tensorflow/python/ops/ragged:ragged_tile_op_test PASSED in 58.5s //tensorflow/python/ops/ragged:ragged_to_sparse_op_test PASSED in 7.9s //tensorflow/python/ops/ragged:ragged_to_tensor_op_test PASSED in 62.6s //tensorflow/python/ops/ragged:ragged_util_test PASSED in 22.3s //tensorflow/python/ops/ragged:ragged_where_op_test PASSED in 27.4s //tensorflow/python/ops/ragged:row_partition_test PASSED in 27.9s //tensorflow/python/ops/ragged:string_ngrams_op_test PASSED in 7.9s //tensorflow/python/ops/ragged:strings_reduce_join_op_test PASSED in 7.9s //tensorflow/python/ops/structured:structured_array_ops_test PASSED in 43.4s //tensorflow/python/ops/structured:structured_tensor_slice_test PASSED in 77.4s //tensorflow/python/ops/structured:structured_tensor_spec_test PASSED in 12.8s //tensorflow/python/ops/structured:structured_tensor_test PASSED in 50.7s //tensorflow/python/ops/v1_compat_tests:gradient_checker_test_cpu PASSED in 11.8s //tensorflow/python/platform:benchmark_test PASSED in 9.7s //tensorflow/python/platform:build_info_test PASSED in 7.9s //tensorflow/python/platform:resource_loader_test PASSED in 2.2s //tensorflow/python/profiler:pprof_profiler_test PASSED in 6.5s //tensorflow/python/profiler:profile_context_test_cpu PASSED in 34.2s //tensorflow/python/profiler:profiler_client_test_cpu PASSED in 8.6s //tensorflow/python/profiler:profiler_test_cpu PASSED in 17.2s //tensorflow/python/profiler:profiler_v2_test_cpu PASSED in 7.9s //tensorflow/python/profiler:profiler_wrapper_test PASSED in 7.3s //tensorflow/python/profiler:tfprof_logger_test PASSED in 7.3s //tensorflow/python/profiler/integration_test:profiler_api_test_cpu PASSED in 31.4s //tensorflow/python/profiler/internal:flops_registry_test PASSED in 6.2s //tensorflow/python/profiler/internal:print_model_analysis_test PASSED in 7.0s //tensorflow/python/profiler/internal:run_metadata_test_cpu PASSED in 13.4s //tensorflow/python/saved_model:fingerprinting_test PASSED in 8.0s //tensorflow/python/saved_model:keras_injection_test PASSED in 15.0s //tensorflow/python/saved_model:load_v1_in_v2_test PASSED in 13.1s //tensorflow/python/saved_model:loader_test PASSED in 10.8s //tensorflow/python/saved_model:method_name_updater_test PASSED in 8.2s //tensorflow/python/saved_model:metrics_test PASSED in 7.5s //tensorflow/python/saved_model:nested_structure_coder_test PASSED in 7.2s //tensorflow/python/saved_model:pywrap_saved_model_fingerprinting_test PASSED in 6.7s //tensorflow/python/saved_model:pywrap_saved_model_metrics_test PASSED in 7.3s //tensorflow/python/saved_model:revived_types_test PASSED in 7.8s //tensorflow/python/saved_model:save_context_test PASSED in 8.0s //tensorflow/python/saved_model:save_test PASSED in 27.4s //tensorflow/python/saved_model:saved_model_test PASSED in 20.2s //tensorflow/python/saved_model:signature_def_utils_test PASSED in 8.4s //tensorflow/python/saved_model:simple_save_test PASSED in 7.3s //tensorflow/python/saved_model:tracing_utils_test PASSED in 7.2s //tensorflow/python/saved_model:utils_test PASSED in 8.8s //tensorflow/python/saved_model/model_utils:export_output_test PASSED in 6.7s //tensorflow/python/saved_model/model_utils:export_test PASSED in 12.1s //tensorflow/python/saved_model/model_utils:mode_keys_test PASSED in 6.9s //tensorflow/python/saved_model/registration:registration_saving_test PASSED in 14.5s //tensorflow/python/saved_model/registration:registration_test PASSED in 8.4s //tensorflow/python/saved_model/registration:tf_registration_test PASSED in 15.2s //tensorflow/python/summary:plugin_asset_test PASSED in 8.9s //tensorflow/python/summary:summary_iterator_test PASSED in 8.2s //tensorflow/python/summary:summary_test PASSED in 6.2s //tensorflow/python/summary:summary_v2_test PASSED in 10.1s //tensorflow/python/summary/writer:writer_test PASSED in 20.6s //tensorflow/python/tools:aot_compiled_test PASSED in 25.3s //tensorflow/python/tools:freeze_graph_test PASSED in 11.1s //tensorflow/python/tools:optimize_for_inference_test PASSED in 9.1s //tensorflow/python/tools:print_selective_registration_header_test PASSED in 6.2s //tensorflow/python/tools:saved_model_cli_test PASSED in 27.3s //tensorflow/python/tools:saved_model_utils_test PASSED in 6.8s //tensorflow/python/tools:strip_unused_test PASSED in 6.3s //tensorflow/python/tools/api/generator:create_python_api_test PASSED in 14.4s //tensorflow/python/tools/api/generator:output_init_files_test PASSED in 15.0s //tensorflow/python/tools/api/generator:tensorflow_doc_srcs_test PASSED in 10.4s //tensorflow/python/tpu:bfloat16_test PASSED in 7.7s //tensorflow/python/tpu:feature_column_test PASSED in 14.1s //tensorflow/python/tpu:topology_test PASSED in 13.6s //tensorflow/python/tpu:tpu_embedding_for_serving_test PASSED in 11.9s //tensorflow/python/tpu:tpu_embedding_v2_utils_test PASSED in 11.0s //tensorflow/python/tpu:tpu_infeed_test PASSED in 15.1s //tensorflow/python/tpu:tpu_sharding_test PASSED in 7.1s //tensorflow/python/tpu:tpu_test_wrapper_test PASSED in 9.4s //tensorflow/python/tpu/client:client_py_test PASSED in 9.1s //tensorflow/python/trackable:autotrackable_test PASSED in 10.2s //tensorflow/python/trackable:base_delegate_test PASSED in 8.2s //tensorflow/python/trackable:base_test PASSED in 8.8s //tensorflow/python/trackable:data_structures_test PASSED in 12.2s //tensorflow/python/trackable:python_state_test PASSED in 11.3s //tensorflow/python/trackable:resource_test PASSED in 9.7s //tensorflow/python/trackable:trackable_utils_test PASSED in 9.1s //tensorflow/python/training:adadelta_test_cpu PASSED in 16.1s //tensorflow/python/training:adagrad_da_test_cpu PASSED in 12.2s //tensorflow/python/training:adagrad_test_cpu PASSED in 16.0s //tensorflow/python/training:adam_test_cpu PASSED in 16.2s //tensorflow/python/training:basic_loops_test_cpu PASSED in 9.3s //tensorflow/python/training:basic_session_run_hooks_test PASSED in 22.5s //tensorflow/python/training:checkpoint_ops_test PASSED in 15.5s //tensorflow/python/training:coordinator_test_cpu PASSED in 14.3s //tensorflow/python/training:device_setter_test_cpu PASSED in 8.9s //tensorflow/python/training:ftrl_test_cpu PASSED in 15.2s //tensorflow/python/training:gradient_descent_test_cpu PASSED in 8.6s //tensorflow/python/training:input_test PASSED in 30.8s //tensorflow/python/training:momentum_test_cpu PASSED in 11.0s //tensorflow/python/training:monitored_session_test PASSED in 27.1s //tensorflow/python/training:moving_averages_test_cpu PASSED in 14.6s //tensorflow/python/training:optimizer_test_cpu PASSED in 13.5s //tensorflow/python/training:proximal_adagrad_test_cpu PASSED in 12.1s //tensorflow/python/training:proximal_gradient_descent_test_cpu PASSED in 10.3s //tensorflow/python/training:quantize_training_test_cpu PASSED in 9.9s //tensorflow/python/training:queue_runner_test_cpu PASSED in 7.4s //tensorflow/python/training:rmsprop_test_cpu PASSED in 36.2s //tensorflow/python/training:saver_large_partitioned_variable_test PASSED in 14.3s //tensorflow/python/training:saver_test_2gpu PASSED in 33.4s //tensorflow/python/training:saver_test_cpu PASSED in 54.7s //tensorflow/python/training:server_lib_multiple_containers_test PASSED in 10.3s //tensorflow/python/training:server_lib_same_variables_clear_container_test PASSED in 11.5s //tensorflow/python/training:server_lib_same_variables_clear_test PASSED in 8.0s //tensorflow/python/training:server_lib_same_variables_no_clear_test PASSED in 7.0s //tensorflow/python/training:server_lib_sparse_job_test PASSED in 10.9s //tensorflow/python/training:server_lib_test PASSED in 20.9s //tensorflow/python/training:session_manager_test_cpu PASSED in 79.3s //tensorflow/python/training:slot_creator_test_cpu PASSED in 12.5s //tensorflow/python/training:supervisor_test PASSED in 20.8s //tensorflow/python/training:training_ops_mlir_test_cpu PASSED in 9.2s //tensorflow/python/training:training_ops_test_cpu PASSED in 16.5s //tensorflow/python/training:training_util_test PASSED in 7.6s //tensorflow/python/training:warm_starting_util_test PASSED in 22.5s //tensorflow/python/training/experimental:loss_scale_optimizer_test PASSED in 26.2s //tensorflow/python/training/experimental:loss_scale_test PASSED in 50.5s //tensorflow/python/training/experimental:mixed_precision_test_cpu PASSED in 9.0s //tensorflow/python/training/saving:saveable_object_util_test PASSED in 14.5s //tensorflow/python/util:compat_test PASSED in 9.4s //tensorflow/python/util:decorator_utils_test PASSED in 14.2s //tensorflow/python/util:deprecation_test PASSED in 14.7s //tensorflow/python/util:dispatch_test PASSED in 13.6s //tensorflow/python/util:example_parser_configuration_test PASSED in 6.5s //tensorflow/python/util:fast_module_type_test PASSED in 11.6s //tensorflow/python/util:function_parameter_canonicalizer_test PASSED in 8.5s //tensorflow/python/util:function_utils_test PASSED in 13.9s //tensorflow/python/util:keyword_args_test PASSED in 12.0s //tensorflow/python/util:lock_util_test PASSED in 8.4s //tensorflow/python/util:module_wrapper_test PASSED in 14.7s //tensorflow/python/util:nest_test PASSED in 12.6s //tensorflow/python/util:object_identity_test PASSED in 9.4s //tensorflow/python/util:pywrap_xla_ops_test PASSED in 2.6s //tensorflow/python/util:serialization_test PASSED in 8.9s //tensorflow/python/util:tf_contextlib_test PASSED in 9.8s //tensorflow/python/util:tf_decorator_test PASSED in 14.3s //tensorflow/python/util:tf_export_test PASSED in 11.4s //tensorflow/python/util:tf_inspect_test PASSED in 8.2s //tensorflow/python/util:tf_should_use_test PASSED in 8.4s //tensorflow/python/util:tf_stack_test PASSED in 8.4s //tensorflow/python/util:traceback_utils_test PASSED in 10.6s //tensorflow/python/util:type_annotations_test PASSED in 9.1s //tensorflow/python/util:variable_utils_test PASSED in 11.0s //tensorflow/python/util:vlog_test PASSED in 12.1s //tensorflow/tools/api/tests:module_test PASSED in 27.9s //tensorflow/tools/benchmark:benchmark_model_test PASSED in 2.3s //tensorflow/tools/common:public_api_test PASSED in 2.7s //tensorflow/tools/common:traverse_test PASSED in 1.7s //tensorflow/tools/compatibility:all_renames_v2_test PASSED in 8.1s //tensorflow/tools/compatibility:ast_edits_test PASSED in 12.3s //tensorflow/tools/compatibility:test_file_v1_0 PASSED in 18.6s //tensorflow/tools/compatibility:test_file_v2_0 PASSED in 17.5s //tensorflow/tools/compatibility:tf_upgrade_test PASSED in 7.5s //tensorflow/tools/compatibility:tf_upgrade_v2_safety_test PASSED in 6.5s //tensorflow/tools/docs:tf_doctest_test PASSED in 1.1s //tensorflow/tools/graph_transforms:file_utils_test PASSED in 0.8s //tensorflow/tools/graph_transforms:transform_graph_test PASSED in 3.6s //tensorflow/tools/graph_transforms:transform_utils_test PASSED in 2.0s //tensorflow/tools/graph_transforms:transforms_test PASSED in 6.9s //tensorflow/tools/proto_text:gen_proto_text_functions_lib_test PASSED in 0.4s //tensorflow/tools/tensorflow_builder/compat_checker:compat_checker_test PASSED in 0.7s //tensorflow/tsl/c:tsl_status_helper_test PASSED in 0.4s //tensorflow/tsl/c:tsl_status_test PASSED in 0.1s //tensorflow/tsl/concurrency:async_value_ref_test PASSED in 0.1s //tensorflow/tsl/concurrency:async_value_test PASSED in 0.3s //tensorflow/tsl/concurrency:concurrent_vector_test PASSED in 0.2s //tensorflow/tsl/cuda:cudnn_version_test PASSED in 0.1s //tensorflow/tsl/distributed_runtime/coordination:coordination_service_agent_test PASSED in 12.8s //tensorflow/tsl/distributed_runtime/coordination:coordination_service_error_util_test PASSED in 0.2s //tensorflow/tsl/distributed_runtime/coordination:coordination_service_recoverable_job_test PASSED in 1.2s //tensorflow/tsl/distributed_runtime/preemption:preemption_notifier_test PASSED in 7.2s //tensorflow/tsl/distributed_runtime/preemption:preemption_sync_manager_test PASSED in 5.7s //tensorflow/tsl/distributed_runtime/rpc:grpc_channel_test PASSED in 0.1s //tensorflow/tsl/distributed_runtime/rpc:grpc_util_test PASSED in 0.1s //tensorflow/tsl/framework:cancellation_test PASSED in 1.3s //tensorflow/tsl/framework:device_id_utils_test PASSED in 4.2s //tensorflow/tsl/framework/convolution:spatial_convolutions_test PASSED in 0.4s //tensorflow/tsl/lib/gtl:tsl_lib_gtl_tests PASSED in 0.2s //tensorflow/tsl/lib/hash:crc32c_test PASSED in 0.1s //tensorflow/tsl/lib/histogram:histogram_test PASSED in 0.3s //tensorflow/tsl/lib/io:buffered_inputstream_test PASSED in 0.5s //tensorflow/tsl/lib/io:cache_test PASSED in 0.2s //tensorflow/tsl/lib/io:inputbuffer_test PASSED in 3.3s //tensorflow/tsl/lib/io:inputstream_interface_test PASSED in 0.7s //tensorflow/tsl/lib/io:random_inputstream_test PASSED in 0.4s //tensorflow/tsl/lib/io:record_reader_writer_test PASSED in 0.3s //tensorflow/tsl/lib/io:recordio_test PASSED in 0.4s //tensorflow/tsl/lib/io:table_test PASSED in 4.0s //tensorflow/tsl/lib/io:zlib_buffers_test PASSED in 13.3s //tensorflow/tsl/lib/io/snappy:snappy_test PASSED in 0.3s //tensorflow/tsl/lib/math:math_util_test PASSED in 0.2s //tensorflow/tsl/lib/random:distribution_sampler_test PASSED in 0.5s //tensorflow/tsl/lib/random:philox_random_test PASSED in 0.2s //tensorflow/tsl/lib/random:random_distributions_test PASSED in 18.4s //tensorflow/tsl/lib/random:simple_philox_test PASSED in 0.1s //tensorflow/tsl/lib/random:weighted_picker_test PASSED in 14.2s //tensorflow/tsl/platform:ctstring_test PASSED in 0.6s //tensorflow/tsl/platform:denormal_test PASSED in 0.3s //tensorflow/tsl/platform:errors_test PASSED in 0.1s //tensorflow/tsl/platform:fingerprint_test PASSED in 0.2s //tensorflow/tsl/platform:float8_test PASSED in 0.9s //tensorflow/tsl/platform:hash_test PASSED in 0.6s //tensorflow/tsl/platform:integral_types_test PASSED in 0.1s //tensorflow/tsl/platform:intrusive_ptr_test PASSED in 0.1s //tensorflow/tsl/platform:logging_test PASSED in 25.7s //tensorflow/tsl/platform:mutex_test PASSED in 0.4s //tensorflow/tsl/platform:net_test PASSED in 0.4s //tensorflow/tsl/platform:numbers_test PASSED