==================== Test output for //tensorflow/dtensor/python/tests:input_util_test (shard 1 of 8): Running tests under Python 3.11.3: /usr/local/bin/python3 [ RUN ] DTensorDatasetTest.testForInIterationEager I0525 22:38:24.022357 281473587049344 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:24.022588 281473587049344 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:24.022748 281473587049344 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:24.023302 281473587049344 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:24.023495 281473587049344 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'] /usr/local/lib/python3.11/dist-packages/google/protobuf/message_factory.py:166: UserWarning: MessageFactory class is deprecated. Please use GetMessageClass() instead of MessageFactory.GetPrototype. MessageFactory class will be removed after 2024. warnings.warn('MessageFactory class is deprecated. Please use ' 2023-05-25 22:38:24.443793: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:24.514274: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:24.561899: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:24.608766: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:25.928444: E tensorflow/dtensor/cc/dtensor_device.cc:2213] Encountered error while executing function: CopyToMesh__func_18130263970634465464_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_6397550668954835598_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. 2023-05-25 22:38:25.928736: E tensorflow/dtensor/cc/dtensor_device.cc:2247] Error executing CopyToMesh {{function_node IteratorGetNext__func_6397550668954835598_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. [ FAILED ] DTensorDatasetTest.testForInIterationEager INFO:tensorflow:time(__main__.DTensorDatasetTest.testForInIterationEager): 2.12s I0525 22:38:26.142986 281473587049344 test_util.py:2464] time(__main__.DTensorDatasetTest.testForInIterationEager): 2.12s [ RUN ] DTensorDatasetTest.testIterOnBatchedDatasetGraph I0525 22:38:26.144403 281473587049344 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:26.144587 281473587049344 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:26.144775 281473587049344 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:26.145245 281473587049344 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:26.145372 281473587049344 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'] 2023-05-25 22:38:26.549051: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:26.624377: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:26.699584: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:26.769412: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:28.252519: I tensorflow/dtensor/cc/dtensor_device.cc:1574] DTensor cache key lookup missed for __inference_train_619. DTensor is (re-)computing its SPMD transformation. 2023-05-25 22:38:28.260123: I tensorflow/dtensor/cc/dtensor_device.cc:1644] DTensor cache key lookup missed for __inference_train_619. DTensor is (re-)computing its ExecutionFunctions. INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterOnBatchedDatasetGraph): 3.09s I0525 22:38:29.231852 281473587049344 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterOnBatchedDatasetGraph): 3.09s [ OK ] DTensorDatasetTest.testIterOnBatchedDatasetGraph [ RUN ] DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True) I0525 22:38:29.233235 281473587049344 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:29.233379 281473587049344 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:29.233512 281473587049344 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:29.233931 281473587049344 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:29.234050 281473587049344 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'] 2023-05-25 22:38:29.467259: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True)): 2.34s I0525 22:38:31.574288 281473587049344 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True)): 2.34s [ 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) I0525 22:38:31.576055 281473587049344 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:31.576207 281473587049344 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:31.576343 281473587049344 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:31.576814 281473587049344 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:31.576937 281473587049344 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'] 2023-05-25 22:38:31.880908: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:31.940743: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:31.998197: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:32.055340: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts17 (images_sharding=['batch', 'height', 'width', 'unsharded'], labels_sharding=['batch', 'unsharded'], is_graph=False, through_dtensor=True)): 1.73s I0525 22:38:33.309836 281473587049344 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts17 (images_sharding=['batch', 'height', 'width', 'unsharded'], labels_sharding=['batch', 'unsharded'], is_graph=False, through_dtensor=True)): 1.73s [ 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) I0525 22:38:33.311142 281473587049344 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:33.311268 281473587049344 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:33.311400 281473587049344 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:33.311802 281473587049344 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:33.311923 281473587049344 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'] 2023-05-25 22:38:33.508424: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:35.823291: I tensorflow/dtensor/cc/dtensor_device.cc:1574] DTensor cache key lookup missed for __inference_train_1463. DTensor is (re-)computing its SPMD transformation. 2023-05-25 22:38:35.831193: I tensorflow/dtensor/cc/dtensor_device.cc:1644] DTensor cache key lookup missed for __inference_train_1463. DTensor is (re-)computing its ExecutionFunctions. INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True)): 3.4s I0525 22:38:36.712224 281473587049344 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True)): 3.4s [ OK ] DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True) [ RUN ] DTensorDatasetTest.testMixedLayoutsFails I0525 22:38:36.713740 281473587049344 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:36.713880 281473587049344 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:36.714017 281473587049344 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:36.714424 281473587049344 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:36.714550 281473587049344 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): 0.31s I0525 22:38:37.025748 281473587049344 test_util.py:2464] time(__main__.DTensorDatasetTest.testMixedLayoutsFails): 0.31s [ OK ] DTensorDatasetTest.testMixedLayoutsFails [ RUN ] InputUtilHelpersTest.testShardCounts1 (mesh_dims=[('batch', 8)], layout_specs=['batch'], batch_dim=None, counts=[8]) I0525 22:38:37.027058 281473587049344 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:37.027188 281473587049344 mesh_util.py:36] Number of global CPU devices: 8 I0525 22:38:37.027314 281473587049344 mesh_util.py:39] Global device IDs: [0 1 2 3 4 5 6 7] I0525 22:38:37.027623 281473587049344 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7] I0525 22:38:37.027740 281473587049344 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 I0525 22:38:37.028168 281473587049344 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 356, 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_5735373847289228717_13230101824050524202_2386512056599665587_2}} Function was cancelled before it was started ---------------------------------------------------------------------- Ran 7 tests in 13.008s FAILED (errors=1) ================================================================================ ==================== Test output for //tensorflow/dtensor/python/tests:input_util_test (shard 1 of 8): Running tests under Python 3.11.3: /usr/local/bin/python3 [ RUN ] DTensorDatasetTest.testForInIterationEager I0525 22:38:40.996731 281473738109824 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:40.996991 281473738109824 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:40.997172 281473738109824 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:40.997795 281473738109824 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:40.998008 281473738109824 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'] /usr/local/lib/python3.11/dist-packages/google/protobuf/message_factory.py:166: UserWarning: MessageFactory class is deprecated. Please use GetMessageClass() instead of MessageFactory.GetPrototype. MessageFactory class will be removed after 2024. warnings.warn('MessageFactory class is deprecated. Please use ' 2023-05-25 22:38:41.365955: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:41.426169: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:41.487678: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:41.540848: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:43.796438: E tensorflow/dtensor/cc/dtensor_device.cc:2213] Encountered error while executing function: CopyToMesh__func_9914779654734794765_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_5038403174660240266_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. 2023-05-25 22:38:43.796821: E tensorflow/dtensor/cc/dtensor_device.cc:2247] Error executing CopyToMesh {{function_node IteratorGetNext__func_5038403174660240266_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. [ FAILED ] DTensorDatasetTest.testForInIterationEager INFO:tensorflow:time(__main__.DTensorDatasetTest.testForInIterationEager): 2.93s I0525 22:38:43.925961 281473738109824 test_util.py:2464] time(__main__.DTensorDatasetTest.testForInIterationEager): 2.93s [ RUN ] DTensorDatasetTest.testIterOnBatchedDatasetGraph I0525 22:38:43.927399 281473738109824 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:43.927589 281473738109824 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:43.927774 281473738109824 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:43.928242 281473738109824 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:43.928368 281473738109824 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'] 2023-05-25 22:38:44.225508: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:44.293219: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:44.362690: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:44.430899: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:46.342682: I tensorflow/dtensor/cc/dtensor_device.cc:1574] DTensor cache key lookup missed for __inference_train_619. DTensor is (re-)computing its SPMD transformation. 2023-05-25 22:38:46.380249: I tensorflow/dtensor/cc/dtensor_device.cc:1644] DTensor cache key lookup missed for __inference_train_619. DTensor is (re-)computing its ExecutionFunctions. INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterOnBatchedDatasetGraph): 3.45s I0525 22:38:47.379354 281473738109824 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterOnBatchedDatasetGraph): 3.45s [ OK ] DTensorDatasetTest.testIterOnBatchedDatasetGraph [ RUN ] DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True) I0525 22:38:47.380959 281473738109824 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:47.381095 281473738109824 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:47.381227 281473738109824 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:47.381642 281473738109824 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:47.381766 281473738109824 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'] 2023-05-25 22:38:47.608371: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True)): 2.61s I0525 22:38:49.991616 281473738109824 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts1 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=False, through_dtensor=True)): 2.61s [ 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) I0525 22:38:49.993055 281473738109824 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:49.993196 281473738109824 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:49.993330 281473738109824 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:49.993771 281473738109824 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:49.993896 281473738109824 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'] 2023-05-25 22:38:50.208843: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:50.277921: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:50.345005: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:50.405959: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts17 (images_sharding=['batch', 'height', 'width', 'unsharded'], labels_sharding=['batch', 'unsharded'], is_graph=False, through_dtensor=True)): 2.15s I0525 22:38:52.138153 281473738109824 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts17 (images_sharding=['batch', 'height', 'width', 'unsharded'], labels_sharding=['batch', 'unsharded'], is_graph=False, through_dtensor=True)): 2.15s [ 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) I0525 22:38:52.140084 281473738109824 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:52.140270 281473738109824 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:52.140410 281473738109824 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:52.140862 281473738109824 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:52.140992 281473738109824 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'] 2023-05-25 22:38:52.529712: I tensorflow/core/grappler/optimizers/data/replicate_on_split.cc:32] Running replicate on split optimization 2023-05-25 22:38:54.017820: I tensorflow/dtensor/cc/dtensor_device.cc:1574] DTensor cache key lookup missed for __inference_train_1463. DTensor is (re-)computing its SPMD transformation. 2023-05-25 22:38:54.026076: I tensorflow/dtensor/cc/dtensor_device.cc:1644] DTensor cache key lookup missed for __inference_train_1463. DTensor is (re-)computing its ExecutionFunctions. INFO:tensorflow:time(__main__.DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True)): 2.69s I0525 22:38:54.832423 281473738109824 test_util.py:2464] time(__main__.DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True)): 2.69s [ OK ] DTensorDatasetTest.testIterWithLayouts3 (images_sharding=['unsharded', 'unsharded', 'unsharded', 'unsharded'], labels_sharding=['unsharded', 'unsharded'], is_graph=True, through_dtensor=True) [ RUN ] DTensorDatasetTest.testMixedLayoutsFails I0525 22:38:54.834289 281473738109824 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:54.834440 281473738109824 mesh_util.py:36] Number of global CPU devices: 16 I0525 22:38:54.834576 281473738109824 mesh_util.py:39] Global device IDs: [[[ 0 1] [ 2 3]] [[ 4 5] [ 6 7]] [[ 8 9] [10 11]] [[12 13] [14 15]]] I0525 22:38:54.835016 281473738109824 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] I0525 22:38:54.835144 281473738109824 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): 0.43s I0525 22:38:55.262356 281473738109824 test_util.py:2464] time(__main__.DTensorDatasetTest.testMixedLayoutsFails): 0.43s [ OK ] DTensorDatasetTest.testMixedLayoutsFails [ RUN ] InputUtilHelpersTest.testShardCounts1 (mesh_dims=[('batch', 8)], layout_specs=['batch'], batch_dim=None, counts=[8]) I0525 22:38:55.264268 281473738109824 mesh_util.py:35] This is client 0 of 1 clients I0525 22:38:55.264493 281473738109824 mesh_util.py:36] Number of global CPU devices: 8 I0525 22:38:55.264658 281473738109824 mesh_util.py:39] Global device IDs: [0 1 2 3 4 5 6 7] I0525 22:38:55.265054 281473738109824 mesh_util.py:40] Local device IDs: [0, 1, 2, 3, 4, 5, 6, 7] I0525 22:38:55.265199 281473738109824 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 I0525 22:38:55.265829 281473738109824 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 356, 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_8239727039202768993_13230101824050524202_2386512056599665587_2}} Function was cancelled before it was started ---------------------------------------------------------------------- Ran 7 tests in 14.271s FAILED (errors=1) ================================================================================ ==================== Test output for //tensorflow/python/distribute/failure_handling:gce_failure_handler_test (shard 7 of 8): Running tests under Python 3.11.3: /usr/local/bin/python3 [ RUN ] GceFailureHandlingTest.test_basic_run_test_inputarg_manager_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 34685 I0525 22:42:21.539898 281473778480000 test_util.py:3796] Using local port 34685 INFO:tensorflow:Using local port 36651 I0525 22:42:21.540449 281473778480000 test_util.py:3796] Using local port 36651 INFO:tensorflow:Using local port 33227 I0525 22:42:21.540764 281473778480000 test_util.py:3796] Using local port 33227 INFO:tensorflow:Using local port 41107 I0525 22:42:21.541067 281473778480000 test_util.py:3796] Using local port 41107 INFO:tensorflow:Cluster starting. I0525 22:42:26.296987 281473778480000 gce_failure_handler_test.py:317] Cluster starting. [worker-0]: I0525 22:42:26.739753 281473864070016 multi_process_runner.py:840] Subprocess with PID 2422526 (worker, 0) is now being started. [worker-1]: I0525 22:42:26.774580 281473864070016 multi_process_runner.py:840] Subprocess with PID 2422615 (worker, 1) is now being started. [worker-0]: I0525 22:42:26.740230 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:34685", "localhost:36651", "localhost:33227", "localhost:41107"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:42:26.788097 281473864070016 multi_process_runner.py:840] Subprocess with PID 2422735 (worker, 2) is now being started. [worker-3]: I0525 22:42:26.794722 281473864070016 multi_process_runner.py:840] Subprocess with PID 2422799 (worker, 3) is now being started. [worker-1]: I0525 22:42:26.775104 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:34685", "localhost:36651", "localhost:33227", "localhost:41107"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:42:26.795289 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:34685", "localhost:36651", "localhost:33227", "localhost:41107"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:42:26.788651 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:34685", "localhost:36651", "localhost:33227", "localhost:41107"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-1]: E0525 22:42:26.892207014 2422615 server_chttp2.cc:40] {"created":"@1685054546.892014655","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":"@1685054546.892009304","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":"@1685054546.891976731","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":"@1685054546.891959214","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":"@1685054546.892008144","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":"@1685054546.891999848","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]: 2023-05-25 22:42:26.892361: E tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:608] UNKNOWN: Could not start gRPC server [worker-1]: 2023-05-25 22:42:26.896557: E tensorflow/core/common_runtime/eager/context_distributed_manager.cc:699] Could not start gRPC server [worker-1]: Process _Process-3: [worker-3]: 2023-05-25 22:42:26.956080: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:41107 [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.11/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]: ^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^ [worker-1]: File "/usr/lib/python3.11/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]: ^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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-2]: 2023-05-25 22:42:26.967945: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:33227 [worker-0]: 2023-05-25 22:42:27.024170: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:34685 [worker-0]: 2023-05-25 22:42:27.040522: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 10363075658618555006 [worker-0]: 2023-05-25 22:42:27.044360: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 12674033651634518391 [worker-0]: 2023-05-25 22:42:27.044559: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-2]: 2023-05-25 22:42:27.046391: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:42:27.077506: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 3138768377646139069 [worker-3]: 2023-05-25 22:42:27.078347: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. INFO:tensorflow:restarting workers I0525 22:42:56.687191 281473778480000 gce_failure_handler_test.py:323] restarting workers INFO:tensorflow:workers restarted I0525 22:42:56.806235 281473778480000 gce_failure_handler_test.py:327] workers restarted [worker-1]: I0525 22:42:56.828250 281473864070016 multi_process_runner.py:840] Subprocess with PID 2492246 (worker, 1) is now being started. [worker-0]: I0525 22:42:56.829699 281473864070016 multi_process_runner.py:840] Subprocess with PID 2492241 (worker, 0) is now being started. [worker-1]: I0525 22:42:56.828677 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:34685", "localhost:36651", "localhost:33227", "localhost:41107"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-0]: I0525 22:42:56.830081 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:34685", "localhost:36651", "localhost:33227", "localhost:41107"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:42:56.831962 281473864070016 multi_process_runner.py:840] Subprocess with PID 2492250 (worker, 2) is now being started. [worker-3]: I0525 22:42:56.838414 281473864070016 multi_process_runner.py:840] Subprocess with PID 2492387 (worker, 3) is now being started. [worker-2]: I0525 22:42:56.832335 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:34685", "localhost:36651", "localhost:33227", "localhost:41107"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:42:56.838836 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:34685", "localhost:36651", "localhost:33227", "localhost:41107"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: E0525 22:42:56.854015528 2492250 server_chttp2.cc:40] {"created":"@1685054576.853864108","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":"@1685054576.853859622","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":"@1685054576.853830264","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":"@1685054576.853815297","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":"@1685054576.853858442","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":"@1685054576.853850926","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]: 2023-05-25 22:42:56.854150: E tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:608] UNKNOWN: Could not start gRPC server [worker-0]: E0525 22:42:56.900776817 2492241 server_chttp2.cc:40] {"created":"@1685054576.900627947","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":"@1685054576.900623371","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":"@1685054576.900594503","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":"@1685054576.900580127","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":"@1685054576.900622241","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":"@1685054576.900615425","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]: 2023-05-25 22:42:56.900903: E tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:608] UNKNOWN: Could not start gRPC server [worker-3]: E0525 22:42:56.879479927 2492387 server_chttp2.cc:40] {"created":"@1685054576.879331326","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":"@1685054576.879326401","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":"@1685054576.879296993","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":"@1685054576.879283061","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":"@1685054576.879325431","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":"@1685054576.879318050","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-3]: 2023-05-25 22:42:56.879620: E tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:608] UNKNOWN: Could not start gRPC server [worker-0]: 2023-05-25 22:42:56.957640: E tensorflow/core/common_runtime/eager/context_distributed_manager.cc:699] Could not start gRPC server [worker-1]: 2023-05-25 22:42:56.990684: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:36651 [worker-3]: 2023-05-25 22:42:57.008334: E tensorflow/core/common_runtime/eager/context_distributed_manager.cc:699] Could not start gRPC server [worker-0]: 2023-05-25 22:42:57.049742: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 12846756812100227291 [worker-1]: 2023-05-25 22:42:57.053565: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] 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]: I0525 22:42:57.076790 281473864070016 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]: I0525 22:42:57.097350 281473864070016 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]: I0525 22:42:57.104067 281473864070016 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]: I0525 22:42:57.114073 281473864070016 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]: I0525 22:42:57.152514 281473864070016 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]: I0525 22:42:57.153041 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:34685', 'localhost:36651', 'localhost:33227', 'localhost:41107']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:42:57.153226 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:34685', 'localhost:36651', 'localhost:33227', 'localhost:41107']}, 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-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0525 22:42:57.204920 281473864070016 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]: I0525 22:42:57.205387 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:34685', 'localhost:36651', 'localhost:33227', 'localhost:41107']}, 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]: I0525 22:42:57.188047 281473864070016 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]: I0525 22:42:57.188503 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:34685', 'localhost:36651', 'localhost:33227', 'localhost:41107']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:42:57.188691 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:34685', 'localhost:36651', 'localhost:33227', 'localhost:41107']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:42:57.205572 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:34685', 'localhost:36651', 'localhost:33227', 'localhost:41107']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: Process _Process-6: [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.11/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]: ^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^ [worker-0]: File "/usr/lib/python3.11/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]: ^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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-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-1]: I0525 22:42:57.202332 281473864070016 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]: I0525 22:42:57.340373 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:34685', 'localhost:36651', 'localhost:33227', 'localhost:41107']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:42:57.340589 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:34685', 'localhost:36651', 'localhost:33227', 'localhost:41107']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: Process _Process-9: [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.11/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]: ^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^ [worker-3]: File "/usr/lib/python3.11/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]: ^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0525 22:42:57.585868 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: I0525 22:42:57.576993 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: I0525 22:42:57.585484 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0525 22:42:57.596655 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-0]: I0525 22:42:57.596531 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0525 22:42:57.598459 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0525 22:42:57.616731 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-0]: I0525 22:42:57.616313 281473864070016 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:PreemptionCheckpointHandler initialized or restored. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: I0525 22:42:57.617353 281473864070016 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: W0525 22:42:57.616681 281473864070016 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]: 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]: Instructions for updating: [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: W0525 22:42:57.617702 281473864070016 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]: I0525 22:42:57.617866 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0525 22:42:57.621230 281473864070016 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]: W0525 22:42:57.621560 281473864070016 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]: I0525 22:42:57.621712 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: INFO:tensorflow:Start training at 0 [worker-0]: I0525 22:42:57.616837 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: INFO:tensorflow:['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-0]: I0525 22:42:57.667195 281473864070016 gce_failure_handler_test.py:203] ['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0525 22:42:57.676251 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0525 22:42:57.696538 281473864070016 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]: W0525 22:42:57.696880 281473864070016 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]: I0525 22:42:57.697036 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: INFO:tensorflow:['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-1]: I0525 22:42:57.707429 281473864070016 gce_failure_handler_test.py:203] ['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-2]: INFO:tensorflow:['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-2]: I0525 22:42:57.812211 281473864070016 gce_failure_handler_test.py:203] ['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-3]: INFO:tensorflow:['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-3]: I0525 22:42:57.863773 281473864070016 gce_failure_handler_test.py:203] ['workertemp_2', 'workertemp_3', 'workertemp_1'] [worker-2]: 2023-05-25 22:42:57.932222: E tensorflow/core/common_runtime/eager/context_distributed_manager.cc:699] Could not start gRPC server [worker-1]: Process _Process-7: [worker-0]: Process _Process-2: [worker-0]: Traceback (most recent call last): [worker-1]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap [worker-2]: Process _Process-4: [worker-0]: self.run() [worker-1]: File "/usr/lib/python3.11/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/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-1]: self.run() [worker-0]: return self._actual_run() [worker-3]: Process _Process-5: [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-0]: ^^^^^^^^^^^^^^^^^^ [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/multi_process_lib.py", line 54, in _run_with_absl [worker-1]: return self._actual_run() [worker-0]: app.run(lambda _: self._run_impl()) [worker-2]: File "/usr/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap [worker-1]: ^^^^^^^^^^^^^^^^^^ [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-2]: 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_lib.py", line 54, in _run_with_absl [worker-3]: Traceback (most recent call last): [worker-0]: _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/org_tensorflow/tensorflow/python/distribute/multi_process_runner.py", line 755, in _run_with_setenv [worker-2]: return self._actual_run() [worker-2]: ^^^^^^^^^^^^^^^^^^ [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-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-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-3]: File "/usr/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap [worker-0]: sys.exit(main(argv)) [worker-2]: _run_main(main, args) [worker-0]: ^^^^^^^^^^ [worker-3]: 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/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 [worker-2]: 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_runner.py", line 755, in _run_with_setenv [worker-0]: app.run(lambda _: self._run_impl()) [worker-1]: app.run(lambda _: self._run_impl()) [worker-2]: ^^^^^^^^^^ [worker-3]: 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 312, in run [worker-0]: ^^^^^^^^^^^^^^^^ [worker-3]: ^^^^^^^^^^^^^^^^^^ [worker-1]: _run_main(main, args) [worker-0]: File "/usr/lib/python3.11/multiprocessing/process.py", line 108, in 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 [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-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]: self._target(*self._args, **self._kwargs) [worker-2]: app.run(lambda _: self._run_impl()) [worker-1]: 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_runner.py", line 866, in __call__ [worker-3]: app.run(lambda _: self._run_impl()) [worker-2]: ^^^^^^^^^^^^^^^^ [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]: six.reraise(*info.exc_info) [worker-3]: _run_main(main, args) [worker-2]: File "/usr/lib/python3.11/multiprocessing/process.py", line 108, in run [worker-2]: self._target(*self._args, **self._kwargs) [worker-1]: ^^^^^^^^^^ [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-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-3]: sys.exit(main(argv)) [worker-3]: ^^^^^^^^^^ [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/six_archive/six.py", line 719, in reraise [worker-1]: app.run(lambda _: self._run_impl()) [worker-0]: raise value [worker-2]: six.reraise(*info.exc_info) [worker-1]: ^^^^^^^^^^^^^^^^ [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-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]: Process _Process-8: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.11/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]: ^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^ [worker-2]: File "/usr/lib/python3.11/multiprocessing/process.py", line 108, in run [worker-0]: return_value = fn(*args, **kwargs) [worker-1]: File "/usr/lib/python3.11/multiprocessing/process.py", line 108, in run [worker-2]: raise value [worker-1]: 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 1060, in _run_contained [worker-0]: ^^^^^^^^^^^^^^^^^^^ [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/failure_handling/gce_failure_handler_test.py", line 211, in worker_fn [worker-2]: 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/multi_process_lib.py", line 54, in [worker-0]: self.assertNotEmpty(checkpoint_index) [worker-1]: six.reraise(*info.exc_info) [worker-2]: ^^^^^^^^^^^^^^^^^^^ [worker-3]: 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/testing/absltest.py", line 972, in assertNotEmpty [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-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-3]: ^^^^^^^^^^^^^^^^ [worker-1]: raise value [worker-0]: self.fail('{!r} has length of 0.'.format(container), msg) [worker-2]: self.assertNotEmpty(checkpoint_index) [worker-3]: File "/usr/lib/python3.11/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/testing/absltest.py", line 1814, in fail [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-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-3]: self._target(*self._args, **self._kwargs) [worker-1]: return_value = fn(*args, **kwargs) [worker-0]: return super(TestCase, self).fail(self._formatMessage(prefix, msg)) [worker-2]: 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 866, in __call__ [worker-3]: 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/absl_py/absl/testing/absltest.py", line 1814, in fail [worker-1]: ^^^^^^^^^^^^^^^^^^^ [worker-0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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-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-2]: return super(TestCase, self).fail(self._formatMessage(prefix, msg)) [worker-0]: File "/usr/lib/python3.11/unittest/case.py", line 703, in fail [worker-3]: raise value [worker-1]: self.assertNotEmpty(checkpoint_index) [worker-2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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-0]: raise self.failureException(msg) [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-2]: File "/usr/lib/python3.11/unittest/case.py", line 703, in fail [worker-3]: return_value = fn(*args, **kwargs) [worker-0]: AssertionError: [] has length of 0. [worker-1]: self.fail('{!r} has length of 0.'.format(container), msg) [worker-2]: raise self.failureException(msg) [worker-3]: ^^^^^^^^^^^^^^^^^^^ [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-2]: AssertionError: [] has length of 0. [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-1]: return super(TestCase, self).fail(self._formatMessage(prefix, msg)) [worker-3]: self.assertNotEmpty(checkpoint_index) [worker-1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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-1]: File "/usr/lib/python3.11/unittest/case.py", line 703, in fail [worker-1]: 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/testing/absltest.py", line 1814, in fail [worker-1]: AssertionError: [] has length of 0. [worker-3]: return super(TestCase, self).fail(self._formatMessage(prefix, msg)) [worker-3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [worker-3]: File "/usr/lib/python3.11/unittest/case.py", line 703, in fail [worker-3]: raise self.failureException(msg) [worker-3]: AssertionError: [] has length of 0. [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]: ^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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 I0525 22:42:58.602715 281473778480000 multi_process_runner.py:646] worker-0 exit code: 1 I0525 22:42:58.602993 281473778480000 multi_process_runner.py:646] worker-1 exit code: 1 I0525 22:42:58.603110 281473778480000 multi_process_runner.py:646] worker-2 exit code: 1 I0525 22:42:58.603218 281473778480000 multi_process_runner.py:646] worker-3 exit code: 1 [ FAILED ] GceFailureHandlingTest.test_basic_run_test_inputarg_manager_strategyoption_MWMSmultiworker INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_basic_run_test_inputarg_manager_strategyoption_MWMSmultiworker): 37.17s I0525 22:42:58.704212 281473778480000 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_basic_run_test_inputarg_manager_strategyoption_MWMSmultiworker): 37.17s [ RUN ] GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_False_inputarg_manager_strategyoption_MWMSmultiworker INFO:tensorflow:Using MirroredStrategy with devices ('/device:CPU:0',) I0525 22:42:59.013665 281473778480000 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 I0525 22:42:59.014130 281473778480000 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. I0525 22:42:59.044705 281473778480000 failure_handling.py:683] Start polling for termination signal. INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. I0525 22:42:59.093993 281473778480000 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. W0525 22:42:59.094396 281473778480000 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 I0525 22:42:59.094565 281473778480000 gce_failure_handler_test.py:194] Start training at 0 WARNING:tensorflow:5 out of the last 5 calls to .wrapped_fn at 0xffff0d7baa20> 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. W0525 22:42:59.437375 281473778480000 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff0d7baa20> 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 0xffff0d7b9da0> 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. W0525 22:42:59.464064 281473778480000 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff0d7b9da0> 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 I0525 22:42:59.464422 281473778480000 gce_failure_handler_test.py:192] epoch 0 finished INFO:tensorflow:epoch 1 finished I0525 22:42:59.661389 281473778480000 gce_failure_handler_test.py:192] epoch 1 finished INFO:tensorflow:epoch 2 finished I0525 22:43:00.036413 281473778480000 gce_failure_handler_test.py:192] epoch 2 finished INFO:tensorflow:epoch 3 finished I0525 22:43:00.354342 281473778480000 gce_failure_handler_test.py:192] epoch 3 finished INFO:tensorflow:epoch 4 finished I0525 22:43:01.014267 281473778480000 gce_failure_handler_test.py:192] epoch 4 finished INFO:tensorflow:Training finished. I0525 22:43:01.014570 281473778480000 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_False_inputarg_manager_strategyoption_MWMSmultiworker): 2.32s I0525 22:43:01.025187 281473778480000 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_False_inputarg_manager_strategyoption_MWMSmultiworker): 2.32s [ OK ] GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_False_inputarg_manager_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_True_inputarg_manager_strategyoption_MWMSmultiworker INFO:tensorflow:Using MirroredStrategy with devices ('/device:CPU:0',) I0525 22:43:01.141259 281473778480000 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 I0525 22:43:01.141642 281473778480000 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. I0525 22:43:01.166545 281473778480000 failure_handling.py:683] Start polling for termination signal. INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. I0525 22:43:01.167088 281473778480000 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. INFO:tensorflow:Start training at 0 I0525 22:43:01.167338 281473778480000 gce_failure_handler_test.py:194] Start training at 0 INFO:tensorflow:epoch 0 finished I0525 22:43:01.562931 281473778480000 gce_failure_handler_test.py:192] epoch 0 finished INFO:tensorflow:epoch 1 finished I0525 22:43:02.048478 281473778480000 gce_failure_handler_test.py:192] epoch 1 finished INFO:tensorflow:epoch 2 finished I0525 22:43:02.472519 281473778480000 gce_failure_handler_test.py:192] epoch 2 finished INFO:tensorflow:epoch 3 finished I0525 22:43:02.793702 281473778480000 gce_failure_handler_test.py:192] epoch 3 finished INFO:tensorflow:epoch 4 finished I0525 22:43:03.070318 281473778480000 gce_failure_handler_test.py:192] epoch 4 finished INFO:tensorflow:Training finished. I0525 22:43:03.070640 281473778480000 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:time(__main__.GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_True_inputarg_manager_strategyoption_MWMSmultiworker): 2.05s I0525 22:43:03.075247 281473778480000 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_True_inputarg_manager_strategyoption_MWMSmultiworker): 2.05s [ OK ] GceFailureHandlingTest.test_grace_period_continue_training_test_apiwrappingtrain_True_inputarg_manager_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_0_inputarg_manager_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 37039 I0525 22:43:03.079149 281473778480000 test_util.py:3796] Using local port 37039 INFO:tensorflow:Using local port 45015 I0525 22:43:03.079480 281473778480000 test_util.py:3796] Using local port 45015 INFO:tensorflow:Using local port 33141 I0525 22:43:03.079767 281473778480000 test_util.py:3796] Using local port 33141 INFO:tensorflow:Using local port 34463 I0525 22:43:03.080054 281473778480000 test_util.py:3796] Using local port 34463 INFO:tensorflow:Cluster starting. I0525 22:43:03.741363 281473778480000 gce_failure_handler_test.py:405] Cluster starting. [worker-0]: I0525 22:43:03.947742 281473864070016 multi_process_runner.py:840] Subprocess with PID 2510853 (worker, 0) is now being started. [worker-0]: I0525 22:43:03.948207 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:37039", "localhost:45015", "localhost:33141", "localhost:34463"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0525 22:43:04.257516 281473864070016 multi_process_runner.py:840] Subprocess with PID 2510895 (worker, 1) is now being started. [worker-0]: 2023-05-25 22:43:04.278178: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:37039 [worker-0]: 2023-05-25 22:43:04.298232: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 10838048914353471866 [worker-0]: 2023-05-25 22:43:04.299007: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-1]: I0525 22:43:04.258012 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:37039", "localhost:45015", "localhost:33141", "localhost:34463"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:43:04.348055 281473864070016 multi_process_runner.py:840] Subprocess with PID 2510905 (worker, 2) is now being started. [worker-3]: I0525 22:43:04.369838 281473864070016 multi_process_runner.py:840] Subprocess with PID 2510923 (worker, 3) is now being started. [worker-2]: I0525 22:43:04.348620 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:37039", "localhost:45015", "localhost:33141", "localhost:34463"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:43:04.370403 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:37039", "localhost:45015", "localhost:33141", "localhost:34463"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-25 22:43:04.548927: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:45015 [worker-0]: 2023-05-25 22:43:04.566893: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 7890935507765262904 [worker-1]: 2023-05-25 22:43:04.586523: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-2]: 2023-05-25 22:43:04.627035: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:33141 [worker-0]: 2023-05-25 22:43:04.630652: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 7613339233746557579 [worker-2]: 2023-05-25 22:43:04.632005: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-3]: 2023-05-25 22:43:04.717027: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:34463 [worker-0]: 2023-05-25 22:43:04.739573: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 9756866357561419890 [worker-3]: 2023-05-25 22:43:04.740382: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] 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]: I0525 22:43:04.742923 281473864070016 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]: I0525 22:43:04.743678 281473864070016 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]: I0525 22:43:04.755509 281473864070016 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]: I0525 22:43:04.776941 281473864070016 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]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0525 22:43:04.909364 281473864070016 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]: I0525 22:43:04.910909 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:43:04.911584 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, 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]: I0525 22:43:04.954900 281473864070016 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]: I0525 22:43:04.956494 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:43:04.956712 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, 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]: I0525 22:43:04.974879 281473864070016 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]: I0525 22:43:04.986920 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:43:04.987644 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, 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]: I0525 22:43:05.018273 281473864070016 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]: I0525 22:43:05.019080 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:43:05.019279 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0525 22:43:05.171859 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0525 22:43:05.182530 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0525 22:43:05.193295 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0525 22:43:05.206909 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0525 22:43:05.217189 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0525 22:43:05.230631 281473864070016 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]: W0525 22:43:05.231107 281473864070016 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]: I0525 22:43:05.231274 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0525 22:43:05.236847 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0525 22:43:05.260960 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0525 22:43:05.276278 281473864070016 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]: W0525 22:43:05.276789 281473864070016 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]: I0525 22:43:05.276957 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0525 22:43:05.296202 281473864070016 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]: W0525 22:43:05.296630 281473864070016 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]: I0525 22:43:05.296792 281473864070016 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]: I0525 22:43:05.400251 281473864070016 cross_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:Start polling for termination signal. [worker-1]: I0525 22:43:05.416312 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0525 22:43:05.446722 281473864070016 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]: W0525 22:43:05.449651 281473864070016 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]: I0525 22:43:05.449844 281473864070016 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]: I0525 22:43:05.481785 281473864070016 cross_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]: I0525 22:43:05.518929 281473864070016 cross_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]: I0525 22:43:05.630508 281473864070016 cross_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]: I0525 22:43:05.770898 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:05.760470 281473864070016 cross_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]: I0525 22:43:05.760924 281473864070016 cross_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]: I0525 22:43:05.770344 281473864070016 cross_device_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]: I0525 22:43:05.910521 281473864070016 cross_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]: I0525 22:43:05.937158 281473864070016 cross_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]: I0525 22:43:05.960308 281473864070016 cross_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]: I0525 22:43:05.979973 281473864070016 cross_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]: I0525 22:43:06.066752 281473864070016 cross_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]: I0525 22:43:06.077382 281473864070016 cross_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]: I0525 22:43:06.100776 281473864070016 cross_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]: I0525 22:43:06.104141 281473864070016 cross_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]: I0525 22:43:06.197920 281473864070016 cross_device_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]: I0525 22:43:06.197994 281473864070016 cross_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]: I0525 22:43:06.230209 281473864070016 cross_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]: I0525 22:43:06.257569 281473864070016 cross_device_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 0xffffba64b880> 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]: W0525 22:43:06.299356 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64b880> 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 0xffffba642840> 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 0xffffba64b920> 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]: W0525 22:43:06.299619 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba642840> 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]: W0525 22:43:06.299703 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64b920> 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]: I0525 22:43:06.306687 281473864070016 cross_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 0xffff12a87880> 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]: W0525 22:43:06.304459 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87880> 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-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0525 22:43:06.320274 281473864070016 cross_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]: I0525 22:43:06.307216 281473864070016 cross_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]: I0525 22:43:06.328832 281473864070016 cross_device_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 0xffff140132e0> 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 0xffffba64bd80> 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]: W0525 22:43:06.426092 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba64bd80> 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]: W0525 22:43:06.425851 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff140132e0> 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-3]: INFO:tensorflow:epoch 0 finished [worker-1]: I0525 22:43:06.426481 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: I0525 22:43:06.426259 281473864070016 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-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:06.433444 281473864070016 cross_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]: I0525 22:43:06.433537 281473864070016 cross_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 0xffff12a87740> 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 0xffff1598f600> 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]: W0525 22:43:06.435024 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: W0525 22:43:06.430678 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff12a87740> 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-2]: INFO:tensorflow:epoch 0 finished [worker-0]: I0525 22:43:06.435337 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: I0525 22:43:06.431058 281473864070016 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]: I0525 22:43:06.438021 281473864070016 cross_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]: I0525 22:43:06.459773 281473864070016 cross_device_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]: I0525 22:43:06.569651 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:06.563477 281473864070016 cross_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]: I0525 22:43:06.579837 281473864070016 cross_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]: I0525 22:43:06.600279 281473864070016 cross_device_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]: I0525 22:43:06.699941 281473864070016 cross_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]: I0525 22:43:06.700320 281473864070016 cross_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]: I0525 22:43:06.729760 281473864070016 cross_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]: I0525 22:43:06.768140 281473864070016 cross_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]: I0525 22:43:06.909823 281473864070016 cross_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]: I0525 22:43:06.909596 281473864070016 cross_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]: I0525 22:43:06.931431 281473864070016 cross_device_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]: I0525 22:43:06.950209 281473864070016 cross_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]: I0525 22:43:07.079542 281473864070016 cross_device_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]: I0525 22:43:07.099761 281473864070016 cross_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]: I0525 22:43:07.122515 281473864070016 cross_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]: I0525 22:43:07.140602 281473864070016 cross_device_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]: I0525 22:43:07.273342 281473864070016 cross_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]: I0525 22:43:07.300563 281473864070016 cross_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]: I0525 22:43:07.322071 281473864070016 cross_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]: I0525 22:43:07.341235 281473864070016 cross_device_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]: I0525 22:43:07.470409 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0525 22:43:07.471556 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0525 22:43:07.476062 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0525 22:43:07.480456 281473864070016 gce_failure_handler_test.py:192] epoch 1 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]: I0525 22:43:07.490550 281473864070016 cross_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]: I0525 22:43:07.499847 281473864070016 cross_device_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]: I0525 22:43:07.510707 281473864070016 cross_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]: I0525 22:43:07.539602 281473864070016 cross_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-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:07.669898 281473864070016 cross_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]: I0525 22:43:07.669940 281473864070016 cross_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]: I0525 22:43:07.659910 281473864070016 cross_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]: I0525 22:43:07.679893 281473864070016 cross_device_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]: I0525 22:43:07.824007 281473864070016 cross_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]: I0525 22:43:07.839947 281473864070016 cross_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-2]: I0525 22:43:07.831854 281473864070016 cross_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]: I0525 22:43:07.849496 281473864070016 cross_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]: I0525 22:43:07.935195 281473864070016 cross_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]: I0525 22:43:07.953430 281473864070016 cross_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]: I0525 22:43:07.963907 281473864070016 cross_device_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]: I0525 22:43:07.967561 281473864070016 cross_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]: I0525 22:43:08.017657 281473864070016 cross_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]: I0525 22:43:08.031440 281473864070016 cross_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]: I0525 22:43:08.077711 281473864070016 cross_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]: I0525 22:43:08.102088 281473864070016 cross_device_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]: I0525 22:43:08.180907 281473864070016 cross_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]: I0525 22:43:08.190001 281473864070016 cross_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]: I0525 22:43:08.199755 281473864070016 cross_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]: I0525 22:43:08.220366 281473864070016 cross_device_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]: I0525 22:43:09.201692 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-1]: I0525 22:43:09.208624 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-0]: I0525 22:43:09.213061 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0525 22:43:09.222687 281473864070016 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]: I0525 22:43:09.230331 281473864070016 cross_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]: I0525 22:43:09.249938 281473864070016 cross_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]: I0525 22:43:09.250773 281473864070016 cross_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]: I0525 22:43:09.266965 281473864070016 cross_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]: I0525 22:43:09.542535 281473864070016 cross_device_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]: I0525 22:43:09.571076 281473864070016 cross_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]: I0525 22:43:09.580310 281473864070016 cross_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]: I0525 22:43:09.590082 281473864070016 cross_device_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]: I0525 22:43:09.720087 281473864070016 cross_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]: I0525 22:43:09.729756 281473864070016 cross_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]: I0525 22:43:09.759964 281473864070016 cross_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]: I0525 22:43:09.780499 281473864070016 cross_device_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]: I0525 22:43:10.009976 281473864070016 cross_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]: I0525 22:43:10.050898 281473864070016 cross_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]: I0525 22:43:10.071083 281473864070016 cross_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]: I0525 22:43:10.089804 281473864070016 cross_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]: I0525 22:43:10.283432 281473864070016 cross_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-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0525 22:43:10.327193 281473864070016 cross_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]: I0525 22:43:10.324605 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:10.327403 281473864070016 cross_device_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]: I0525 22:43:10.490035 281473864070016 cross_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]: I0525 22:43:10.499832 281473864070016 cross_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]: I0525 22:43:10.533970 281473864070016 cross_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]: I0525 22:43:10.563738 281473864070016 cross_device_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-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0525 22:43:10.749539 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: I0525 22:43:10.743612 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: I0525 22:43:10.737353 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0525 22:43:10.756569 281473864070016 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]: I0525 22:43:10.770209 281473864070016 cross_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]: I0525 22:43:10.780343 281473864070016 cross_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]: I0525 22:43:10.780030 281473864070016 cross_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]: I0525 22:43:10.800186 281473864070016 cross_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]: I0525 22:43:11.040350 281473864070016 cross_device_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]: I0525 22:43:11.052123 281473864070016 cross_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]: I0525 22:43:11.080714 281473864070016 cross_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]: I0525 22:43:11.102212 281473864070016 cross_device_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]: I0525 22:43:11.240084 281473864070016 cross_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]: I0525 22:43:11.279862 281473864070016 cross_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]: I0525 22:43:11.319984 281473864070016 cross_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]: I0525 22:43:11.450404 281473864070016 cross_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]: I0525 22:43:11.592851 281473864070016 cross_device_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]: I0525 22:43:11.611755 281473864070016 cross_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]: I0525 22:43:11.739981 281473864070016 cross_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]: I0525 22:43:11.750212 281473864070016 cross_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]: I0525 22:43:11.859879 281473864070016 cross_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]: I0525 22:43:11.897415 281473864070016 cross_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]: I0525 22:43:11.925223 281473864070016 cross_device_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]: I0525 22:43:12.000983 281473864070016 cross_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]: I0525 22:43:12.190026 281473864070016 cross_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]: I0525 22:43:12.203194 281473864070016 cross_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]: I0525 22:43:12.226220 281473864070016 cross_device_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]: I0525 22:43:12.240566 281473864070016 cross_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]: I0525 22:43:12.352093 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0525 22:43:12.352326 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0525 22:43:12.353295 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0525 22:43:12.353551 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-3]: INFO:tensorflow:epoch 4 finished [worker-3]: I0525 22:43:12.360121 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0525 22:43:12.366464 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0525 22:43:12.366755 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0525 22:43:12.360409 281473864070016 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:Termination notice available. I0525 22:43:12.546222 281465302479328 gce_failure_handler_test.py:142] Termination notice available. INFO:tensorflow:Member single_worker has received termination notice. I0525 22:43:12.546514 281465302479328 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/python3.11/threading.py", line 1109, in join raise RuntimeError("cannot join current thread") RuntimeError: cannot join current thread INFO:tensorflow:restarting workers I0525 22:43:14.156547 281473778480000 gce_failure_handler_test.py:411] restarting workers INFO:tensorflow:workers restarted I0525 22:43:14.205427 281473778480000 gce_failure_handler_test.py:415] workers restarted [worker-0]: I0525 22:43:14.219942 281473864070016 multi_process_runner.py:840] Subprocess with PID 2555831 (worker, 0) is now being started. [worker-0]: I0525 22:43:14.220400 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:37039", "localhost:45015", "localhost:33141", "localhost:34463"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0525 22:43:14.258094 281473864070016 multi_process_runner.py:840] Subprocess with PID 2555990 (worker, 1) is now being started. [worker-1]: I0525 22:43:14.258510 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:37039", "localhost:45015", "localhost:33141", "localhost:34463"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:43:14.440312 281473864070016 multi_process_runner.py:840] Subprocess with PID 2556027 (worker, 2) is now being started. [worker-0]: 2023-05-25 22:43:14.475440: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:37039 [worker-2]: I0525 22:43:14.440739 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:37039", "localhost:45015", "localhost:33141", "localhost:34463"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:43:14.488029 281473864070016 multi_process_runner.py:840] Subprocess with PID 2556047 (worker, 3) is now being started. [worker-3]: I0525 22:43:14.488460 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:37039", "localhost:45015", "localhost:33141", "localhost:34463"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-0]: 2023-05-25 22:43:14.504325: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 611571356722727040 [worker-0]: 2023-05-25 22:43:14.504702: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-1]: 2023-05-25 22:43:14.527948: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:45015 [worker-0]: 2023-05-25 22:43:14.572391: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 18257969435565721552 [worker-1]: 2023-05-25 22:43:14.575186: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-2]: 2023-05-25 22:43:14.623571: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:33141 [worker-0]: 2023-05-25 22:43:14.636292: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 13274460841344910863 [worker-2]: 2023-05-25 22:43:14.656213: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-3]: 2023-05-25 22:43:14.706439: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:34463 [worker-0]: 2023-05-25 22:43:14.721553: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 18085662993983933167 [worker-3]: 2023-05-25 22:43:14.722234: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] 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-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]: I0525 22:43:14.723968 281473864070016 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]: I0525 22:43:14.724040 281473864070016 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-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]: I0525 22:43:14.736937 281473864070016 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]: I0525 22:43:14.746944 281473864070016 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]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-0]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-2]: I0525 22:43:14.780791 281473864070016 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-0]: I0525 22:43:14.780838 281473864070016 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:Check health not enabled. [worker-2]: I0525 22:43:14.781250 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: I0525 22:43:14.781291 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, 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:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:43:14.781440 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:43:14.781481 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, 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]: I0525 22:43:14.835248 281473864070016 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]: I0525 22:43:14.835742 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:43:14.835931 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0525 22:43:14.848050 281473864070016 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]: I0525 22:43:14.848485 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:43:14.848679 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:37039', 'localhost:45015', 'localhost:33141', 'localhost:34463']}, 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]: I0525 22:43:14.947021 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0525 22:43:14.946988 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0525 22:43:14.955632 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0525 22:43:14.958495 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0525 22:43:14.965023 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0525 22:43:14.965884 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0525 22:43:14.966548 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0525 22:43:14.978231 281473864070016 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]: W0525 22:43:14.978575 281473864070016 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]: I0525 22:43:14.978735 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0525 22:43:14.966588 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.11/threading.py", line 975, 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-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0525 22:43:14.986417 281473864070016 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-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.11/threading.py", line 975, in run [worker-3]: self._target(*self._args, **self._kwargs) [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.11/threading.py", line 975, 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-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-0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [worker-3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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-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]: elif frequent_send and not maintenance_event.is_set(): [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-1]: Instructions for updating: [worker-3]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: W0525 22:43:14.986791 281473864070016 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:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0525 22:43:14.988165 281473864070016 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: Instructions for updating: [worker-3]: I0525 22:43:14.988173 281473864070016 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-1]: Track steps using a tf.Variable saved in checkpoint instead. [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-1]: INFO:tensorflow:Start training at 0 [worker-3]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-1]: I0525 22:43:14.986953 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: W0525 22:43:14.988517 281473864070016 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]: W0525 22:43:14.988512 281473864070016 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-3]: Instructions for updating: [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: INFO:tensorflow:Start training at 0 [worker-3]: INFO:tensorflow:Start training at 0 [worker-0]: I0525 22:43:14.988679 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: I0525 22:43:14.988671 281473864070016 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]: I0525 22:43:15.117305 281473864070016 cross_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]: I0525 22:43:15.139127 281473864070016 cross_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]: I0525 22:43:15.149364 281473864070016 cross_device_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]: I0525 22:43:15.188363 281473864070016 cross_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]: I0525 22:43:15.333139 281473864070016 cross_device_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]: I0525 22:43:15.329753 281473864070016 cross_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]: I0525 22:43:15.359821 281473864070016 cross_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]: I0525 22:43:15.351857 281473864070016 cross_device_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]: I0525 22:43:15.436228 281473864070016 cross_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]: I0525 22:43:15.470867 281473864070016 cross_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]: I0525 22:43:15.459532 281473864070016 cross_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]: I0525 22:43:15.494078 281473864070016 cross_device_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]: I0525 22:43:15.563198 281473864070016 cross_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]: I0525 22:43:15.555189 281473864070016 cross_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]: I0525 22:43:15.567210 281473864070016 cross_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]: I0525 22:43:15.623386 281473864070016 cross_device_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]: I0525 22:43:15.704475 281473864070016 cross_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]: I0525 22:43:15.714790 281473864070016 cross_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]: I0525 22:43:15.719380 281473864070016 cross_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]: I0525 22:43:15.730016 281473864070016 cross_device_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 0xffff12a87600> 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]: W0525 22:43:15.812618 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87600> 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 0xffffba64b7e0> 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]: W0525 22:43:15.822748 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64b7e0> 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]: I0525 22:43:15.830416 281473864070016 cross_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 0xffff12a87600> 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]: W0525 22:43:15.852431 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87600> 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 0xffffba64ab60> 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]: W0525 22:43:15.856914 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64ab60> 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]: I0525 22:43:15.849373 281473864070016 cross_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]: I0525 22:43:15.863618 281473864070016 cross_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]: I0525 22:43:15.893229 281473864070016 cross_device_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 0xffff1598f600> 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]: W0525 22:43:15.958401 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffffba670360> 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]: W0525 22:43:15.964189 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba670360> 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]: I0525 22:43:15.964515 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff12a86fc0> 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]: I0525 22:43:15.958715 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: W0525 22:43:15.968462 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff12a86fc0> 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]: I0525 22:43:15.968748 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffffba6702c0> 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]: W0525 22:43:15.976463 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba6702c0> 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]: I0525 22:43:15.976765 281473864070016 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-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0525 22:43:15.999457 281473864070016 cross_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]: I0525 22:43:15.989842 281473864070016 cross_device_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]: I0525 22:43:16.012570 281473864070016 cross_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]: I0525 22:43:16.029718 281473864070016 cross_device_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]: I0525 22:43:16.140080 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:16.149492 281473864070016 cross_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]: I0525 22:43:16.149477 281473864070016 cross_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]: I0525 22:43:16.171034 281473864070016 cross_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]: I0525 22:43:16.254445 281473864070016 cross_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]: I0525 22:43:16.253692 281473864070016 cross_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]: I0525 22:43:16.270049 281473864070016 cross_device_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]: I0525 22:43:16.280025 281473864070016 cross_device_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]: I0525 22:43:16.383317 281473864070016 cross_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]: I0525 22:43:16.399324 281473864070016 cross_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]: I0525 22:43:16.399326 281473864070016 cross_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]: I0525 22:43:16.459689 281473864070016 cross_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]: I0525 22:43:16.569391 281473864070016 cross_device_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]: I0525 22:43:16.565474 281473864070016 cross_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]: I0525 22:43:16.579298 281473864070016 cross_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]: I0525 22:43:16.582046 281473864070016 cross_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]: I0525 22:43:16.807237 281473864070016 cross_device_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]: I0525 22:43:16.820166 281473864070016 cross_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]: I0525 22:43:16.835351 281473864070016 cross_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]: I0525 22:43:16.827999 281473864070016 cross_device_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-0]: INFO:tensorflow:epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-3]: I0525 22:43:16.890877 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: I0525 22:43:16.891020 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: I0525 22:43:16.891218 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0525 22:43:16.894743 281473864070016 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-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:16.897714 281473864070016 cross_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]: I0525 22:43:16.897785 281473864070016 cross_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]: I0525 22:43:16.901223 281473864070016 cross_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]: I0525 22:43:16.929734 281473864070016 cross_device_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]: I0525 22:43:17.009859 281473864070016 cross_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]: I0525 22:43:17.029408 281473864070016 cross_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]: I0525 22:43:17.019678 281473864070016 cross_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]: I0525 22:43:17.032963 281473864070016 cross_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]: I0525 22:43:17.116435 281473864070016 cross_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]: I0525 22:43:17.141809 281473864070016 cross_device_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]: I0525 22:43:17.164462 281473864070016 cross_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]: I0525 22:43:17.203152 281473864070016 cross_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]: I0525 22:43:17.270517 281473864070016 cross_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]: I0525 22:43:17.274831 281473864070016 cross_device_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]: I0525 22:43:17.289403 281473864070016 cross_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]: I0525 22:43:17.310916 281473864070016 cross_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]: I0525 22:43:17.410247 281473864070016 cross_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]: I0525 22:43:17.404536 281473864070016 cross_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]: I0525 22:43:17.424677 281473864070016 cross_device_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]: I0525 22:43:17.406929 281473864070016 cross_device_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]: I0525 22:43:17.513458 281473864070016 cross_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]: I0525 22:43:17.513873 281473864070016 cross_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]: I0525 22:43:17.514047 281473864070016 cross_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]: I0525 22:43:17.514050 281473864070016 cross_device_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]: I0525 22:43:17.589265 281473864070016 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]: I0525 22:43:17.596299 281473864070016 cross_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]: I0525 22:43:17.594086 281473864070016 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]: I0525 22:43:17.600844 281473864070016 cross_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 2 finished [worker-0]: I0525 22:43:17.606330 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow: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]: I0525 22:43:17.613216 281473864070016 cross_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]: I0525 22:43:17.606513 281473864070016 gce_failure_handler_test.py:192] epoch 2 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]: I0525 22:43:17.649167 281473864070016 cross_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]: I0525 22:43:17.740639 281473864070016 cross_device_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]: I0525 22:43:17.736410 281473864070016 cross_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]: I0525 22:43:17.760615 281473864070016 cross_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]: I0525 22:43:17.755095 281473864070016 cross_device_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]: I0525 22:43:17.839333 281473864070016 cross_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]: I0525 22:43:17.855442 281473864070016 cross_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]: I0525 22:43:17.856249 281473864070016 cross_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]: I0525 22:43:17.880304 281473864070016 cross_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]: I0525 22:43:17.932324 281473864070016 cross_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]: I0525 22:43:17.942861 281473864070016 cross_device_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-1]: I0525 22:43:17.970062 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:17.946880 281473864070016 cross_device_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]: I0525 22:43:18.042473 281473864070016 cross_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]: I0525 22:43:18.042474 281473864070016 cross_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]: I0525 22:43:18.046214 281473864070016 cross_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]: I0525 22:43:18.059597 281473864070016 cross_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]: I0525 22:43:18.209984 281473864070016 cross_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]: I0525 22:43:18.231108 281473864070016 cross_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]: I0525 22:43:18.250247 281473864070016 cross_device_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]: I0525 22:43:18.270815 281473864070016 cross_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-1]: I0525 22:43:18.466914 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: I0525 22:43:18.461274 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0525 22:43:18.471798 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: INFO:tensorflow:epoch 3 finished [worker-3]: I0525 22:43:18.486477 281473864070016 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]: I0525 22:43:18.481025 281473864070016 cross_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]: I0525 22:43:18.490191 281473864070016 cross_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]: I0525 22:43:18.490182 281473864070016 cross_device_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]: I0525 22:43:18.511259 281473864070016 cross_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]: I0525 22:43:18.750388 281473864070016 cross_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]: I0525 22:43:18.750970 281473864070016 cross_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]: I0525 22:43:18.760300 281473864070016 cross_device_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]: I0525 22:43:18.810061 281473864070016 cross_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]: I0525 22:43:19.050517 281473864070016 cross_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]: I0525 22:43:19.050043 281473864070016 cross_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]: I0525 22:43:19.069930 281473864070016 cross_device_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]: I0525 22:43:19.150234 281473864070016 cross_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]: I0525 22:43:19.270003 281473864070016 cross_device_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]: I0525 22:43:19.269943 281473864070016 cross_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]: I0525 22:43:19.287972 281473864070016 cross_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]: I0525 22:43:19.292441 281473864070016 cross_device_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]: I0525 22:43:19.431545 281473864070016 cross_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]: I0525 22:43:19.440015 281473864070016 cross_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]: I0525 22:43:19.440003 281473864070016 cross_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]: I0525 22:43:19.460120 281473864070016 cross_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]: I0525 22:43:19.569965 281473864070016 cross_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]: I0525 22:43:19.569971 281473864070016 cross_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]: I0525 22:43:19.592371 281473864070016 cross_device_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]: I0525 22:43:19.611214 281473864070016 cross_device_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]: I0525 22:43:19.728888 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0525 22:43:19.729204 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:epoch 4 finished [worker-2]: INFO:tensorflow:epoch 4 finished [worker-1]: INFO:tensorflow:epoch 4 finished [worker-0]: I0525 22:43:19.769374 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: I0525 22:43:19.777112 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: I0525 22:43:19.776849 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-2]: INFO:tensorflow:Training finished. [worker-1]: I0525 22:43:19.777160 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-2]: I0525 22:43:19.777409 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0525 22:43:19.769680 281473864070016 gce_failure_handler_test.py:244] Training finished. I0525 22:43:20.196289 281473778480000 multi_process_runner.py:646] worker-0 exit code: 0 I0525 22:43:20.196570 281473778480000 multi_process_runner.py:646] worker-1 exit code: 0 I0525 22:43:20.196730 281473778480000 multi_process_runner.py:646] worker-2 exit code: 0 I0525 22:43:20.196866 281473778480000 multi_process_runner.py:646] worker-3 exit code: 0 I0525 22:43:20.199770 281473778480000 multi_process_runner.py:662] Joining log reading threads. I0525 22:43:20.200006 281473778480000 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_manager_strategyoption_MWMSmultiworker): 17.37s I0525 22:43:20.444780 281473778480000 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_0_inputarg_manager_strategyoption_MWMSmultiworker): 17.37s [ OK ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_0_inputarg_manager_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_7_inputarg_manager_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 45259 I0525 22:43:20.446598 281473778480000 test_util.py:3796] Using local port 45259 INFO:tensorflow:Using local port 41323 I0525 22:43:20.447019 281473778480000 test_util.py:3796] Using local port 41323 INFO:tensorflow:Using local port 33405 I0525 22:43:20.447367 281473778480000 test_util.py:3796] Using local port 33405 INFO:tensorflow:Using local port 40111 I0525 22:43:20.447715 281473778480000 test_util.py:3796] Using local port 40111 INFO:tensorflow:Cluster starting. I0525 22:43:20.609180 281473778480000 gce_failure_handler_test.py:405] Cluster starting. [worker-0]: I0525 22:43:20.747132 281473864070016 multi_process_runner.py:840] Subprocess with PID 2587273 (worker, 0) is now being started. [worker-0]: I0525 22:43:20.747682 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:45259", "localhost:41323", "localhost:33405", "localhost:40111"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0525 22:43:20.837975 281473864070016 multi_process_runner.py:840] Subprocess with PID 2587383 (worker, 1) is now being started. [worker-2]: I0525 22:43:20.858689 281473864070016 multi_process_runner.py:840] Subprocess with PID 2587502 (worker, 2) is now being started. [worker-2]: I0525 22:43:20.859218 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:45259", "localhost:41323", "localhost:33405", "localhost:40111"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:43:20.870620 281473864070016 multi_process_runner.py:840] Subprocess with PID 2587607 (worker, 3) is now being started. [worker-1]: I0525 22:43:20.838539 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:45259", "localhost:41323", "localhost:33405", "localhost:40111"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:43:20.871159 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:45259", "localhost:41323", "localhost:33405", "localhost:40111"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-0]: 2023-05-25 22:43:20.969646: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:45259 [worker-0]: 2023-05-25 22:43:20.988439: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 12387825286847217074 [worker-1]: 2023-05-25 22:43:21.003851: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:41323 [worker-0]: 2023-05-25 22:43:21.006966: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:21.027854: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 8565400778506834172 [worker-1]: 2023-05-25 22:43:21.036140: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-2]: 2023-05-25 22:43:21.132851: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:33405 [worker-3]: 2023-05-25 22:43:21.143851: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:40111 [worker-0]: 2023-05-25 22:43:21.145165: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 615928154293178459 [worker-2]: 2023-05-25 22:43:21.145713: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:21.147285: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 14560177666308478864 [worker-3]: 2023-05-25 22:43:21.147485: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] 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-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]: I0525 22:43:21.188591 281473864070016 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]: I0525 22:43:21.197066 281473864070016 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]: 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-0]: I0525 22:43:21.169652 281473864070016 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]: I0525 22:43:21.187322 281473864070016 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-1]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0525 22:43:21.248245 281473864070016 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]: I0525 22:43:21.248778 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:43:21.249005 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0525 22:43:21.259378 281473864070016 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]: I0525 22:43:21.259898 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:43:21.260127 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, 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]: I0525 22:43:21.278723 281473864070016 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]: I0525 22:43:21.279240 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:43:21.279468 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, 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]: I0525 22:43:21.278723 281473864070016 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]: I0525 22:43:21.279240 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:43:21.279467 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, 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]: I0525 22:43:21.347858 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0525 22:43:21.348989 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0525 22:43:21.353646 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0525 22:43:21.354745 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0525 22:43:21.348340 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0525 22:43:21.349692 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-1]: I0525 22:43:21.350238 281473864070016 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]: W0525 22:43:21.351007 281473864070016 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]: I0525 22:43:21.351381 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0525 22:43:21.365660 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0525 22:43:21.366497 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.11/threading.py", line 975, in run [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-3]: self._target(*self._args, **self._kwargs) [worker-0]: 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]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: if self._termination_watcher_fn(): [worker-3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.11/threading.py", line 975, in run [worker-2]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [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]: self.run() [worker-2]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0525 22:43:21.368791 281473864070016 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]: W0525 22:43:21.369113 281473864070016 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]: I0525 22:43:21.369301 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: self._target(*self._args, **self._kwargs) [worker-3]: ^^^^^^^^^^^^^^^^^^^^^^^^ [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-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [worker-3]: INFO:tensorflow: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/gce_failure_handler_test.py", line 145, in mock_termination_watcher_function_gce [worker-3]: I0525 22:43:21.368432 281473864070016 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-0]: elif frequent_send and not maintenance_event.is_set(): [worker-0]: ^^^^^^^^^^^^^^^^^^^^^^^^ [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]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: Instructions for updating: [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: I0525 22:43:21.368343 281473864070016 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: W0525 22:43:21.368816 281473864070016 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]: 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-0]: Instructions for updating: [worker-3]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: W0525 22:43:21.368721 281473864070016 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 training at 0 [worker-0]: Instructions for updating: [worker-3]: I0525 22:43:21.369007 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: Track steps using a tf.Variable saved in checkpoint instead. [worker-0]: INFO:tensorflow:Start training at 0 [worker-0]: I0525 22:43:21.368916 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [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]: I0525 22:43:21.582910 281473864070016 cross_device_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]: I0525 22:43:21.607304 281473864070016 cross_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]: I0525 22:43:21.663570 281473864070016 cross_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]: I0525 22:43:21.663776 281473864070016 cross_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]: I0525 22:43:21.766989 281473864070016 cross_device_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]: I0525 22:43:21.757266 281473864070016 cross_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]: I0525 22:43:21.785813 281473864070016 cross_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]: I0525 22:43:21.810703 281473864070016 cross_device_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]: I0525 22:43:21.925884 281473864070016 cross_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]: I0525 22:43:21.955532 281473864070016 cross_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]: I0525 22:43:21.940330 281473864070016 cross_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]: I0525 22:43:21.970225 281473864070016 cross_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]: I0525 22:43:22.084291 281473864070016 cross_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]: I0525 22:43:22.084356 281473864070016 cross_device_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]: I0525 22:43:22.100117 281473864070016 cross_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]: I0525 22:43:22.101136 281473864070016 cross_device_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]: I0525 22:43:22.181076 281473864070016 cross_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]: I0525 22:43:22.182147 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:22.180823 281473864070016 cross_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]: I0525 22:43:22.219903 281473864070016 cross_device_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 0xffffba64ab60> 