in 0.3s //tensorflow/tsl/platform:path_test PASSED in 0.2s //tensorflow/tsl/platform:port_test PASSED in 8.4s //tensorflow/tsl/platform:random_test PASSED in 1.8s //tensorflow/tsl/platform:refcount_test PASSED in 2.4s //tensorflow/tsl/platform:retrying_file_system_test PASSED in 0.5s //tensorflow/tsl/platform:retrying_utils_test PASSED in 0.8s //tensorflow/tsl/platform:scanner_test PASSED in 0.5s //tensorflow/tsl/platform:setround_test PASSED in 0.2s //tensorflow/tsl/platform:stacktrace_handler_test PASSED in 2.0s //tensorflow/tsl/platform:stacktrace_test PASSED in 0.1s //tensorflow/tsl/platform:status_matchers_test PASSED in 0.3s //tensorflow/tsl/platform:status_test PASSED in 0.4s //tensorflow/tsl/platform:statusor_test PASSED in 2.7s //tensorflow/tsl/platform:str_util_test PASSED in 0.1s //tensorflow/tsl/platform:strcat_test PASSED in 0.2s //tensorflow/tsl/platform:stringpiece_test PASSED in 0.2s //tensorflow/tsl/platform:stringprintf_test PASSED in 0.1s //tensorflow/tsl/platform:subprocess_test PASSED in 1.0s //tensorflow/tsl/platform:tstring_test PASSED in 0.5s //tensorflow/tsl/platform:unbounded_work_queue_test PASSED in 0.6s //tensorflow/tsl/platform/cloud:compute_engine_metadata_client_test PASSED in 0.3s //tensorflow/tsl/platform/cloud:compute_engine_zone_provider_test PASSED in 0.3s //tensorflow/tsl/platform/cloud:curl_http_request_test PASSED in 7.6s //tensorflow/tsl/platform/cloud:expiring_lru_cache_test PASSED in 0.6s //tensorflow/tsl/platform/cloud:gcs_dns_cache_test PASSED in 0.3s //tensorflow/tsl/platform/cloud:gcs_file_system_test PASSED in 7.9s //tensorflow/tsl/platform/cloud:gcs_throttle_test PASSED in 0.2s //tensorflow/tsl/platform/cloud:google_auth_provider_test PASSED in 0.1s //tensorflow/tsl/platform/cloud:oauth_client_test PASSED in 0.1s //tensorflow/tsl/platform/cloud:ram_file_block_cache_test PASSED in 2.3s //tensorflow/tsl/platform/cloud:time_util_test PASSED in 0.4s //tensorflow/tsl/profiler/backends/cpu:traceme_recorder_test PASSED in 0.3s //tensorflow/tsl/profiler/convert:trace_container_test PASSED in 0.2s //tensorflow/tsl/profiler/convert:trace_events_to_json_test PASSED in 0.2s //tensorflow/tsl/profiler/convert:xla_op_utils_test PASSED in 0.4s //tensorflow/tsl/profiler/convert:xplane_to_trace_events_test PASSED in 0.3s //tensorflow/tsl/profiler/lib:profiler_factory_test PASSED in 0.7s //tensorflow/tsl/profiler/lib:profiler_lock_test PASSED in 0.2s //tensorflow/tsl/profiler/lib:scoped_annotation_test PASSED in 0.2s //tensorflow/tsl/profiler/lib:traceme_encode_test PASSED in 0.5s //tensorflow/tsl/profiler/rpc/client:profiler_client_test PASSED in 3.7s //tensorflow/tsl/profiler/rpc/client:remote_profiler_session_manager_test PASSED in 3.9s //tensorflow/tsl/profiler/utils:buffer_pool_test PASSED in 0.1s //tensorflow/tsl/profiler/utils:group_events_test PASSED in 0.2s //tensorflow/tsl/profiler/utils:parse_annotation_test PASSED in 0.3s //tensorflow/tsl/profiler/utils:preprocess_xplane_test PASSED in 0.3s //tensorflow/tsl/profiler/utils:tf_op_utils_test PASSED in 0.1s //tensorflow/tsl/profiler/utils:timespan_test PASSED in 0.3s //tensorflow/tsl/profiler/utils:tpu_xplane_utils_test PASSED in 0.1s //tensorflow/tsl/profiler/utils:xplane_builder_test PASSED in 0.2s //tensorflow/tsl/profiler/utils:xplane_utils_test PASSED in 0.1s //tensorflow/tsl/util:device_name_utils_test PASSED in 0.1s //tensorflow/tsl/util:stats_calculator_test PASSED in 0.2s //tensorflow/compiler/tests:complex_div_test_cpu PASSED in 9.0s Stats over 2 runs: max = 9.0s, min = 7.7s, avg = 8.3s, dev = 0.7s //tensorflow/compiler/tests:complex_div_test_cpu_mlir_bridge_test PASSED in 7.9s Stats over 2 runs: max = 7.9s, min = 6.6s, avg = 7.3s, dev = 0.7s //tensorflow/compiler/xla/tests:conditional_test_cpu PASSED in 18.1s Stats over 2 runs: max = 18.1s, min = 16.3s, avg = 17.2s, dev = 0.9s //tensorflow/python:control_flow_ops_test_cpu PASSED in 25.2s Stats over 2 runs: max = 25.2s, min = 19.6s, avg = 22.4s, dev = 2.8s //tensorflow/python/data/experimental/kernel_tests/optimization:optimization_test PASSED in 29.9s Stats over 2 runs: max = 29.9s, min = 21.3s, avg = 25.6s, dev = 4.3s //tensorflow/python/data/experimental/kernel_tests/service:metadata_test PASSED in 18.7s Stats over 2 runs: max = 18.7s, min = 16.8s, avg = 17.8s, dev = 0.9s //tensorflow/python/data/kernel_tests:padded_batch_test PASSED in 28.6s Stats over 2 runs: max = 28.6s, min = 27.6s, avg = 28.1s, dev = 0.5s //tensorflow/python/data/kernel_tests:repeat_test PASSED in 63.1s Stats over 2 runs: max = 63.1s, min = 60.3s, avg = 61.7s, dev = 1.4s //tensorflow/python/data/kernel_tests:window_test PASSED in 70.4s Stats over 2 runs: max = 70.4s, min = 47.6s, avg = 59.0s, dev = 11.4s //tensorflow/python/distribute:strategy_common_test_2gpu PASSED in 28.8s Stats over 2 runs: max = 28.8s, min = 21.8s, avg = 25.3s, dev = 3.5s //tensorflow/python/distribute:strategy_common_test_cpu PASSED in 26.3s Stats over 2 runs: max = 26.3s, min = 22.5s, avg = 24.4s, dev = 1.9s //tensorflow/python/distribute:strategy_common_test_xla_2gpu PASSED in 17.2s Stats over 2 runs: max = 17.2s, min = 15.8s, avg = 16.5s, dev = 0.7s //tensorflow/python/kernel_tests/array_ops:scatter_nd_ops_test_cpu PASSED in 14.9s Stats over 2 runs: max = 14.9s, min = 13.3s, avg = 14.1s, dev = 0.8s //tensorflow/python/kernel_tests/array_ops:scatter_ops_test_cpu PASSED in 30.9s Stats over 2 runs: max = 30.9s, min = 28.4s, avg = 29.7s, dev = 1.3s //tensorflow/python/kernel_tests/control_flow:functional_ops_test_cpu PASSED in 28.2s Stats over 2 runs: max = 28.2s, min = 26.0s, avg = 27.1s, dev = 1.1s //tensorflow/python/kernel_tests/control_flow:map_fn_test_cpu PASSED in 11.3s Stats over 2 runs: max = 11.3s, min = 10.9s, avg = 11.1s, dev = 0.2s //tensorflow/python/kernel_tests/nn_ops:atrous_conv2d_test_cpu PASSED in 30.0s Stats over 2 runs: max = 30.0s, min = 20.4s, avg = 25.2s, dev = 4.8s //tensorflow/python/kernel_tests/nn_ops:bias_op_d9m_test_cpu PASSED in 131.9s Stats over 2 runs: max = 131.9s, min = 51.9s, avg = 91.9s, dev = 40.0s //tensorflow/python/kernel_tests/nn_ops:conv2d_backprop_filter_grad_test_cpu PASSED in 168.8s Stats over 2 runs: max = 168.8s, min = 6.5s, avg = 87.7s, dev = 81.1s //tensorflow/compiler/tests:spacetobatch_op_test_cpu PASSED in 8.9s Stats over 3 runs: max = 8.9s, min = 8.8s, avg = 8.9s, dev = 0.1s //tensorflow/compiler/tests:spacetobatch_op_test_cpu_mlir_bridge_test PASSED in 12.3s Stats over 3 runs: max = 12.3s, min = 11.4s, avg = 11.9s, dev = 0.4s //tensorflow/compiler/xla/tests:triangular_solve_test_cpu PASSED in 77.4s Stats over 3 runs: max = 77.4s, min = 69.2s, avg = 72.6s, dev = 3.5s //tensorflow/core/data/service:thread_safe_buffer_test PASSED in 0.5s Stats over 3 runs: max = 0.5s, min = 0.4s, avg = 0.4s, dev = 0.1s //tensorflow/python/data/experimental/kernel_tests/service:multi_process_cluster_test PASSED in 17.2s Stats over 3 runs: max = 17.2s, min = 11.7s, avg = 14.7s, dev = 2.3s //tensorflow/python/data/kernel_tests:unique_test