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 0xffff12a87880> 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]: W0525 22:43:22.313788 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87880> 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 0xffffba649ee0> 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]: W0525 22:43:22.308372 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64ab60> 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 0xffff12a87600> 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]: W0525 22:43:22.318468 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87600> 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]: W0525 22:43:22.313555 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba649ee0> 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]: I0525 22:43:22.321517 281473864070016 cross_device_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]: I0525 22:43:22.324333 281473864070016 cross_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]: I0525 22:43:22.321504 281473864070016 cross_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]: I0525 22:43:22.340181 281473864070016 cross_device_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 0xffff1598f600> 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]: W0525 22:43:22.428264 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: I0525 22:43:22.428658 281473864070016 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]: I0525 22:43:22.437403 281473864070016 cross_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 0xffff1598f600> 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]: W0525 22:43:22.447087 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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:6 out of the last 6 calls to .wrapped_fn at 0xffffba670360> 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]: W0525 22:43:22.452072 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba670360> 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]: I0525 22:43:22.447467 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: INFO:tensorflow:epoch 0 finished [worker-2]: I0525 22:43:22.452431 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: W0525 22:43:22.446444 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: I0525 22:43:22.446842 281473864070016 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]: I0525 22:43:22.460805 281473864070016 cross_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]: I0525 22:43:22.470398 281473864070016 cross_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]: I0525 22:43:22.500017 281473864070016 cross_device_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]: I0525 22:43:22.612274 281473864070016 cross_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]: I0525 22:43:22.640078 281473864070016 cross_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]: I0525 22:43:22.660018 281473864070016 cross_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]: I0525 22:43:22.676975 281473864070016 cross_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]: I0525 22:43:22.768056 281473864070016 cross_device_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]: I0525 22:43:22.768654 281473864070016 cross_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]: I0525 22:43:22.781215 281473864070016 cross_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]: I0525 22:43:22.819804 281473864070016 cross_device_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]: I0525 22:43:22.925903 281473864070016 cross_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]: I0525 22:43:22.946432 281473864070016 cross_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]: I0525 22:43:22.955056 281473864070016 cross_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]: I0525 22:43:22.966930 281473864070016 cross_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]: I0525 22:43:23.075066 281473864070016 cross_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]: I0525 22:43:23.090429 281473864070016 cross_device_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]: I0525 22:43:23.091547 281473864070016 cross_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]: I0525 22:43:23.099977 281473864070016 cross_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]: I0525 22:43:23.194447 281473864070016 cross_device_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-1]: I0525 22:43:23.178720 281473864070016 cross_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]: I0525 22:43:23.220163 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:23.181560 281473864070016 cross_device_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]: I0525 22:43:23.345122 281473864070016 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]: I0525 22:43:23.350266 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: I0525 22:43:23.356053 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0525 22:43:23.356426 281473864070016 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-2]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0525 22:43:23.368596 281473864070016 cross_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]: I0525 22:43:23.365775 281473864070016 cross_device_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]: I0525 22:43:23.381371 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:23.378440 281473864070016 cross_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]: I0525 22:43:23.488497 281473864070016 cross_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]: I0525 22:43:23.500255 281473864070016 cross_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]: I0525 22:43:23.522276 281473864070016 cross_device_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]: I0525 22:43:23.552206 281473864070016 cross_device_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]: I0525 22:43:23.676296 281473864070016 cross_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]: I0525 22:43:23.679956 281473864070016 cross_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]: I0525 22:43:23.690185 281473864070016 cross_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]: I0525 22:43:23.730185 281473864070016 cross_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]: I0525 22:43:23.855366 281473864070016 cross_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-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:23.890070 281473864070016 cross_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]: I0525 22:43:23.900014 281473864070016 cross_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]: I0525 22:43:23.900007 281473864070016 cross_device_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-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:24.030020 281473864070016 cross_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]: I0525 22:43:24.030165 281473864070016 cross_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]: I0525 22:43:24.030017 281473864070016 cross_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]: I0525 22:43:24.039823 281473864070016 cross_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]: I0525 22:43:24.190917 281473864070016 cross_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]: I0525 22:43:24.192644 281473864070016 cross_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]: I0525 22:43:24.210020 281473864070016 cross_device_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]: I0525 22:43:24.239521 281473864070016 cross_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 2 finished [worker-0]: I0525 22:43:24.337693 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0525 22:43:24.347779 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: I0525 22:43:24.342715 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: INFO:tensorflow:epoch 2 finished [worker-3]: I0525 22:43:24.360959 281473864070016 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]: I0525 22:43:24.359874 281473864070016 cross_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]: I0525 22:43:24.369820 281473864070016 cross_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]: I0525 22:43:24.391181 281473864070016 cross_device_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]: I0525 22:43:24.419460 281473864070016 cross_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]: I0525 22:43:24.609262 281473864070016 cross_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]: I0525 22:43:24.628087 281473864070016 cross_device_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]: I0525 22:43:24.637270 281473864070016 cross_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]: I0525 22:43:24.641644 281473864070016 cross_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]: I0525 22:43:24.831917 281473864070016 cross_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]: I0525 22:43:24.822341 281473864070016 cross_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]: I0525 22:43:24.840654 281473864070016 cross_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]: I0525 22:43:24.857565 281473864070016 cross_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-3]: I0525 22:43:25.029761 281473864070016 cross_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]: I0525 22:43:25.043423 281473864070016 cross_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]: I0525 22:43:25.039753 281473864070016 cross_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]: I0525 22:43:25.058007 281473864070016 cross_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]: I0525 22:43:25.289494 281473864070016 cross_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]: I0525 22:43:25.298299 281473864070016 cross_device_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]: I0525 22:43:25.309372 281473864070016 cross_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]: I0525 22:43:25.319345 281473864070016 cross_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]: I0525 22:43:25.385324 281473864070016 cross_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]: I0525 22:43:25.387866 281473864070016 cross_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]: I0525 22:43:25.399554 281473864070016 cross_device_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]: I0525 22:43:25.430104 281473864070016 cross_device_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-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0525 22:43:25.547783 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: I0525 22:43:25.542653 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: I0525 22:43:25.538504 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0525 22:43:25.559076 281473864070016 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]: I0525 22:43:25.573657 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:25.573566 281473864070016 cross_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]: I0525 22:43:25.589406 281473864070016 cross_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]: I0525 22:43:25.580869 281473864070016 cross_device_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]: I0525 22:43:25.749449 281473864070016 cross_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-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-1]: I0525 22:43:25.797459 281473864070016 cross_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]: I0525 22:43:25.780595 281473864070016 cross_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]: I0525 22:43:25.817351 281473864070016 cross_device_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-1]: I0525 22:43:26.004234 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:26.000613 281473864070016 cross_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]: I0525 22:43:26.019705 281473864070016 cross_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]: I0525 22:43:26.090156 281473864070016 cross_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]: I0525 22:43:26.210221 281473864070016 cross_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]: I0525 22:43:26.219697 281473864070016 cross_device_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]: I0525 22:43:26.229578 281473864070016 cross_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]: I0525 22:43:26.240023 281473864070016 cross_device_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]: I0525 22:43:26.440105 281473864070016 cross_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]: I0525 22:43:26.443739 281473864070016 cross_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]: I0525 22:43:26.446971 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:26.429904 281473864070016 cross_device_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]: I0525 22:43:26.639769 281473864070016 cross_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]: I0525 22:43:26.639690 281473864070016 cross_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]: I0525 22:43:26.647646 281473864070016 cross_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]: I0525 22:43:26.649563 281473864070016 cross_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-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0525 22:43:26.784015 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: I0525 22:43:26.782042 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-0]: INFO:tensorflow:Training finished. [worker-1]: I0525 22:43:26.784256 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-0]: I0525 22:43:26.782329 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-3]: INFO:tensorflow:epoch 4 finished [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0525 22:43:26.798416 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0525 22:43:26.798674 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-3]: I0525 22:43:26.796591 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0525 22:43:26.796875 281473864070016 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:restarting workers I0525 22:43:28.826850 281473778480000 gce_failure_handler_test.py:411] restarting workers [worker-0]: I0525 22:43:28.937484 281473864070016 multi_process_runner.py:840] Subprocess with PID 2614324 (worker, 0) is now being started. [worker-0]: I0525 22:43:28.937941 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:45259", "localhost:41323", "localhost:33405", "localhost:40111"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' INFO:tensorflow:workers restarted I0525 22:43:28.966226 281473778480000 gce_failure_handler_test.py:415] workers restarted [worker-1]: I0525 22:43:29.258828 281473864070016 multi_process_runner.py:840] Subprocess with PID 2614469 (worker, 1) is now being started. [worker-1]: I0525 22:43:29.259320 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:45259", "localhost:41323", "localhost:33405", "localhost:40111"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:43:29.308990 281473864070016 multi_process_runner.py:840] Subprocess with PID 2614491 (worker, 3) is now being started. [worker-2]: I0525 22:43:29.310924 281473864070016 multi_process_runner.py:840] Subprocess with PID 2614488 (worker, 2) is now being started. [worker-0]: 2023-05-25 22:43:29.330842: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:45259 [worker-3]: I0525 22:43:29.309456 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:45259", "localhost:41323", "localhost:33405", "localhost:40111"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-0]: 2023-05-25 22:43:29.390190: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 1109292573615857785 [worker-0]: 2023-05-25 22:43:29.390834: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-2]: I0525 22:43:29.311341 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:45259", "localhost:41323", "localhost:33405", "localhost:40111"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-2]: 2023-05-25 22:43:29.508254: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:33405 [worker-0]: 2023-05-25 22:43:29.511783: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 8827509979237925089 [worker-2]: 2023-05-25 22:43:29.512013: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-1]: 2023-05-25 22:43:29.537481: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:41323 [worker-3]: 2023-05-25 22:43:29.566990: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:40111 [worker-0]: 2023-05-25 22:43:29.576189: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 10587719428546992594 [worker-3]: 2023-05-25 22:43:29.586167: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:29.616205: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 5764008975968841887 [worker-1]: 2023-05-25 22:43:29.617196: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] 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]: I0525 22:43:29.647470 281473864070016 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]: I0525 22:43:29.658477 281473864070016 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]: I0525 22:43:29.673925 281473864070016 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]: I0525 22:43:29.676834 281473864070016 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:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0525 22:43:29.714181 281473864070016 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]: I0525 22:43:29.714665 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:43:29.714877 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, 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]: I0525 22:43:29.733719 281473864070016 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]: I0525 22:43:29.734184 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:43:29.734389 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, 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]: I0525 22:43:29.755593 281473864070016 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]: I0525 22:43:29.756091 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:43:29.756486 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, 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]: I0525 22:43:29.767819 281473864070016 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]: I0525 22:43:29.770358 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:43:29.770573 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:45259', 'localhost:41323', 'localhost:33405', 'localhost:40111']}, 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:Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0525 22:43:29.815835 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: I0525 22:43:29.815292 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0525 22:43:29.816823 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: I0525 22:43:29.817578 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0525 22:43:29.817646 281473864070016 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]: W0525 22:43:29.817982 281473864070016 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-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start training at 0 [worker-3]: I0525 22:43:29.825536 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: I0525 22:43:29.818252 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0525 22:43:29.815056 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0525 22:43:29.826685 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0525 22:43:29.838187 281473864070016 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]: W0525 22:43:29.838557 281473864070016 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-3]: INFO:tensorflow:Start polling for termination signal. [worker-1]: Track steps using a tf.Variable saved in checkpoint instead. [worker-3]: I0525 22:43:29.840363 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: INFO:tensorflow:Start training at 0 [worker-1]: I0525 22:43:29.838730 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0525 22:43:29.848050 281473864070016 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [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]: W0525 22:43:29.848404 281473864070016 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]: I0525 22:43:29.848567 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0525 22:43:29.858113 281473864070016 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]: W0525 22:43:29.858487 281473864070016 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]: I0525 22:43:29.858653 281473864070016 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]: I0525 22:43:29.954497 281473864070016 cross_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]: I0525 22:43:30.018148 281473864070016 cross_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]: I0525 22:43:30.058983 281473864070016 cross_device_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]: I0525 22:43:30.095088 281473864070016 cross_device_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]: I0525 22:43:30.193095 281473864070016 cross_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]: I0525 22:43:30.196956 281473864070016 cross_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]: I0525 22:43:30.210236 281473864070016 cross_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]: I0525 22:43:30.240052 281473864070016 cross_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]: I0525 22:43:30.379790 281473864070016 cross_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]: I0525 22:43:30.370059 281473864070016 cross_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]: I0525 22:43:30.379796 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:30.379863 281473864070016 cross_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]: I0525 22:43:30.479803 281473864070016 cross_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]: I0525 22:43:30.479803 281473864070016 cross_device_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]: I0525 22:43:30.540518 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:30.510774 281473864070016 cross_device_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]: I0525 22:43:30.754654 281473864070016 cross_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]: I0525 22:43:30.754421 281473864070016 cross_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]: I0525 22:43:30.757732 281473864070016 cross_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]: I0525 22:43:30.773572 281473864070016 cross_device_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 0xffffba64b240> 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 0xffffba64a8e0> 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]: W0525 22:43:30.882707 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64a8e0> 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]: W0525 22:43:30.877010 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64b240> 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 0xffff12a87740> 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]: W0525 22:43:30.882953 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87740> 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 0xffffba64bba0> 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]: W0525 22:43:30.887184 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64bba0> 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:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:30.893929 281473864070016 cross_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]: I0525 22:43:30.894780 281473864070016 cross_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]: I0525 22:43:30.900204 281473864070016 cross_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]: I0525 22:43:30.929686 281473864070016 cross_device_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 0xffffba6d04a0> 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]: W0525 22:43:31.007912 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba6d04a0> 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]: I0525 22:43:31.008249 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffffba64b420> 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]: W0525 22:43:31.016940 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba64b420> 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]: I0525 22:43:31.017261 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffffba670400> 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:6 out of the last 6 calls to .wrapped_fn at 0xffffba649e40> 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]: W0525 22:43:31.020950 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba670400> 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]: W0525 22:43:31.020840 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba649e40> 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]: I0525 22:43:31.021255 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: I0525 22:43:31.021149 281473864070016 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]: I0525 22:43:31.049946 281473864070016 cross_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]: I0525 22:43:31.039924 281473864070016 cross_device_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]: I0525 22:43:31.060060 281473864070016 cross_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]: I0525 22:43:31.039645 281473864070016 