PASSED in 18.6s Stats over 3 runs: max = 18.6s, min = 14.7s, avg = 16.0s, dev = 1.8s //tensorflow/python/kernel_tests/array_ops:gather_op_test_cpu PASSED in 49.2s Stats over 3 runs: max = 49.2s, min = 36.5s, avg = 41.5s, dev = 5.6s //tensorflow/python/kernel_tests/array_ops:weights_broadcast_test PASSED in 9.3s Stats over 3 runs: max = 9.3s, min = 9.0s, avg = 9.2s, dev = 0.1s //tensorflow/python/kernel_tests/distributions:util_test_cpu PASSED in 11.6s Stats over 3 runs: max = 11.6s, min = 10.3s, avg = 10.8s, dev = 0.6s //tensorflow/python/kernel_tests/linalg:matrix_triangular_solve_op_test_cpu PASSED in 628.1s Stats over 3 runs: max = 628.1s, min = 8.3s, avg = 215.6s, dev = 291.6s //tensorflow/python/kernel_tests/random:multinomial_op_big_test_cpu PASSED in 18.3s Stats over 3 runs: max = 18.3s, min = 15.0s, avg = 16.6s, dev = 1.3s //tensorflow/compiler/xla/tests:dynamic_ops_test_cpu PASSED in 19.1s Stats over 4 runs: max = 19.1s, min = 13.9s, avg = 16.4s, dev = 2.0s //tensorflow/core/kernels:example_parsing_ops_test PASSED in 0.7s Stats over 4 runs: max = 0.7s, min = 0.5s, avg = 0.6s, dev = 0.1s //tensorflow/python:nn_batchnorm_test_cpu PASSED in 17.0s Stats over 4 runs: max = 17.0s, min = 13.6s, avg = 14.7s, dev = 1.4s //tensorflow/python:nn_fused_batchnorm_d9m_test_cpu PASSED in 15.4s Stats over 4 runs: max = 15.4s, min = 14.6s, avg = 14.9s, dev = 0.3s //tensorflow/python/data/experimental/kernel_tests:auto_shard_dataset_test PASSED in 29.7s Stats over 4 runs: max = 29.7s, min = 17.2s, avg = 22.6s, dev = 4.7s //tensorflow/python/data/experimental/kernel_tests:map_and_batch_test PASSED in 33.5s Stats over 4 runs: max = 33.5s, min = 21.4s, avg = 25.5s, dev = 4.7s //tensorflow/python/data/experimental/kernel_tests:parse_example_dataset_test PASSED in 23.9s Stats over 4 runs: max = 23.9s, min = 10.6s, avg = 17.6s, dev = 6.1s //tensorflow/python/data/experimental/kernel_tests:rebatch_dataset_test PASSED in 25.9s Stats over 4 runs: max = 25.9s, min = 10.3s, avg = 16.8s, dev = 5.9s //tensorflow/python/data/experimental/kernel_tests:sql_dataset_test PASSED in 67.3s Stats over 4 runs: max = 67.3s, min = 48.9s, avg = 57.4s, dev = 8.5s //tensorflow/python/data/experimental/kernel_tests/service:cross_trainer_cache_ft_test PASSED in 8.5s Stats over 4 runs: max = 8.5s, min = 6.7s, avg = 7.6s, dev = 0.8s //tensorflow/python/data/experimental/kernel_tests/service:distributed_save_test PASSED in 46.5s Stats over 4 runs: max = 46.5s, min = 20.2s, avg = 32.5s, dev = 11.1s //tensorflow/python/data/kernel_tests:batch_test PASSED in 57.2s Stats over 4 runs: max = 57.2s, min = 43.4s, avg = 48.0s, dev = 5.4s //tensorflow/python/data/kernel_tests:fixed_length_record_dataset_test PASSED in 19.6s Stats over 4 runs: max = 19.6s, min = 9.7s, avg = 14.4s, dev = 4.4s //tensorflow/python/data/kernel_tests:from_generator_test PASSED in 38.2s Stats over 4 runs: max = 38.2s, min = 19.7s, avg = 27.0s, dev = 7.1s //tensorflow/python/data/kernel_tests:group_by_window_test PASSED in 23.1s Stats over 4 runs: max = 23.1s, min = 7.0s, avg = 13.1s, dev = 6.7s //tensorflow/python/data/kernel_tests:ragged_batch_test PASSED in 24.7s Stats over 4 runs: max = 24.7s, min = 22.6s, avg = 23.9s, dev = 0.8s //tensorflow/python/data/kernel_tests:skip_test PASSED in 19.7s Stats over 4 runs: max = 19.7s, min = 13.4s, avg = 16.5s, dev = 2.6s //tensorflow/python/data/kernel_tests:take_test PASSED in 22.6s Stats over 4 runs: max = 22.6s, min = 21.5s, avg = 22.0s, dev = 0.4s //tensorflow/python/data/kernel_tests:take_while_test PASSED in 28.9s Stats over 4 runs: max = 28.9s, min = 25.1s, avg = 26.8s, dev = 1.4s //tensorflow/python/data/kernel_tests:text_line_dataset_test PASSED in 19.4s Stats over 4 runs: max = 19.4s, min = 12.8s, avg = 16.0s, dev = 2.9s //tensorflow/python/data/kernel_tests:zip_test PASSED in 14.6s Stats over 4 runs: max = 14.6s, min = 13.0s, avg = 13.7s, dev = 0.6s //tensorflow/python/debug/lib:dumping_callback_test_cpu PASSED in 16.0s Stats over 4 runs: max = 16.0s, min = 13.3s, avg = 14.2s, dev = 1.1s //tensorflow/python/distribute:cross_device_ops_test_2gpu PASSED in 33.5s Stats over 4 runs: max = 33.5s, min = 26.5s, avg = 29.4s, dev = 2.6s //tensorflow/python/distribute:cross_device_ops_test_cpu PASSED in 27.4s Stats over 4 runs: max = 27.4s, min = 20.5s, avg = 23.6s, dev = 2.8s //tensorflow/python/distribute:strategy_gather_test_2gpu PASSED in 35.6s Stats over 4 runs: max = 35.6s, min = 17.7s, avg = 25.8s, dev = 7.8s //tensorflow/python/distribute:strategy_gather_test_cpu PASSED in 39.3s Stats over 4 runs: max = 39.3s, min = 22.5s, avg = 31.4s, dev = 7.8s //tensorflow/python/distribute:strategy_gather_test_xla_2gpu PASSED in 29.3s Stats over 4 runs: max = 29.3s, min = 12.3s, avg = 20.9s, dev = 8.4s //tensorflow/python/framework:convert_to_constants_test PASSED in 32.1s Stats over 4 runs: max = 32.1s, min = 19.6s, avg = 24.5s, dev = 4.8s //tensorflow/python/kernel_tests:collective_ops_test_2gpu PASSED in 26.7s Stats over 4 runs: max = 26.7s, min = 23.8s, avg = 25.5s, dev = 1.1s //tensorflow/python/kernel_tests:collective_ops_test_cpu PASSED in 44.8s Stats over 4 runs: max = 44.8s, min = 39.0s, avg = 42.7s, dev = 2.3s //tensorflow/python/kernel_tests/array_ops:concat_op_test_cpu PASSED in 14.4s Stats over 4 runs: max = 14.4s, min = 12.7s, avg = 13.6s, dev = 0.6s //tensorflow/python/kernel_tests/array_ops:init_ops_test_cpu PASSED in 74.7s Stats over 4 runs: max = 74.7s, min = 25.0s, avg = 47.6s, dev = 21.0s //tensorflow/python/kernel_tests/array_ops:split_op_test_cpu PASSED in 36.3s Stats over 4 runs: max = 36.3s, min = 12.5s, avg = 21.4s, dev = 9.8s //tensorflow/python/kernel_tests/linalg:einsum_op_test_cpu PASSED in 97.2s Stats over 4 runs: max = 97.2s, min = 17.6s, avg = 48.9s, dev = 32.1s //tensorflow/python/kernel_tests/linalg:linear_operator_lower_triangular_test_cpu PASSED in 28.2s Stats over 4 runs: max = 28.2s, min = 24.9s, avg = 26.5s, dev = 1.4s //tensorflow/python/kernel_tests/nn_ops:conv_ops_test_cpu PASSED in 44.4s Stats over 4 runs: max = 44.4s, min = 37.8s, avg = 41.6s, dev = 2.5s //tensorflow/python/kernel_tests/random:random_gamma_test_cpu PASSED in 100.7s Stats over 4 runs: max = 100.7s, min = 7.8s, avg = 49.2s, dev = 41.8s //tensorflow/python/kernel_tests/signal:window_ops_test_cpu PASSED in 16.4s Stats over 4 runs: max = 16.4s, min = 16.0s, avg = 16.2s, dev = 0.2s //tensorflow/python/ops/ragged:ragged_gather_op_test PASSED in 81.6s Stats over 4 runs: max = 81.6s, min = 19.2s, avg = 49.0s, dev = 22.5s //tensorflow/python/ops/ragged:ragged_getitem_test PASSED in 75.4s Stats over 4 runs: max = 75.4s, min = 56.2s, avg = 63.9s, dev = 7.1s //tensorflow/compiler/tests:async_comp_test_cpu PASSED in 9.3s Stats over 5 runs: max = 9.3s, min = 9.3s, avg = 9.3s, dev = 0.0s //tensorflow/compiler/tests:conv3d_test_cpu PASSED in 16.0s Stats over 5 runs: max = 16.0s, min = 6.6s, avg = 10.8s, dev = 4.2s //tensorflow/compiler/tests:conv3d_test_cpu_mlir_bridge_test