cross_device_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]: I0525 22:43:31.192707 281473864070016 cross_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]: I0525 22:43:31.226871 281473864070016 cross_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]: I0525 22:43:31.219671 281473864070016 cross_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]: I0525 22:43:31.226880 281473864070016 cross_device_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]: I0525 22:43:31.339607 281473864070016 cross_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]: I0525 22:43:31.349543 281473864070016 cross_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]: I0525 22:43:31.373870 281473864070016 cross_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]: I0525 22:43:31.349542 281473864070016 cross_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]: I0525 22:43:31.489886 281473864070016 cross_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]: I0525 22:43:31.493046 281473864070016 cross_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]: I0525 22:43:31.500322 281473864070016 cross_device_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]: I0525 22:43:31.499624 281473864070016 cross_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]: I0525 22:43:31.639907 281473864070016 cross_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]: I0525 22:43:31.642771 281473864070016 cross_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]: I0525 22:43:31.649476 281473864070016 cross_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]: I0525 22:43:31.659476 281473864070016 cross_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]: I0525 22:43:31.829385 281473864070016 cross_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]: I0525 22:43:31.840094 281473864070016 cross_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]: I0525 22:43:31.839374 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:31.838407 281473864070016 cross_device_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-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0525 22:43:32.019135 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0525 22:43:32.021426 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-3]: I0525 22:43:32.017017 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0525 22:43:32.036419 281473864070016 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-0]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0525 22:43:32.059746 281473864070016 cross_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]: I0525 22:43:32.059862 281473864070016 cross_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]: I0525 22:43:32.067507 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:32.049778 281473864070016 cross_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]: I0525 22:43:32.199889 281473864070016 cross_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]: I0525 22:43:32.220681 281473864070016 cross_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]: I0525 22:43:32.202187 281473864070016 cross_device_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]: I0525 22:43:32.229682 281473864070016 cross_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]: I0525 22:43:32.359830 281473864070016 cross_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]: I0525 22:43:32.359937 281473864070016 cross_device_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]: I0525 22:43:32.376786 281473864070016 cross_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]: I0525 22:43:32.389501 281473864070016 cross_device_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]: I0525 22:43:32.510101 281473864070016 cross_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]: I0525 22:43:32.519805 281473864070016 cross_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]: I0525 22:43:32.519806 281473864070016 cross_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]: I0525 22:43:32.600120 281473864070016 cross_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]: I0525 22:43:32.710787 281473864070016 cross_device_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]: I0525 22:43:32.719923 281473864070016 cross_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]: I0525 22:43:32.739955 281473864070016 cross_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]: I0525 22:43:32.739943 281473864070016 cross_device_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]: I0525 22:43:32.835733 281473864070016 cross_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-2]: I0525 22:43:32.844648 281473864070016 cross_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]: I0525 22:43:32.846867 281473864070016 cross_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]: I0525 22:43:32.861178 281473864070016 cross_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 2 finished [worker-0]: I0525 22:43:32.965808 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-2]: I0525 22:43:32.966343 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: I0525 22:43:32.966269 281473864070016 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-3]: INFO:tensorflow:epoch 2 finished [worker-1]: I0525 22:43:32.975604 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:32.966456 281473864070016 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]: I0525 22:43:32.990175 281473864070016 cross_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]: I0525 22:43:32.991214 281473864070016 cross_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]: I0525 22:43:32.990677 281473864070016 cross_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]: I0525 22:43:33.101219 281473864070016 cross_device_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]: I0525 22:43:33.087202 281473864070016 cross_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]: I0525 22:43:33.114181 281473864070016 cross_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]: I0525 22:43:33.136932 281473864070016 cross_device_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]: I0525 22:43:33.201107 281473864070016 cross_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]: I0525 22:43:33.205182 281473864070016 cross_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]: I0525 22:43:33.213940 281473864070016 cross_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]: I0525 22:43:33.230466 281473864070016 cross_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]: I0525 22:43:33.295670 281473864070016 cross_device_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]: I0525 22:43:33.301624 281473864070016 cross_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]: I0525 22:43:33.296794 281473864070016 cross_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]: I0525 22:43:33.330806 281473864070016 cross_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]: I0525 22:43:33.425426 281473864070016 cross_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]: I0525 22:43:33.428741 281473864070016 cross_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]: I0525 22:43:33.430100 281473864070016 cross_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]: I0525 22:43:33.428047 281473864070016 cross_device_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]: I0525 22:43:33.515166 281473864070016 cross_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]: I0525 22:43:33.550081 281473864070016 cross_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]: I0525 22:43:33.559940 281473864070016 cross_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]: I0525 22:43:33.557535 281473864070016 cross_device_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]: I0525 22:43:33.666936 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0525 22:43:33.685369 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: I0525 22:43:33.679238 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-1]: I0525 22:43:33.686510 281473864070016 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-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]: I0525 22:43:33.710937 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:33.690031 281473864070016 cross_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]: I0525 22:43:33.700120 281473864070016 cross_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]: I0525 22:43:33.730067 281473864070016 cross_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]: I0525 22:43:33.884696 281473864070016 cross_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]: I0525 22:43:33.884291 281473864070016 cross_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]: I0525 22:43:33.901975 281473864070016 cross_device_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]: I0525 22:43:33.906958 281473864070016 cross_device_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]: I0525 22:43:34.020630 281473864070016 cross_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]: I0525 22:43:34.030417 281473864070016 cross_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]: I0525 22:43:34.030218 281473864070016 cross_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]: I0525 22:43:34.070266 281473864070016 cross_device_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]: I0525 22:43:34.170620 281473864070016 cross_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]: I0525 22:43:34.181141 281473864070016 cross_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]: I0525 22:43:34.180283 281473864070016 cross_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]: I0525 22:43:34.190043 281473864070016 cross_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]: I0525 22:43:34.320331 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:34.320330 281473864070016 cross_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]: I0525 22:43:34.321135 281473864070016 cross_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]: I0525 22:43:34.340406 281473864070016 cross_device_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]: I0525 22:43:34.440165 281473864070016 cross_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]: I0525 22:43:34.450380 281473864070016 cross_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]: I0525 22:43:34.451764 281473864070016 cross_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]: I0525 22:43:34.510052 281473864070016 cross_device_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]: I0525 22:43:34.575628 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0525 22:43:34.575913 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-3]: I0525 22:43:34.573768 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0525 22:43:34.574085 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0525 22:43:34.576305 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0525 22:43:34.576582 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0525 22:43:34.589739 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0525 22:43:34.590021 281473864070016 gce_failure_handler_test.py:244] Training finished. I0525 22:43:35.956713 281473778480000 multi_process_runner.py:646] worker-0 exit code: 0 I0525 22:43:35.957056 281473778480000 multi_process_runner.py:646] worker-1 exit code: 0 I0525 22:43:35.957198 281473778480000 multi_process_runner.py:646] worker-2 exit code: 0 I0525 22:43:35.957328 281473778480000 multi_process_runner.py:646] worker-3 exit code: 0 I0525 22:43:35.979081 281473778480000 multi_process_runner.py:662] Joining log reading threads. I0525 22:43:35.979467 281473778480000 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_manager_strategyoption_MWMSmultiworker): 15.75s I0525 22:43:36.195539 281473778480000 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_7_inputarg_manager_strategyoption_MWMSmultiworker): 15.75s [ OK ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_False_graceperiod_7_inputarg_manager_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_0_inputarg_manager_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 44631 I0525 22:43:36.197425 281473778480000 test_util.py:3796] Using local port 44631 INFO:tensorflow:Using local port 39841 I0525 22:43:36.197810 281473778480000 test_util.py:3796] Using local port 39841 INFO:tensorflow:Using local port 44951 I0525 22:43:36.198143 281473778480000 test_util.py:3796] Using local port 44951 INFO:tensorflow:Using local port 33625 I0525 22:43:36.198479 281473778480000 test_util.py:3796] Using local port 33625 INFO:tensorflow:Cluster starting. I0525 22:43:36.419343 281473778480000 gce_failure_handler_test.py:405] Cluster starting. [worker-0]: I0525 22:43:36.480813 281473864070016 multi_process_runner.py:840] Subprocess with PID 2627017 (worker, 0) is now being started. [worker-0]: I0525 22:43:36.481405 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:44631", "localhost:39841", "localhost:44951", "localhost:33625"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0525 22:43:36.526828 281473864070016 multi_process_runner.py:840] Subprocess with PID 2627060 (worker, 1) is now being started. [worker-1]: I0525 22:43:36.527413 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:44631", "localhost:39841", "localhost:44951", "localhost:33625"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:43:36.571007 281473864070016 multi_process_runner.py:840] Subprocess with PID 2627187 (worker, 2) is now being started. [worker-2]: I0525 22:43:36.571591 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:44631", "localhost:39841", "localhost:44951", "localhost:33625"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:43:36.597629 281473864070016 multi_process_runner.py:840] Subprocess with PID 2627261 (worker, 3) is now being started. [worker-3]: I0525 22:43:36.598121 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:44631", "localhost:39841", "localhost:44951", "localhost:33625"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-25 22:43:36.860225: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:39841 [worker-2]: 2023-05-25 22:43:36.887606: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:44951 [worker-3]: 2023-05-25 22:43:36.907014: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:33625 [worker-0]: 2023-05-25 22:43:37.246962: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:44631 [worker-0]: 2023-05-25 22:43:37.253276: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 4092559380959822258 [worker-0]: 2023-05-25 22:43:37.253682: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 1214739590313779499 [worker-3]: 2023-05-25 22:43:37.254079: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-1]: 2023-05-25 22:43:37.254203: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:37.258245: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 395943391226033340 [worker-2]: 2023-05-25 22:43:37.258523: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:37.264392: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 13298999162861314624 [worker-0]: 2023-05-25 22:43:37.264670: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] 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-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-1]: I0525 22:43:37.266672 281473864070016 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]: I0525 22:43:37.267127 281473864070016 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]: I0525 22:43:37.267186 281473864070016 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]: I0525 22:43:37.267409 281473864070016 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:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0525 22:43:37.330728 281473864070016 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]: I0525 22:43:37.331324 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:43:37.331583 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, 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]: I0525 22:43:37.349889 281473864070016 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]: I0525 22:43:37.350512 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:43:37.350788 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, 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]: I0525 22:43:37.418846 281473864070016 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]: I0525 22:43:37.420431 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:43:37.421318 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, 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]: I0525 22:43:37.437769 281473864070016 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]: I0525 22:43:37.439090 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:43:37.439372 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, 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]: I0525 22:43:37.677910 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0525 22:43:37.678567 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0525 22:43:37.693501 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: I0525 22:43:37.688764 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0525 22:43:37.697134 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-0]: I0525 22:43:37.686889 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0525 22:43:37.697229 281473864070016 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]: W0525 22:43:37.697694 281473864070016 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]: I0525 22:43:37.697930 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0525 22:43:37.716320 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0525 22:43:37.718745 281473864070016 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]: W0525 22:43:37.719236 281473864070016 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]: I0525 22:43:37.719482 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0525 22:43:37.726426 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0525 22:43:37.747621 281473864070016 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]: W0525 22:43:37.748172 281473864070016 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]: I0525 22:43:37.749585 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0525 22:43:37.767082 281473864070016 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]: W0525 22:43:37.767601 281473864070016 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]: I0525 22:43:37.767842 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [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]: I0525 22:43:37.873688 281473864070016 cross_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]: I0525 22:43:37.873734 281473864070016 cross_device_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]: I0525 22:43:37.893515 281473864070016 cross_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]: I0525 22:43:37.965526 281473864070016 cross_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]: I0525 22:43:38.074003 281473864070016 cross_device_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]: I0525 22:43:38.080892 281473864070016 cross_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]: I0525 22:43:38.090667 281473864070016 cross_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]: I0525 22:43:38.090706 281473864070016 cross_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]: I0525 22:43:38.210801 281473864070016 cross_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]: I0525 22:43:38.197900 281473864070016 cross_device_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]: I0525 22:43:38.210783 281473864070016 cross_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]: I0525 22:43:38.237027 281473864070016 cross_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]: I0525 22:43:38.336602 281473864070016 cross_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]: I0525 22:43:38.339744 281473864070016 cross_device_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]: I0525 22:43:38.340655 281473864070016 cross_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]: I0525 22:43:38.336212 281473864070016 cross_device_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]: I0525 22:43:38.445461 281473864070016 cross_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]: I0525 22:43:38.460930 281473864070016 cross_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]: I0525 22:43:38.450774 281473864070016 cross_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]: I0525 22:43:38.450753 281473864070016 cross_device_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 0xffff12a87c40> 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]: W0525 22:43:38.520188 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87c40> 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 0xffff12a879c0> 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]: W0525 22:43:38.527784 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a879c0> 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 0xffff12a87880> 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]: W0525 22:43:38.533157 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87880> 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 0xffffba64b920> 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]: W0525 22:43:38.539302 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64b920> 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]: I0525 22:43:38.530646 281473864070016 cross_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]: I0525 22:43:38.550643 281473864070016 cross_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]: I0525 22:43:38.560825 281473864070016 cross_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]: I0525 22:43:38.560789 281473864070016 cross_device_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 0xffff1598f600> 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 0xffffba6704a0> 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:6 out of the last 6 calls to .wrapped_fn at 0xffffba670360> 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 0xffff12a851c0> 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]: W0525 22:43:38.687486 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: W0525 22:43:38.694671 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba670360> 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-2]: INFO:tensorflow:epoch 0 finished [worker-3]: I0525 22:43:38.687928 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: I0525 22:43:38.695068 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: W0525 22:43:38.687713 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff12a851c0> 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]: I0525 22:43:38.688124 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: W0525 22:43:38.694128 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba6704a0> 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]: I0525 22:43:38.694528 281473864070016 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]: I0525 22:43:38.710756 281473864070016 cross_device_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]: I0525 22:43:38.720545 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:38.731191 281473864070016 cross_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]: I0525 22:43:38.720446 281473864070016 cross_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]: I0525 22:43:38.901249 281473864070016 cross_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]: I0525 22:43:38.920402 281473864070016 cross_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]: I0525 22:43:38.915004 281473864070016 cross_device_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]: I0525 22:43:38.927212 281473864070016 cross_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]: I0525 22:43:39.042093 281473864070016 cross_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]: I0525 22:43:39.050529 281473864070016 cross_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]: I0525 22:43:39.051493 281473864070016 cross_device_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]: I0525 22:43:39.060786 281473864070016 cross_device_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-1]: I0525 22:43:39.186383 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:39.201878 281473864070016 cross_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]: I0525 22:43:39.210179 281473864070016 cross_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]: I0525 22:43:39.257039 281473864070016 cross_device_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]: I0525 22:43:39.447241 281473864070016 cross_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]: I0525 22:43:39.440442 281473864070016 cross_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]: I0525 22:43:39.440233 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:39.420542 281473864070016 cross_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]: I0525 22:43:39.640218 281473864070016 cross_device_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]: I0525 22:43:39.640278 281473864070016 cross_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]: I0525 22:43:39.687006 281473864070016 cross_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]: I0525 22:43:39.690683 281473864070016 cross_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-3]: INFO:tensorflow:epoch 1 finished [worker-3]: I0525 22:43:39.823796 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: I0525 22:43:39.818088 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0525 22:43:39.827218 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-2]: I0525 22:43:39.834438 281473864070016 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]: I0525 22:43:39.851566 281473864070016 cross_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]: I0525 22:43:39.880452 281473864070016 cross_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]: I0525 22:43:39.886929 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:39.870493 281473864070016 cross_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]: I0525 22:43:40.079737 281473864070016 cross_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]: I0525 22:43:40.079662 281473864070016 cross_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]: I0525 22:43:40.089443 281473864070016 cross_device_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]: I0525 22:43:40.156002 281473864070016 cross_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]: I0525 22:43:40.279854 281473864070016 cross_device_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]: I0525 22:43:40.299970 281473864070016 cross_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]: I0525 22:43:40.310507 281473864070016 cross_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]: I0525 22:43:40.325220 281473864070016 cross_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]: I0525 22:43:40.529498 281473864070016 cross_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]: I0525 22:43:40.519886 281473864070016 cross_device_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]: I0525 22:43:40.519935 281473864070016 cross_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]: I0525 22:43:40.549696 281473864070016 cross_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]: I0525 22:43:40.699480 281473864070016 cross_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]: I0525 22:43:40.699584 281473864070016 cross_device_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]: I0525 22:43:40.699571 281473864070016 cross_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]: I0525 22:43:40.721244 281473864070016 cross_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]: I0525 22:43:40.900043 281473864070016 cross_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]: I0525 22:43:40.909626 281473864070016 cross_device_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]: I0525 22:43:40.927712 281473864070016 cross_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]: I0525 22:43:40.967484 281473864070016 cross_device_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]: I0525 22:43:41.117911 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: I0525 22:43:41.112313 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-1]: I0525 22:43:41.126379 281473864070016 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]: I0525 22:43:41.140200 281473864070016 cross_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]: I0525 22:43:41.156393 281473864070016 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]: I0525 22:43:41.149910 281473864070016 cross_device_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]: I0525 22:43:41.159680 281473864070016 cross_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]: I0525 22:43:41.227283 281473864070016 cross_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]: I0525 22:43:41.396841 281473864070016 cross_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]: I0525 22:43:41.430087 281473864070016 cross_device_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]: I0525 22:43:41.441347 281473864070016 cross_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]: I0525 22:43:41.451105 281473864070016 cross_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]: I0525 22:43:41.630024 281473864070016 cross_device_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]: I0525 22:43:41.659724 281473864070016 cross_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]: I0525 22:43:41.659798 281473864070016 cross_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]: I0525 22:43:41.659700 281473864070016 cross_device_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]: I0525 22:43:41.809999 281473864070016 cross_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]: I0525 22:43:41.816916 281473864070016 cross_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]: I0525 22:43:41.832915 281473864070016 cross_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]: I0525 22:43:41.836893 281473864070016 cross_device_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]: I0525 22:43:42.000462 281473864070016 cross_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]: I0525 22:43:42.026776 281473864070016 cross_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]: I0525 22:43:42.066933 281473864070016 cross_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]: I0525 22:43:42.046923 281473864070016 cross_device_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]: I0525 22:43:42.250344 281473864070016 cross_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]: I0525 22:43:42.263007 281473864070016 cross_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]: I0525 22:43:42.290086 281473864070016 cross_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]: I0525 22:43:42.280521 281473864070016 cross_device_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]: I0525 22:43:42.437374 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:epoch 3 finished [worker-0]: I0525 22:43:42.466884 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-1]: I0525 22:43:42.477167 281473864070016 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]: I0525 22:43:42.470061 281473864070016 cross_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]: I0525 22:43:42.477300 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: I0525 22:43:42.479642 281473864070016 cross_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]: I0525 22:43:42.500006 281473864070016 cross_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]: I0525 22:43:42.530394 281473864070016 cross_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]: I0525 22:43:42.739697 281473864070016 cross_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]: I0525 22:43:42.750101 281473864070016 cross_device_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]: I0525 22:43:42.739701 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:42.736888 281473864070016 cross_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]: I0525 22:43:42.860209 281473864070016 cross_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]: I0525 22:43:42.877172 281473864070016 cross_device_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]: I0525 22:43:42.887094 281473864070016 cross_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]: I0525 22:43:42.870650 281473864070016 cross_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]: I0525 22:43:43.029988 281473864070016 cross_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]: I0525 22:43:43.058927 281473864070016 cross_device_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]: I0525 22:43:43.066160 281473864070016 cross_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]: I0525 22:43:43.047066 281473864070016 cross_device_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]: I0525 22:43:43.260150 281473864070016 cross_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]: I0525 22:43:43.270035 281473864070016 cross_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]: I0525 22:43:43.279567 281473864070016 cross_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]: I0525 22:43:43.300673 281473864070016 cross_device_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]: I0525 22:43:43.409940 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:43.410072 281473864070016 cross_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]: I0525 22:43:43.421074 281473864070016 cross_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]: I0525 22:43:43.429635 281473864070016 cross_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 4 finished [worker-1]: I0525 22:43:43.521914 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0525 22:43:43.522205 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:epoch 4 finished [worker-3]: INFO:tensorflow:epoch 4 finished [worker-3]: I0525 22:43:43.526425 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: I0525 22:43:43.520405 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-0]: INFO:tensorflow:Training finished. [worker-3]: I0525 22:43:43.526727 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-2]: INFO:tensorflow:epoch 4 finished [worker-0]: I0525 22:43:43.520744 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-2]: I0525 22:43:43.528373 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0525 22:43:43.528684 281473864070016 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:restarting workers I0525 22:43:45.646684 281473778480000 gce_failure_handler_test.py:411] restarting workers INFO:tensorflow:workers restarted I0525 22:43:45.786580 281473778480000 gce_failure_handler_test.py:415] workers restarted [worker-0]: I0525 22:43:46.040797 281473864070016 multi_process_runner.py:840] Subprocess with PID 2634365 (worker, 0) is now being started. [worker-0]: I0525 22:43:46.041378 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:44631", "localhost:39841", "localhost:44951", "localhost:33625"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0525 22:43:46.257844 281473864070016 multi_process_runner.py:840] Subprocess with PID 2634460 (worker, 1) is now being started. [worker-3]: I0525 22:43:46.368542 281473864070016 multi_process_runner.py:840] Subprocess with PID 2634510 (worker, 3) is now being started. [worker-1]: I0525 22:43:46.258419 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:44631", "localhost:39841", "localhost:44951", "localhost:33625"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:43:46.369139 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:44631", "localhost:39841", "localhost:44951", "localhost:33625"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:43:46.447899 281473864070016 multi_process_runner.py:840] Subprocess with PID 2634496 (worker, 2) is now being started. [worker-2]: I0525 22:43:46.448498 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:44631", "localhost:39841", "localhost:44951", "localhost:33625"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-25 22:43:46.606947: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:39841 [worker-0]: 2023-05-25 22:43:46.612409: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:44631 [worker-0]: 2023-05-25 22:43:46.629964: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 12192439021598645457 [worker-1]: 2023-05-25 22:43:46.636535: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:46.649653: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 10939644811084177506 [worker-0]: 2023-05-25 22:43:46.656408: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-3]: 2023-05-25 22:43:46.817694: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:33625 [worker-3]: 2023-05-25 22:43:46.826821: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:46.826348: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 6203703169050565811 [worker-2]: 2023-05-25 22:43:46.940340: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:44951 [worker-2]: 2023-05-25 22:43:46.946983: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:46.946547: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 14233959036324740269 [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]: I0525 22:43:46.997432 281473864070016 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-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]: I0525 22:43:47.007192 281473864070016 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]: I0525 22:43:47.017826 281473864070016 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]: I0525 22:43:47.115498 281473864070016 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]: I0525 22:43:47.116159 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:43:47.116401 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, 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: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-1]: I0525 22:43:47.160093 281473864070016 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]: I0525 22:43:47.160655 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:43:47.160916 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:43:47.136846 281473864070016 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]: I0525 22:43:47.180077 281473864070016 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]: I0525 22:43:47.180710 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:43:47.180961 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, 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]: I0525 22:43:47.268577 281473864070016 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]: I0525 22:43:47.269195 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:43:47.269441 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:44631', 'localhost:39841', 'localhost:44951', 'localhost:33625']}, 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]: I0525 22:43:47.388230 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: I0525 22:43:47.397413 281473864070016 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-1]: I0525 22:43:47.406888 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-0]: I0525 22:43:47.406911 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-3]: I0525 22:43:47.418156 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0525 22:43:47.429368 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0525 22:43:47.436176 281473864070016 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-1]: INFO:tensorflow:Start polling for termination signal. [worker-0]: W0525 22:43:47.436606 281473864070016 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-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0525 22:43:47.441751 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: I0525 22:43:47.436277 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0525 22:43:47.445042 281473864070016 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]: W0525 22:43:47.445509 281473864070016 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]: I0525 22:43:47.445727 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: INFO:tensorflow:Start training at 0 [worker-0]: I0525 22:43:47.436815 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-2]: self.run() [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-2]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-3]: Traceback (most recent call last): [worker-3]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0525 22:43:47.476205 281473864070016 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]: W0525 22:43:47.476696 281473864070016 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]: I0525 22:43:47.476920 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0525 22:43:47.477484 281473864070016 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]: W0525 22:43:47.477882 281473864070016 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]: I0525 22:43:47.478085 281473864070016 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]: I0525 22:43:47.652036 281473864070016 cross_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]: I0525 22:43:47.671639 281473864070016 cross_device_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]: I0525 22:43:47.682002 281473864070016 cross_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]: I0525 22:43:47.717907 281473864070016 cross_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]: I0525 22:43:47.850329 281473864070016 cross_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]: I0525 22:43:47.840919 281473864070016 cross_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]: I0525 22:43:47.860522 281473864070016 cross_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]: I0525 22:43:47.890437 281473864070016 cross_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]: I0525 22:43:47.956470 281473864070016 cross_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]: I0525 22:43:47.961799 281473864070016 cross_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]: I0525 22:43:47.962799 281473864070016 cross_device_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]: I0525 22:43:47.980246 281473864070016 cross_device_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]: I0525 22:43:48.094780 281473864070016 cross_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]: I0525 22:43:48.110833 281473864070016 cross_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]: I0525 22:43:48.110035 281473864070016 cross_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]: I0525 22:43:48.110086 281473864070016 cross_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]: I0525 22:43:48.200272 281473864070016 cross_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]: I0525 22:43:48.230560 281473864070016 cross_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]: I0525 22:43:48.239829 281473864070016 cross_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]: I0525 22:43:48.236951 281473864070016 cross_device_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 0xffffba64b6a0> 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]: W0525 22:43:48.327484 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64b6a0> 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 0xffff12a87a60> 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]: W0525 22:43:48.346643 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87a60> 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 0xffffba64ba60> 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 0xffff12a87a60> 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]: W0525 22:43:48.333075 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87a60> 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]: W0525 22:43:48.327825 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64ba60> 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]: I0525 22:43:48.350276 281473864070016 cross_device_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]: I0525 22:43:48.350277 281473864070016 cross_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]: I0525 22:43:48.360299 281473864070016 cross_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]: I0525 22:43:48.390729 281473864070016 cross_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 0xffff1598f600> 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 0xffffba670360> 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]: W0525 22:43:48.471016 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba670360> 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]: I0525 22:43:48.471389 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-2]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: W0525 22:43:48.476421 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: I0525 22:43:48.476797 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: W0525 22:43:48.476289 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: W0525 22:43:48.470873 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: I0525 22:43:48.476661 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-0]: INFO:tensorflow:epoch 0 finished [worker-0]: I0525 22:43:48.471305 281473864070016 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]: I0525 22:43:48.500667 281473864070016 cross_device_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]: I0525 22:43:48.500667 281473864070016 cross_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]: I0525 22:43:48.536916 281473864070016 cross_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]: I0525 22:43:48.546900 281473864070016 cross_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]: I0525 22:43:48.673358 281473864070016 cross_device_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]: I0525 22:43:48.666290 281473864070016 cross_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]: I0525 22:43:48.684504 281473864070016 cross_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]: I0525 22:43:48.707245 281473864070016 cross_device_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]: I0525 22:43:48.802801 281473864070016 cross_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]: I0525 22:43:48.829882 281473864070016 cross_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]: I0525 22:43:48.830246 281473864070016 cross_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]: I0525 22:43:48.830244 281473864070016 cross_device_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]: I0525 22:43:48.964826 281473864070016 cross_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]: I0525 22:43:48.990231 281473864070016 cross_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]: I0525 22:43:49.022067 281473864070016 cross_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]: I0525 22:43:49.020749 281473864070016 cross_device_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]: I0525 22:43:49.140751 281473864070016 cross_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-0]: I0525 22:43:49.150172 281473864070016 cross_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]: I0525 22:43:49.160057 281473864070016 cross_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]: I0525 22:43:49.151290 281473864070016 cross_device_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]: I0525 22:43:49.300343 281473864070016 cross_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]: I0525 22:43:49.340053 281473864070016 cross_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]: I0525 22:43:49.337048 281473864070016 cross_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]: I0525 22:43:49.366893 281473864070016 cross_device_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-0]: INFO:tensorflow:epoch 1 finished [worker-3]: I0525 22:43:49.472111 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-1]: I0525 22:43:49.483138 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: I0525 22:43:49.483538 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: I0525 22:43:49.477548 281473864070016 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]: I0525 22:43:49.500231 281473864070016 cross_device_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]: I0525 22:43:49.509900 281473864070016 cross_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]: I0525 22:43:49.509883 281473864070016 cross_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]: I0525 22:43:49.532043 281473864070016 cross_device_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]: I0525 22:43:49.650362 281473864070016 cross_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]: I0525 22:43:49.645114 281473864070016 cross_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]: I0525 22:43:49.657558 281473864070016 cross_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]: I0525 22:43:49.714096 281473864070016 cross_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]: I0525 22:43:49.891715 281473864070016 cross_device_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]: I0525 22:43:49.909125 281473864070016 cross_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]: I0525 22:43:49.906750 281473864070016 cross_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]: I0525 22:43:49.929522 281473864070016 cross_device_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]: I0525 22:43:50.124859 281473864070016 cross_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]: I0525 22:43:50.129808 281473864070016 cross_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]: I0525 22:43:50.140074 281473864070016 cross_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]: I0525 22:43:50.157218 281473864070016 cross_device_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]: I0525 22:43:50.289871 281473864070016 cross_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]: I0525 22:43:50.329462 281473864070016 cross_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]: I0525 22:43:50.309725 281473864070016 cross_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]: I0525 22:43:50.349750 281473864070016 cross_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]: I0525 22:43:50.486236 281473864070016 cross_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]: I0525 22:43:50.488883 281473864070016 cross_device_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]: I0525 22:43:50.489553 281473864070016 cross_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]: I0525 22:43:50.535141 281473864070016 cross_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-3]: INFO:tensorflow:epoch 2 finished [worker-1]: I0525 22:43:50.681929 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-3]: I0525 22:43:50.677067 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-0]: I0525 22:43:50.687275 