PASSED in 12.2s Stats over 5 runs: max = 12.2s, min = 5.6s, avg = 8.4s, dev = 2.9s //tensorflow/compiler/tests:depthwise_conv_op_test_cpu PASSED in 17.3s Stats over 5 runs: max = 17.3s, min = 11.4s, avg = 13.9s, dev = 2.3s //tensorflow/compiler/tests:depthwise_conv_op_test_cpu_mlir_bridge_test PASSED in 14.4s Stats over 5 runs: max = 14.4s, min = 7.6s, avg = 10.4s, dev = 2.7s //tensorflow/compiler/tests:fused_batchnorm_test_cpu PASSED in 8.7s Stats over 5 runs: max = 8.7s, min = 8.1s, avg = 8.5s, dev = 0.2s //tensorflow/compiler/tests:fused_batchnorm_test_cpu_mlir_bridge_test PASSED in 7.1s Stats over 5 runs: max = 7.1s, min = 5.7s, avg = 6.4s, dev = 0.5s //tensorflow/compiler/tests:image_ops_jit_compile_test_cpu PASSED in 7.2s Stats over 5 runs: max = 7.2s, min = 6.0s, avg = 6.7s, dev = 0.4s //tensorflow/compiler/tests:reduce_ops_test_cpu PASSED in 9.7s Stats over 5 runs: max = 9.7s, min = 8.8s, avg = 9.2s, dev = 0.3s //tensorflow/compiler/tests:reduce_ops_test_cpu_mlir_bridge_test PASSED in 17.0s Stats over 5 runs: max = 17.0s, min = 14.2s, avg = 16.0s, dev = 1.3s //tensorflow/compiler/tests:repeat_op_test_cpu PASSED in 8.7s Stats over 5 runs: max = 8.7s, min = 5.8s, avg = 6.6s, dev = 1.1s //tensorflow/compiler/tests:repeat_op_test_cpu_mlir_bridge_test PASSED in 8.9s Stats over 5 runs: max = 8.9s, min = 7.7s, avg = 8.2s, dev = 0.5s //tensorflow/compiler/tests:special_math_test_cpu PASSED in 99.8s Stats over 5 runs: max = 99.8s, min = 13.2s, avg = 47.4s, dev = 29.1s //tensorflow/compiler/tests:special_math_test_cpu_mlir_bridge_test PASSED in 98.2s Stats over 5 runs: max = 98.2s, min = 14.0s, avg = 47.6s, dev = 28.6s //tensorflow/compiler/xla/client/lib:self_adjoint_eig_test_cpu PASSED in 30.5s Stats over 5 runs: max = 30.5s, min = 14.8s, avg = 24.0s, dev = 6.8s //tensorflow/core/grappler/optimizers:constant_folding_test PASSED in 8.8s Stats over 5 runs: max = 8.8s, min = 3.6s, avg = 5.8s, dev = 1.8s //tensorflow/dtensor/python/tests:layout_propagation_test_cpu PASSED in 11.5s Stats over 5 runs: max = 11.5s, min = 10.1s, avg = 10.9s, dev = 0.5s //tensorflow/python/distribute:mirrored_strategy_test_2gpu PASSED in 10.9s Stats over 5 runs: max = 10.9s, min = 9.3s, avg = 10.5s, dev = 0.6s //tensorflow/python/distribute:mirrored_strategy_test_cpu PASSED in 10.5s Stats over 5 runs: max = 10.5s, min = 8.5s, avg = 9.6s, dev = 0.8s //tensorflow/python/distribute:moving_averages_test_2gpu PASSED in 17.7s Stats over 5 runs: max = 17.7s, min = 13.8s, avg = 15.4s, dev = 1.3s //tensorflow/python/distribute:moving_averages_test_cpu PASSED in 19.5s Stats over 5 runs: max = 19.5s, min = 13.9s, avg = 16.6s, dev = 1.8s //tensorflow/python/distribute:vars_test_2gpu PASSED in 17.9s Stats over 5 runs: max = 17.9s, min = 14.7s, avg = 16.4s, dev = 1.0s //tensorflow/python/distribute:vars_test_cpu PASSED in 16.1s Stats over 5 runs: max = 16.1s, min = 13.1s, avg = 14.3s, dev = 1.1s //tensorflow/python/eager:device_placement_test_cpu PASSED in 13.6s Stats over 5 runs: max = 13.6s, min = 10.3s, avg = 12.2s, dev = 1.2s //tensorflow/python/eager:forwardprop_test_cpu PASSED in 123.2s Stats over 5 runs: max = 123.2s, min = 13.9s, avg = 51.0s, dev = 37.7s //tensorflow/python/eager/polymorphic_function:gradients_test_cpu PASSED in 16.0s Stats over 5 runs: max = 16.0s, min = 10.8s, avg = 12.9s, dev = 1.9s //tensorflow/python/kernel_tests/linalg:cholesky_op_test_cpu PASSED in 116.6s Stats over 5 runs: max = 116.6s, min = 51.6s, avg = 73.8s, dev = 23.6s //tensorflow/python/kernel_tests/linalg:linear_operator_adjoint_test_cpu PASSED in 32.5s Stats over 5 runs: max = 32.5s, min = 26.9s, avg = 30.4s, dev = 2.1s //tensorflow/python/kernel_tests/linalg:linear_operator_composition_test_cpu PASSED in 60.3s Stats over 5 runs: max = 60.3s, min = 51.1s, avg = 53.1s, dev = 3.6s //tensorflow/python/kernel_tests/linalg:linear_operator_diag_test_cpu PASSED in 23.4s Stats over 5 runs: max = 23.4s, min = 22.1s, avg = 22.8s, dev = 0.5s //tensorflow/python/kernel_tests/linalg:linear_operator_full_matrix_test_cpu PASSED in 34.1s Stats over 5 runs: max = 34.1s, min = 30.4s, avg = 32.4s, dev = 1.3s //tensorflow/python/kernel_tests/linalg:linear_operator_householder_test_cpu PASSED in 42.3s Stats over 5 runs: max = 42.3s, min = 35.9s, avg = 38.4s, dev = 2.1s //tensorflow/python/kernel_tests/linalg:linear_operator_identity_test_cpu PASSED in 46.6s Stats over 5 runs: max = 46.6s, min = 38.8s, avg = 43.8s, dev = 2.9s //tensorflow/python/kernel_tests/linalg:linear_operator_inversion_test_cpu PASSED in 28.4s Stats over 5 runs: max = 28.4s, min = 23.8s, avg = 24.9s, dev = 1.8s //tensorflow/python/kernel_tests/linalg:linear_operator_permutation_test_cpu PASSED in 32.6s Stats over 5 runs: max = 32.6s, min = 28.1s, avg = 30.0s, dev = 1.5s //tensorflow/python/kernel_tests/linalg:linear_operator_toeplitz_test_cpu PASSED in 16.5s Stats over 5 runs: max = 16.5s, min = 13.5s, avg = 14.6s, dev = 1.0s //tensorflow/python/kernel_tests/linalg:linear_operator_tridiag_test_cpu PASSED in 125.7s Stats over 5 runs: max = 125.7s, min = 102.3s, avg = 113.6s, dev = 8.7s //tensorflow/python/kernel_tests/linalg:linear_operator_util_test_cpu PASSED in 10.3s Stats over 5 runs: max = 10.3s, min = 9.7s, avg = 9.9s, dev = 0.2s //tensorflow/python/kernel_tests/linalg:linear_operator_zeros_test_cpu PASSED in 30.6s Stats over 5 runs: max = 30.6s, min = 28.0s, avg = 29.3s, dev = 1.0s //tensorflow/python/kernel_tests/nn_ops:fractional_avg_pool_op_test PASSED in 18.2s Stats over 5 runs: max = 18.2s, min = 6.6s, avg = 10.2s, dev = 4.2s //tensorflow/python/kernel_tests/nn_ops:fractional_max_pool_op_test PASSED in 15.7s Stats over 5 runs: max = 15.7s, min = 5.0s, avg = 8.3s, dev = 3.9s //tensorflow/python/kernel_tests/sparse_ops:sparse_ops_test_cpu PASSED in 26.2s Stats over 5 runs: max = 26.2s, min = 8.4s, avg = 12.8s, dev = 6.8s //tensorflow/python/ops/parallel_for:math_test_cpu PASSED in 74.9s Stats over 5 runs: max = 74.9s, min = 22.7s, avg = 43.6s, dev = 18.5s //tensorflow/compiler/tests:scan_ops_test_cpu PASSED in 14.2s Stats over 6 runs: max = 14.2s, min = 10.5s, avg = 12.6s, dev = 1.2s //tensorflow/compiler/tests:scan_ops_test_cpu_mlir_bridge_test PASSED in 22.3s Stats over 6 runs: max = 22.3s, min = 14.0s, avg = 18.2s, dev = 3.0s //tensorflow/python:accumulate_n_benchmark_cpu PASSED in 6.7s Stats over 6 runs: max = 6.7s, min = 6.4s, avg = 6.6s, dev = 0.1s //tensorflow/python/data/experimental/kernel_tests:make_batched_features_dataset_test PASSED in 43.3s Stats over 6 runs: max = 43.3s, min = 7.9s, avg = 22.8s, dev = 15.0s //tensorflow/python/kernel_tests/array_ops:diag_op_test_cpu PASSED in 67.4s Stats over 6 runs: max = 67.4s, min = 9.9s, avg = 21.5s, dev = 20.6s //tensorflow/python/kernel_tests/math_ops:reduction_ops_test_cpu PASSED in 60.4s Stats over 6 runs: max = 60.4s, min = 31.8s, avg = 46.4s, dev = 8.5s //tensorflow/python/distribute/experimental/rpc:rpc_ops_test PASSED in 11.0s Stats over 7 runs: max = 11.0s, min = 7.4s, avg = 8.8s, dev = 1.3s //tensorflow/compiler/tests:matrix_diag_ops_test_cpu PASSED in 56.6s Stats over 8 runs: max = 56.6s, min = 6.5s, avg = 23.0s, dev = 17.2s //tensorflow/compiler/tests:matrix_diag_ops_test_cpu_mlir_bridge_test PASSED in 68.4s Stats over 8 runs: max = 68.4s, min = 6.3s, avg = 26.8s, dev = 21.4s //tensorflow/python/data/experimental/kernel_tests:csv_dataset_test PASSED in 28.7s Stats over 8 runs: max = 28.7s, min = 7.2s, avg = 14.8s, dev = 7.7s //tensorflow/python/data/experimental/kernel_tests:parallel_interleave_test PASSED in 25.6s Stats over 8 runs: max = 25.6s, min = 11.3s, avg = 18.2s, dev = 4.9s //tensorflow/python/data/experimental/kernel_tests/service:coordinated_read_ft_test PASSED in 43.8s Stats over 8 runs: max = 43.8s, min = 11.8s, avg = 27.2s, dev = 13.6s //tensorflow/python/data/experimental/kernel_tests/service:coordinated_read_test PASSED in 43.3s Stats over 8 runs: max = 43.3s, min = 14.0s, avg = 21.4s, dev = 9.9s //tensorflow/python/data/experimental/kernel_tests/service:cross_trainer_cache_test PASSED in 42.0s Stats over 8 runs: max = 42.0s, min = 6.6s, avg = 20.5s, dev = 13.7s //tensorflow/python/data/experimental/kernel_tests/service:fault_tolerance_test PASSED in 29.8s Stats over 8 runs: max = 29.8s, min = 14.3s, avg = 18.3s, dev = 4.6s //tensorflow/python/data/kernel_tests:filter_test PASSED in 27.9s Stats over 8 runs: max = 27.9s, min = 16.2s, avg = 21.9s, dev = 3.3s //tensorflow/python/data/kernel_tests:flat_map_test PASSED in 22.5s Stats over 8 runs: max = 22.5s, min = 15.0s, avg = 18.6s, dev = 2.9s //tensorflow/python/data/kernel_tests:shard_test PASSED in 17.3s Stats over 8 runs: max = 17.3s, min = 10.8s, avg = 14.7s, dev = 1.8s //tensorflow/python/data/kernel_tests:shuffle_test PASSED in 55.2s Stats over 8 runs: max = 55.2s, min = 21.3s, avg = 27.6s, dev = 10.5s //tensorflow/python/data/kernel_tests:tf_record_dataset_test PASSED in 38.1s Stats over 8 runs: max = 38.1s, min = 18.2s, avg = 28.7s, dev = 5.7s //tensorflow/python/distribute/failure_handling:failure_handler_test PASSED in 58.0s Stats over 8 runs: max = 58.0s, min = 22.1s, avg = 40.3s, dev = 10.9s //tensorflow/python/kernel_tests/linalg:linalg_ops_test_cpu PASSED in 60.4s Stats over 8 runs: max = 60.4s, min = 40.7s, avg = 50.2s, dev = 7.5s //tensorflow/python/kernel_tests/linalg:linear_operator_block_diag_test_cpu PASSED in 61.2s Stats over 8 runs: max = 61.2s, min = 45.1s, avg = 55.6s, dev = 5.5s //tensorflow/python/kernel_tests/linalg:linear_operator_block_lower_triangular_test_cpu PASSED in 53.8s Stats over 8 runs: max = 53.8s, min = 39.2s, avg = 45.7s, dev = 5.7s //tensorflow/python/kernel_tests/nn_ops:depthwise_conv_op_d9m_test_cpu PASSED in 98.4s Stats over 8 runs: max = 98.4s, min = 4.5s, avg = 23.3s, dev = 31.1s //tensorflow/python/kernel_tests/nn_ops:depthwise_conv_op_test_cpu PASSED in 8.9s Stats over 8 runs: max = 8.9s, min = 7.2s, avg = 8.0s, dev = 0.6s //tensorflow/python/kernel_tests/signal:fft_ops_test_cpu PASSED in 26.8s Stats over 8 runs: max = 26.8s, min = 12.5s, avg = 18.9s, dev = 4.9s //tensorflow/python/ops/ragged:dynamic_ragged_shape_test PASSED in 61.8s Stats over 8 runs: max = 61.8s, min = 37.6s, avg = 45.9s, dev = 8.8s //tensorflow/python/ops/ragged:ragged_tensor_test PASSED in 26.7s Stats over 8 runs: max = 26.7s, min = 11.8s, avg = 16.6s, dev = 4.5s //tensorflow/dtensor/python/tests:input_util_test FLAKY, failed in 1 out of 9 in 36.9s Stats over 9 runs: max = 36.9s, min = 16.8s, avg = 28.7s, dev = 6.1s /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/testlogs/tensorflow/dtensor/python/tests/input_util_test/shard_1_of_8/test_attempts/attempt_1.log //tensorflow/python/distribute/failure_handling:gce_failure_handler_test FLAKY, failed in 1 out of 9 in 108.6s Stats over 9 runs: max = 108.6s, min = 11.6s, avg = 42.1s, dev = 37.1s /home/buildslave/.cache/bazel/_bazel_buildslave/fbac33eb30dbfb6b11b15a7ff5ac830d/execroot/org_tensorflow/bazel-out/aarch64-opt/testlogs/tensorflow/python/distribute/failure_handling/gce_failure_handler_test/shard_3_of_8/test_attempts/attempt_1.log //tensorflow/compiler/tests:bincount_op_test_cpu PASSED in 7.6s Stats over 10 runs: max = 7.6s, min = 4.5s, avg = 5.7s, dev = 1.0s //tensorflow/compiler/tests:conv2d_test_cpu PASSED in 7.2s Stats over 10 runs: max = 7.2s, min = 6.5s, avg = 6.9s, dev = 0.2s //tensorflow/compiler/tests:conv2d_test_cpu_mlir_bridge_test PASSED in 8.6s Stats over 10 runs: max = 8.6s, min = 7.6s, avg = 7.9s, dev = 0.3s //tensorflow/compiler/tests:image_ops_test_cpu PASSED in 22.7s Stats over 10 runs: max = 22.7s, min = 14.0s, avg = 16.9s, dev = 2.7s //tensorflow/compiler/tests:random_ops_test_cpu PASSED in 18.8s Stats over 10 runs: max = 18.8s, min = 12.0s, avg = 15.4s, dev = 2.0s //tensorflow/compiler/tests:random_ops_test_cpu_mlir_bridge_test PASSED in 17.5s Stats over 10 runs: max = 17.5s, min = 11.0s, avg = 14.4s, dev = 2.4s //tensorflow/compiler/tests:stateless_random_ops_test_cpu PASSED in 75.2s Stats over 10 runs: max = 75.2s, min = 36.1s, avg = 53.5s, dev = 12.6s //tensorflow/compiler/tests:stateless_random_ops_test_cpu_mlir_bridge_test PASSED in 74.2s Stats over 10 runs: max = 74.2s, min = 33.5s, avg = 53.6s, dev = 13.1s //tensorflow/compiler/xla/client/lib:svd_test_cpu PASSED in 73.4s Stats over 10 runs: max = 73.4s, min = 9.1s, avg = 27.9s, dev = 23.7s //tensorflow/compiler/xla/client/lib:tridiagonal_test_cpu PASSED in 15.0s Stats over 10 runs: max = 15.0s, min = 11.8s, avg = 12.9s, dev = 1.1s //tensorflow/compiler/xla/service/cpu:cpu_runtime_test PASSED in 13.5s Stats over 10 runs: max = 13.5s, min = 0.9s, avg = 9.5s, dev = 4.3s //tensorflow/python:special_math_ops_test_cpu PASSED in 47.1s Stats over 10 runs: max = 47.1s, min = 11.2s, avg = 16.9s, dev = 10.4s //tensorflow/python/data/kernel_tests:rejection_resample_test PASSED in 28.6s Stats over 10 runs: max = 28.6s, min = 4.0s, avg = 12.9s, dev = 6.7s //tensorflow/python/distribute:input_lib_test_2gpu PASSED in 42.2s Stats over 10 runs: max = 42.2s, min = 31.3s, avg = 38.6s, dev = 3.2s //tensorflow/python/distribute:input_lib_test_cpu PASSED in 48.7s Stats over 10 runs: max = 48.7s, min = 29.3s, avg = 35.2s, dev = 5.6s //tensorflow/python/distribute:input_lib_type_spec_test_2gpu PASSED in 17.5s Stats over 10 runs: max = 17.5s, min = 8.2s, avg = 12.2s, dev = 3.3s //tensorflow/python/distribute:input_lib_type_spec_test_cpu PASSED in 17.1s Stats over 10 runs: max = 17.1s, min = 4.5s, avg = 11.0s, dev = 4.1s //tensorflow/python/framework:config_vgpu_test_2gpu PASSED in 15.3s Stats over 10 runs: max = 15.3s, min = 13.9s, avg = 14.4s, dev = 0.5s //tensorflow/python/framework:config_vgpu_test_cpu PASSED in 7.5s Stats over 10 runs: max = 7.5s, min = 5.0s, avg = 5.9s, dev = 0.7s //tensorflow/python/framework:function_test_cpu PASSED in 70.7s Stats over 10 runs: max = 70.7s, min = 7.5s, avg = 16.3s, dev = 18.7s //tensorflow/python/grappler:cluster_test_cpu PASSED in 7.8s Stats over 10 runs: max = 7.8s, min = 5.3s, avg = 6.7s, dev = 0.9s //tensorflow/python/kernel_tests/array_ops:array_ops_test_cpu PASSED in 16.1s Stats over 10 runs: max = 16.1s, min = 7.8s, avg = 11.0s, dev = 2.5s //tensorflow/python/kernel_tests/array_ops:inplace_ops_test_cpu PASSED in 7.9s Stats over 10 runs: max = 7.9s, min = 6.9s, avg = 7.4s, dev = 0.3s //tensorflow/python/kernel_tests/data_structures:tensor_array_ops_test_cpu PASSED in 10.1s Stats over 10 runs: max = 10.1s, min = 6.9s, avg = 8.3s, dev = 1.0s //tensorflow/python/kernel_tests/linalg:linear_operator_kronecker_test_cpu PASSED in 55.3s Stats over 10 runs: max = 55.3s, min = 43.0s, avg = 47.6s, dev = 3.6s //tensorflow/python/kernel_tests/linalg:linear_operator_low_rank_update_test_cpu PASSED in 111.6s Stats over 10 runs: max = 111.6s, min = 90.6s, avg = 101.6s, dev = 6.4s //tensorflow/python/kernel_tests/linalg:tridiagonal_matmul_op_test_cpu PASSED in 112.4s Stats over 10 runs: max = 112.4s, min = 6.9s, avg = 18.4s, dev = 31.3s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_ops_test_cpu PASSED in 49.8s Stats over 10 runs: max = 49.8s, min = 12.5s, avg = 29.1s, dev = 11.6s //tensorflow/python/kernel_tests/math_ops:segment_reduction_ops_test_cpu PASSED in 67.2s Stats over 10 runs: max = 67.2s, min = 41.7s, avg = 52.5s, dev = 9.5s //tensorflow/python/kernel_tests/nn_ops:pooling_ops_test_cpu PASSED in 57.2s Stats over 10 runs: max = 57.2s, min = 31.0s, avg = 37.8s, dev = 9.6s //tensorflow/python/kernel_tests/nn_ops:rnn_test_cpu PASSED in 11.4s Stats over 10 runs: max = 11.4s, min = 8.7s, avg = 10.2s, dev = 0.8s //tensorflow/python/kernel_tests/random:random_index_shuffle_test PASSED in 14.1s Stats over 10 runs: max = 14.1s, min = 6.2s, avg = 8.3s, dev = 2.1s //tensorflow/python/kernel_tests/random:stateless_random_ops_test_cpu PASSED in 128.7s Stats over 10 runs: max = 128.7s, min = 18.7s, avg = 73.8s, dev = 49.5s //tensorflow/python/ops/ragged:ragged_tensor_supported_values_test PASSED in 15.1s Stats over 10 runs: max = 15.1s, min = 11.6s, avg = 13.2s, dev = 1.2s //tensorflow/python/saved_model:load_test_cpu PASSED in 47.0s Stats over 10 runs: max = 47.0s, min = 21.9s, avg = 29.3s, dev = 6.4s //tensorflow/compiler/tests:fft_test_cpu PASSED in 30.5s Stats over 12 runs: max = 30.5s, min = 12.6s, avg = 21.0s, dev = 7.3s //tensorflow/compiler/xla/service:triangular_solve_expander_test PASSED in 4.9s Stats over 12 runs: max = 4.9s, min = 2.5s, avg = 3.4s, dev = 0.7s //tensorflow/python/data/experimental/kernel_tests:group_by_reducer_test PASSED in 17.2s Stats over 12 runs: max = 17.2s, min = 4.2s, avg = 9.4s, dev = 3.9s //tensorflow/python/data/kernel_tests:choose_from_datasets_test PASSED in 11.5s Stats over 12 runs: max = 11.5s, min = 6.7s, avg = 8.8s, dev = 1.4s //tensorflow/python/data/kernel_tests:memory_cleanup_test_cpu PASSED in 10.0s Stats over 12 runs: max = 10.0s, min = 6.1s, avg = 7.7s, dev = 1.4s //tensorflow/python/distribute:multi_process_runner_test_2gpu PASSED in 222.8s Stats over 12 runs: max = 222.8s, min = 12.8s, avg = 50.2s, dev = 58.0s //tensorflow/python/distribute:multi_process_runner_test_cpu PASSED in 223.6s Stats over 12 runs: max = 223.6s, min = 13.5s, avg = 50.2s, dev = 58.0s //tensorflow/python/eager/polymorphic_function:polymorphic_function_test_cpu PASSED in 19.6s Stats over 15 runs: max = 19.6s, min = 14.0s, avg = 16.2s, dev = 1.5s //tensorflow/python/kernel_tests/linalg:linear_operator_circulant_test_cpu PASSED in 65.5s Stats over 15 runs: max = 65.5s, min = 53.1s, avg = 58.5s, dev = 3.0s //tensorflow/python/kernel_tests/nn_ops:rnn_cell_test_cpu PASSED in 58.1s Stats over 15 runs: max = 58.1s, min = 12.3s, avg = 21.5s, dev = 12.5s //tensorflow/compiler/tests:ftrl_test_cpu PASSED in 9.1s Stats over 16 runs: max = 9.1s, min = 5.7s, avg = 7.2s, dev = 1.2s //tensorflow/compiler/tests:ternary_ops_test_cpu PASSED in 14.2s Stats over 16 runs: max = 14.2s, min = 5.0s, avg = 8.7s, dev = 2.4s //tensorflow/compiler/tests:ternary_ops_test_cpu_mlir_bridge_test PASSED in 8.9s Stats over 16 runs: max = 8.9s, min = 3.8s, avg = 6.2s, dev = 1.8s //tensorflow/python:image_ops_test_cpu PASSED in 22.5s Stats over 16 runs: max = 22.5s, min = 12.6s, avg = 16.5s, dev = 2.6s //tensorflow/python/data/experimental/kernel_tests/service:dynamic_sharding_test PASSED in 32.0s Stats over 16 runs: max = 32.0s, min = 6.4s, avg = 21.0s, dev = 7.1s //tensorflow/python/data/experimental/kernel_tests/service:worker_tags_test PASSED in 26.4s Stats over 16 runs: max = 26.4s, min = 5.9s, avg = 16.0s, dev = 6.8s //tensorflow/python/data/kernel_tests:snapshot_test PASSED in 27.3s Stats over 16 runs: max = 27.3s, min = 10.2s, avg = 17.8s, dev = 4.2s //tensorflow/python/kernel_tests/control_flow:control_flow_ops_py_test_cpu PASSED in 29.1s Stats over 16 runs: max = 29.1s, min = 6.3s, avg = 10.5s, dev = 5.1s //tensorflow/python/kernel_tests/linalg:matrix_exponential_op_test PASSED in 9.2s Stats over 16 runs: max = 9.2s, min = 4.1s, avg = 6.8s, dev = 1.5s //tensorflow/python/kernel_tests/signal:dct_ops_test_cpu PASSED in 17.9s Stats over 16 runs: max = 17.9s, min = 14.9s, avg = 16.3s, dev = 0.8s //tensorflow/python/ops/parallel_for:control_flow_ops_test_cpu PASSED in 55.5s Stats over 16 runs: max = 55.5s, min = 13.3s, avg = 21.9s, dev = 9.5s //tensorflow/python/data/experimental/kernel_tests/service:distributed_save_ft_test PASSED in 12.2s Stats over 17 runs: max = 12.2s, min = 3.8s, avg = 6.7s, dev = 1.9s //tensorflow/python/data/kernel_tests:map_test PASSED in 42.5s Stats over 19 runs: max = 42.5s, min = 13.3s, avg = 21.1s, dev = 6.6s //tensorflow/compiler/tests:pooling_ops_3d_test_cpu PASSED in 7.4s Stats over 20 runs: max = 7.4s, min = 3.9s, avg = 5.7s, dev = 1.1s //tensorflow/compiler/tests:pooling_ops_3d_test_cpu_mlir_bridge_test PASSED in 7.7s Stats over 20 runs: max = 7.7s, min = 4.8s, avg = 6.2s, dev = 0.8s //tensorflow/compiler/tests:pooling_ops_test_cpu PASSED in 11.6s Stats over 20 runs: max = 11.6s, min = 3.9s, avg = 5.9s, dev = 1.7s //tensorflow/compiler/tests:pooling_ops_test_cpu_mlir_bridge_test PASSED in 11.8s Stats over 20 runs: max = 11.8s, min = 3.0s, avg = 5.9s, dev = 2.1s //tensorflow/compiler/xla/tests:convolution_dimension_numbers_test_cpu PASSED in 11.4s Stats over 20 runs: max = 11.4s, min = 9.2s, avg = 10.1s, dev = 0.6s //tensorflow/compiler/xla/tests:dot_operation_single_threaded_runtime_test_cpu PASSED in 17.3s Stats over 20 runs: max = 17.3s, min = 14.7s, avg = 15.9s, dev = 0.7s //tensorflow/compiler/xla/tests:dot_operation_test_cpu PASSED in 21.7s Stats over 20 runs: max = 21.7s, min = 15.7s, avg = 18.1s, dev = 1.6s //tensorflow/compiler/xla/tests:prng_test_cpu PASSED in 16.2s Stats over 20 runs: max = 16.2s, min = 11.4s, avg = 12.8s, dev = 1.1s //tensorflow/compiler/xla/tests:reduce_window_test_cpu PASSED in 43.5s Stats over 20 runs: max = 43.5s, min = 9.4s, avg = 19.3s, dev = 10.5s //tensorflow/python/autograph/tests:loop_control_flow_test PASSED in 23.1s Stats over 20 runs: max = 23.1s, min = 18.3s, avg = 20.7s, dev = 1.4s //tensorflow/python/kernel_tests:metrics_test PASSED in 43.3s Stats over 20 runs: max = 43.3s, min = 7.9s, avg = 20.2s, dev = 9.8s //tensorflow/python/kernel_tests/array_ops:matrix_band_part_op_test_cpu PASSED in 8.4s Stats over 20 runs: max = 8.4s, min = 4.2s, avg = 6.7s, dev = 1.3s //tensorflow/python/kernel_tests/data_structures:barrier_ops_test PASSED in 17.2s Stats over 20 runs: max = 17.2s, min = 3.8s, avg = 7.8s, dev = 4.1s //tensorflow/python/kernel_tests/linalg:eig_op_test PASSED in 43.5s Stats over 20 runs: max = 43.5s, min = 3.3s, avg = 14.1s, dev = 13.7s //tensorflow/python/kernel_tests/linalg:linalg_grad_test_cpu PASSED in 165.6s Stats over 20 runs: max = 165.6s, min = 40.0s, avg = 86.2s, dev = 34.9s //tensorflow/python/kernel_tests/linalg:norm_op_test_cpu PASSED in 7.7s Stats over 20 runs: max = 7.7s, min = 5.4s, avg = 6.8s, dev = 0.7s //tensorflow/python/kernel_tests/linalg:normalize_op_test_cpu PASSED in 18.6s Stats over 20 runs: max = 18.6s, min = 5.5s, avg = 12.3s, dev = 3.3s //tensorflow/python/kernel_tests/linalg:qr_op_test_cpu PASSED in 237.3s Stats over 20 runs: max = 237.3s, min = 37.9s, avg = 107.6s, dev = 58.4s //tensorflow/python/kernel_tests/linalg:self_adjoint_eig_op_test_cpu PASSED in 28.3s Stats over 20 runs: max = 28.3s, min = 5.1s, avg = 12.7s, dev = 7.2s //tensorflow/python/kernel_tests/math_ops:batch_matmul_op_test_cpu PASSED in 28.5s Stats over 20 runs: max = 28.5s, min = 6.4s, avg = 15.8s, dev = 7.6s //tensorflow/python/kernel_tests/math_ops:matmul_op_test_cpu PASSED in 33.6s Stats over 20 runs: max = 33.6s, min = 19.8s, avg = 25.1s, dev = 3.5s //tensorflow/python/kernel_tests/math_ops:tensordot_op_test_cpu PASSED in 89.2s Stats over 20 runs: max = 89.2s, min = 7.3s, avg = 35.1s, dev = 27.5s //tensorflow/python/kernel_tests/nn_ops:embedding_ops_test_cpu PASSED in 27.7s Stats over 20 runs: max = 27.7s, min = 10.4s, avg = 17.4s, dev = 3.6s //tensorflow/python/data/experimental/kernel_tests/service:local_workers_test PASSED in 27.1s Stats over 24 runs: max = 27.1s, min = 9.7s, avg = 17.8s, dev = 4.7s //tensorflow/python/data/kernel_tests:interleave_test PASSED in 34.3s Stats over 24 runs: max = 34.3s, min = 6.7s, avg = 18.0s, dev = 5.9s //tensorflow/python/data/kernel_tests:sample_from_datasets_test PASSED in 24.4s Stats over 24 runs: max = 24.4s, min = 4.1s, avg = 10.8s, dev = 6.3s //tensorflow/compiler/xla/tests:array_elementwise_ops_test_cpu PASSED in 10.6s Stats over 25 runs: max = 10.6s, min = 8.5s, avg = 9.5s, dev = 0.6s //tensorflow/compiler/xla/tests:select_and_scatter_test_cpu PASSED in 38.7s Stats over 25 runs: max = 38.7s, min = 11.7s, avg = 16.4s, dev = 6.7s //tensorflow/compiler/xla/tests:convolution_variants_test_cpu PASSED in 13.4s Stats over 30 runs: max = 13.4s, min = 11.8s, avg = 12.5s, dev = 0.4s //tensorflow/compiler/xla/tests:iota_test_cpu PASSED in 26.0s Stats over 30 runs: max = 26.0s, min = 15.7s, avg = 20.8s, dev = 2.5s //tensorflow/compiler/xla/tests:params_test_cpu PASSED in 11.2s Stats over 30 runs: max = 11.2s, min = 8.9s, avg = 10.0s, dev = 0.6s //tensorflow/compiler/xla/tests:reshape_test_cpu PASSED in 13.1s Stats over 30 runs: max = 13.1s, min = 11.7s, avg = 12.3s, dev = 0.3s //tensorflow/python/kernel_tests/nn_ops:conv_ops_3d_test_cpu PASSED in 20.5s Stats over 30 runs: max = 20.5s, min = 3.3s, avg = 9.3s, dev = 5.1s //tensorflow/compiler/xla/tests:reduce_test_cpu PASSED in 18.1s Stats over 31 runs: max = 18.1s, min = 11.6s, avg = 13.7s, dev = 1.2s //tensorflow/compiler/tests:unary_ops_test_cpu PASSED in 19.3s Stats over 32 runs: max = 19.3s, min = 3.0s, avg = 6.1s, dev = 3.7s //tensorflow/compiler/tests:unary_ops_test_cpu_mlir_bridge_test PASSED in 29.2s Stats over 32 runs: max = 29.2s, min = 3.3s, avg = 8.3s, dev = 5.9s //tensorflow/compiler/xla/tests:scalar_computations_test_cpu PASSED in 16.8s Stats over 32 runs: max = 16.8s, min = 9.8s, avg = 12.9s, dev = 1.6s //tensorflow/python/data/experimental/kernel_tests/service:auto_shard_test PASSED in 19.2s Stats over 32 runs: max = 19.2s, min = 3.7s, avg = 11.3s, dev = 3.9s //tensorflow/python/data/experimental/kernel_tests/service:data_service_ops_test PASSED in 28.3s Stats over 32 runs: max = 28.3s, min = 7.7s, avg = 17.1s, dev = 4.9s //tensorflow/compiler/xla/tests:batch_normalization_test_cpu PASSED in 17.1s Stats over 40 runs: max = 17.1s, min = 11.7s, avg = 14.5s, dev = 1.5s //tensorflow/compiler/xla/tests:bfloat16_test_cpu PASSED in 18.3s Stats over 40 runs: max = 18.3s, min = 10.3s, avg = 12.7s, dev = 1.9s //tensorflow/compiler/xla/tests:conv_depthwise_backprop_filter_test_cpu PASSED in 18.5s Stats over 40 runs: max = 18.5s, min = 9.8s, avg = 13.8s, dev = 2.4s //tensorflow/compiler/xla/tests:slice_test_cpu PASSED in 15.8s Stats over 40 runs: max = 15.8s, min = 10.8s, avg = 13.4s, dev = 1.1s //tensorflow/core/kernels:stochastic_cast_op_test PASSED in 3.2s Stats over 48 runs: max = 3.2s, min = 0.6s, avg = 1.3s, dev = 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/python:quantize_model_test PASSED in 64.0s Stats over 50 runs: max = 64.0s, min = 21.1s, avg = 36.8s, dev = 12.1s //tensorflow/compiler/tests:sort_ops_test_cpu PASSED in 39.9s Stats over 50 runs: max = 39.9s, min = 2.8s, avg = 10.2s, dev = 8.0s //tensorflow/compiler/tests:sort_ops_test_cpu_mlir_bridge_test PASSED in 40.4s Stats over 50 runs: max = 40.4s, min = 3.0s, avg = 10.5s, dev = 7.8s //tensorflow/compiler/xla/tests:conv_depthwise_test_cpu PASSED in 18.0s Stats over 50 runs: max = 18.0s, min = 10.1s, avg = 13.2s, dev = 1.9s //tensorflow/compiler/xla/tests:convolution_test_1d_no_vmodule_cpu PASSED in 22.3s Stats over 50 runs: max = 22.3s, min = 15.3s, avg = 19.6s, dev = 1.5s //tensorflow/compiler/xla/tests:convolution_test_cpu PASSED in 25.2s Stats over 50 runs: max = 25.2s, min = 12.6s, avg = 19.4s, dev = 2.5s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_dense_mat_mul_grad_test_cpu PASSED in 16.2s Stats over 50 runs: max = 16.2s, min = 4.8s, avg = 9.6s, dev = 3.0s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_grad_test_cpu PASSED in 9.2s Stats over 50 runs: max = 9.2s, min = 3.5s, avg = 5.9s, dev = 1.6s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_sparse_mat_mul_grad_test_cpu PASSED in 8.3s Stats over 50 runs: max = 8.3s, min = 3.7s, avg = 5.0s, dev = 1.2s //tensorflow/python/kernel_tests/math_ops:cwise_ops_binary_test_cpu PASSED in 30.2s Stats over 50 runs: max = 30.2s, min = 7.1s, avg = 15.4s, dev = 6.1s //tensorflow/python/kernel_tests/math_ops:cwise_ops_test_cpu PASSED in 20.4s Stats over 50 runs: max = 20.4s, min = 3.4s, avg = 8.9s, dev = 3.4s //tensorflow/python/kernel_tests/math_ops:cwise_ops_unary_test_cpu PASSED in 12.8s Stats over 50 runs: max = 12.8s, min = 3.0s, avg = 5.1s, dev = 2.5s Executed 3783 out of 3783 tests: 3783 tests pass. There were tests whose specified size is too big. Use the --test_verbose_timeout_warnings command line option to see which ones these are.