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0525 22:43:50.686202 281473864070016 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]: I0525 22:43:50.699968 281473864070016 cross_device_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]: I0525 22:43:50.699945 281473864070016 cross_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]: I0525 22:43:50.720447 281473864070016 cross_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]: I0525 22:43:50.729601 281473864070016 cross_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]: I0525 22:43:50.879732 281473864070016 cross_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]: I0525 22:43:50.880199 281473864070016 cross_device_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]: I0525 22:43:50.903292 281473864070016 cross_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]: I0525 22:43:50.889504 281473864070016 cross_device_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]: I0525 22:43:51.139577 281473864070016 cross_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]: I0525 22:43:51.149970 281473864070016 cross_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]: I0525 22:43:51.170524 281473864070016 cross_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]: I0525 22:43:51.190756 281473864070016 cross_device_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]: I0525 22:43:51.359560 281473864070016 cross_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]: I0525 22:43:51.380255 281473864070016 cross_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]: I0525 22:43:51.385336 281473864070016 cross_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]: I0525 22:43:51.389190 281473864070016 cross_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]: I0525 22:43:51.470649 281473864070016 cross_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]: I0525 22:43:51.479387 281473864070016 cross_device_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]: I0525 22:43:51.479388 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:51.479387 281473864070016 cross_device_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]: I0525 22:43:51.649868 281473864070016 cross_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-2]: I0525 22:43:51.660006 281473864070016 cross_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]: I0525 22:43:51.659511 281473864070016 cross_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]: I0525 22:43:51.659480 281473864070016 cross_device_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]: I0525 22:43:51.787246 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: INFO:tensorflow:epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-1]: I0525 22:43:51.792429 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: I0525 22:43:51.797862 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: I0525 22:43:51.796531 281473864070016 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]: I0525 22:43:51.820042 281473864070016 cross_device_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]: I0525 22:43:51.830308 281473864070016 cross_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]: I0525 22:43:51.829774 281473864070016 cross_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]: I0525 22:43:51.861774 281473864070016 cross_device_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]: I0525 22:43:51.986878 281473864070016 cross_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]: I0525 22:43:51.999443 281473864070016 cross_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]: I0525 22:43:52.009438 281473864070016 cross_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]: I0525 22:43:52.049791 281473864070016 cross_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]: I0525 22:43:52.139537 281473864070016 cross_device_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]: I0525 22:43:52.141538 281473864070016 cross_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]: I0525 22:43:52.163830 281473864070016 cross_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]: I0525 22:43:52.139529 281473864070016 cross_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]: I0525 22:43:52.262494 281473864070016 cross_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]: I0525 22:43:52.249897 281473864070016 cross_device_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]: I0525 22:43:52.259506 281473864070016 cross_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]: I0525 22:43:52.286890 281473864070016 cross_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]: I0525 22:43:52.420656 281473864070016 cross_device_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]: I0525 22:43:52.430025 281473864070016 cross_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]: I0525 22:43:52.449429 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:52.432958 281473864070016 cross_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]: I0525 22:43:52.559651 281473864070016 cross_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]: I0525 22:43:52.559823 281473864070016 cross_device_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]: I0525 22:43:52.599429 281473864070016 cross_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]: I0525 22:43:52.589301 281473864070016 cross_device_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]: I0525 22:43:52.860529 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0525 22:43:52.860798 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:epoch 4 finished [worker-0]: I0525 22:43:52.866365 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0525 22:43:52.866611 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0525 22:43:52.870065 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0525 22:43:52.870307 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0525 22:43:52.863025 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0525 22:43:52.863275 281473864070016 gce_failure_handler_test.py:244] Training finished. I0525 22:43:53.732233 281473778480000 multi_process_runner.py:646] worker-0 exit code: 0 I0525 22:43:53.732492 281473778480000 multi_process_runner.py:646] worker-1 exit code: 0 I0525 22:43:53.732622 281473778480000 multi_process_runner.py:646] worker-2 exit code: 0 I0525 22:43:53.732734 281473778480000 multi_process_runner.py:646] worker-3 exit code: 0 I0525 22:43:53.735435 281473778480000 multi_process_runner.py:662] Joining log reading threads. I0525 22:43:53.735648 281473778480000 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_manager_strategyoption_MWMSmultiworker): 17.7s I0525 22:43:53.892493 281473778480000 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_0_inputarg_manager_strategyoption_MWMSmultiworker): 17.7s [ OK ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_0_inputarg_manager_strategyoption_MWMSmultiworker [ RUN ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_7_inputarg_manager_strategyoption_MWMSmultiworker INFO:tensorflow:Using local port 46393 I0525 22:43:53.894105 281473778480000 test_util.py:3796] Using local port 46393 INFO:tensorflow:Using local port 35161 I0525 22:43:53.894471 281473778480000 test_util.py:3796] Using local port 35161 INFO:tensorflow:Using local port 36147 I0525 22:43:53.894782 281473778480000 test_util.py:3796] Using local port 36147 INFO:tensorflow:Using local port 38773 I0525 22:43:53.895085 281473778480000 test_util.py:3796] Using local port 38773 INFO:tensorflow:Cluster starting. I0525 22:43:53.966398 281473778480000 gce_failure_handler_test.py:405] Cluster starting. [worker-1]: I0525 22:43:54.447738 281473864070016 multi_process_runner.py:840] Subprocess with PID 2645344 (worker, 1) is now being started. [worker-0]: I0525 22:43:54.467928 281473864070016 multi_process_runner.py:840] Subprocess with PID 2645263 (worker, 0) is now being started. [worker-1]: I0525 22:43:54.448208 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:46393", "localhost:35161", "localhost:36147", "localhost:38773"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-0]: I0525 22:43:54.468373 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:46393", "localhost:35161", "localhost:36147", "localhost:38773"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-3]: I0525 22:43:54.627749 281473864070016 multi_process_runner.py:840] Subprocess with PID 2645446 (worker, 3) is now being started. [worker-0]: 2023-05-25 22:43:54.628452: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:46393 [worker-2]: I0525 22:43:54.647436 281473864070016 multi_process_runner.py:840] Subprocess with PID 2645354 (worker, 2) is now being started. [worker-3]: I0525 22:43:54.628171 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:46393", "localhost:35161", "localhost:36147", "localhost:38773"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:43:54.647886 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:46393", "localhost:35161", "localhost:36147", "localhost:38773"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-25 22:43:54.687961: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:35161 [worker-0]: 2023-05-25 22:43:54.710065: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 13779229074995633351 [worker-1]: 2023-05-25 22:43:54.711258: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-0]: 2023-05-25 22:43:54.710217: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 1735341058571247903 [worker-0]: 2023-05-25 22:43:54.710799: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-2]: 2023-05-25 22:43:54.865216: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:36147 [worker-0]: 2023-05-25 22:43:54.886756: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 4606394111174835366 [worker-3]: 2023-05-25 22:43:54.896908: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:38773 [worker-0]: 2023-05-25 22:43:54.900689: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 13260570850168885148 [worker-3]: 2023-05-25 22:43:54.901050: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-2]: 2023-05-25 22:43:54.919621: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] 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]: I0525 22:43:54.936888 281473864070016 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-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-0]: I0525 22:43:54.957286 281473864070016 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]: I0525 22:43:54.938265 281473864070016 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:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0525 22:43:55.000994 281473864070016 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]: I0525 22:43:55.001479 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:43:55.001675 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, 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: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]: I0525 22:43:54.959990 281473864070016 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:Using MirroredStrategy with devices ('/job:worker/task:1/device:CPU:0',) [worker-1]: I0525 22:43:55.099017 281473864070016 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]: I0525 22:43:55.100143 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:43:55.101960 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, 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]: I0525 22:43:55.122566 281473864070016 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:0/device:CPU:0',) [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0525 22:43:55.125379 281473864070016 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-0]: INFO:tensorflow:Check health not enabled. [worker-3]: INFO:tensorflow:Check health not enabled. [worker-3]: I0525 22:43:55.125804 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: I0525 22:43:55.124808 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, 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:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:43:55.125996 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:43:55.125021 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0525 22:43:55.261984 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: I0525 22:43:55.262424 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0525 22:43:55.276172 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-3]: I0525 22:43:55.285016 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-2]: I0525 22:43:55.285776 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0525 22:43:55.296862 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-2]: self.run() [worker-2]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: AttributeError: 'str' object has no attribute 'is_set' [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-2]: I0525 22:43:55.326264 281473864070016 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]: W0525 22:43:55.326654 281473864070016 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]: I0525 22:43:55.326813 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0525 22:43:55.339077 281473864070016 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]: W0525 22:43:55.339442 281473864070016 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]: I0525 22:43:55.339601 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0525 22:43:55.346256 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0525 22:43:55.347228 281473864070016 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/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-1]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-1]: self.run() [worker-1]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0525 22:43:55.379044 281473864070016 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]: W0525 22:43:55.379415 281473864070016 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]: I0525 22:43:55.379577 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-1]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0525 22:43:55.381935 281473864070016 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]: W0525 22:43:55.382271 281473864070016 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]: I0525 22:43:55.382428 281473864070016 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]: I0525 22:43:55.520979 281473864070016 cross_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]: I0525 22:43:55.626883 281473864070016 cross_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]: I0525 22:43:55.673927 281473864070016 cross_device_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]: I0525 22:43:55.695243 281473864070016 cross_device_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]: I0525 22:43:55.876282 281473864070016 cross_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]: I0525 22:43:55.890507 281473864070016 cross_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]: I0525 22:43:55.919505 281473864070016 cross_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]: I0525 22:43:55.939682 281473864070016 cross_device_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]: I0525 22:43:56.079679 281473864070016 cross_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]: I0525 22:43:56.089529 281473864070016 cross_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]: I0525 22:43:56.126907 281473864070016 cross_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]: I0525 22:43:56.109628 281473864070016 cross_device_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]: I0525 22:43:56.209515 281473864070016 cross_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]: I0525 22:43:56.209515 281473864070016 cross_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]: I0525 22:43:56.222599 281473864070016 cross_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]: I0525 22:43:56.250003 281473864070016 cross_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]: I0525 22:43:56.383303 281473864070016 cross_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]: I0525 22:43:56.383298 281473864070016 cross_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]: I0525 22:43:56.392897 281473864070016 cross_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]: I0525 22:43:56.399465 281473864070016 cross_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 0xffff12a87920> 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 0xffffba64a480> 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]: W0525 22:43:56.526321 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64a480> 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]: W0525 22:43:56.516708 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87920> 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 0xffff12a87600> 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]: W0525 22:43:56.536543 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87600> 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]: I0525 22:43:56.543647 281473864070016 cross_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]: I0525 22:43:56.560611 281473864070016 cross_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 0xffff12a87c40> 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]: W0525 22:43:56.577024 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87c40> 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]: I0525 22:43:56.609371 281473864070016 cross_device_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]: I0525 22:43:56.629854 281473864070016 cross_device_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 0xffffba6704a0> 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 0xffff12a851c0> 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]: W0525 22:43:56.737354 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba6704a0> 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]: W0525 22:43:56.742023 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff12a851c0> 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-3]: INFO:tensorflow:epoch 0 finished [worker-0]: I0525 22:43:56.742301 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: I0525 22:43:56.737640 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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]: I0525 22:43:56.748640 281473864070016 cross_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 0xffffba670220> 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]: W0525 22:43:56.766685 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba670220> 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]: W0525 22:43:56.762043 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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-1]: INFO:tensorflow:epoch 0 finished [worker-2]: I0525 22:43:56.766975 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-1]: I0525 22:43:56.762345 281473864070016 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]: I0525 22:43:56.760062 281473864070016 cross_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]: I0525 22:43:56.779405 281473864070016 cross_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]: I0525 22:43:56.809831 281473864070016 cross_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]: I0525 22:43:56.929567 281473864070016 cross_device_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]: I0525 22:43:56.949456 281473864070016 cross_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]: I0525 22:43:56.963713 281473864070016 cross_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]: I0525 22:43:56.992193 281473864070016 cross_device_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]: I0525 22:43:57.044846 281473864070016 cross_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]: I0525 22:43:57.065765 281473864070016 cross_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]: I0525 22:43:57.066827 281473864070016 cross_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]: I0525 22:43:57.067570 281473864070016 cross_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]: I0525 22:43:57.256313 281473864070016 cross_device_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]: I0525 22:43:57.269368 281473864070016 cross_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]: I0525 22:43:57.289984 281473864070016 cross_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]: I0525 22:43:57.310027 281473864070016 cross_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-3]: I0525 22:43:57.499257 281473864070016 cross_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]: I0525 22:43:57.499250 281473864070016 cross_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]: I0525 22:43:57.489452 281473864070016 cross_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]: I0525 22:43:57.499263 281473864070016 cross_device_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]: I0525 22:43:57.629310 281473864070016 cross_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]: I0525 22:43:57.649281 281473864070016 cross_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]: I0525 22:43:57.639265 281473864070016 cross_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]: I0525 22:43:57.639259 281473864070016 cross_device_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]: I0525 22:43:57.778605 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0525 22:43:57.782463 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-1]: I0525 22:43:57.783268 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: INFO:tensorflow: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-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0525 22:43:57.783785 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: I0525 22:43:57.813013 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:57.799346 281473864070016 cross_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]: I0525 22:43:57.859028 281473864070016 cross_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]: I0525 22:43:57.869080 281473864070016 cross_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]: I0525 22:43:58.059357 281473864070016 cross_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]: I0525 22:43:58.069276 281473864070016 cross_device_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]: I0525 22:43:58.059357 281473864070016 cross_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]: I0525 22:43:58.089635 281473864070016 cross_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]: I0525 22:43:58.172276 281473864070016 cross_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]: I0525 22:43:58.246790 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:58.246706 281473864070016 cross_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]: I0525 22:43:58.279448 281473864070016 cross_device_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]: I0525 22:43:58.403275 281473864070016 cross_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]: I0525 22:43:58.411350 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:58.394639 281473864070016 cross_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]: I0525 22:43:58.419763 281473864070016 cross_device_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]: I0525 22:43:58.529720 281473864070016 cross_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]: I0525 22:43:58.539398 281473864070016 cross_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]: I0525 22:43:58.539398 281473864070016 cross_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]: I0525 22:43:58.569619 281473864070016 cross_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]: I0525 22:43:58.656983 281473864070016 cross_device_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]: I0525 22:43:58.657389 281473864070016 cross_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]: I0525 22:43:58.689659 281473864070016 cross_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]: I0525 22:43:58.689563 281473864070016 cross_device_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]: I0525 22:43:58.766972 281473864070016 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]: I0525 22:43:58.773663 281473864070016 cross_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 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0525 22:43:58.796429 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-1]: INFO:tensorflow:epoch 2 finished [worker-1]: I0525 22:43:58.797210 281473864070016 gce_failure_handler_test.py:192] epoch 2 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]: I0525 22:43:58.803097 281473864070016 cross_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]: I0525 22:43:58.778499 281473864070016 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]: I0525 22:43:58.785137 281473864070016 cross_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]: I0525 22:43:58.819300 281473864070016 cross_device_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]: I0525 22:43:58.993093 281473864070016 cross_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]: I0525 22:43:58.989402 281473864070016 cross_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]: I0525 22:43:59.000436 281473864070016 cross_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]: I0525 22:43:59.029373 281473864070016 cross_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-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-2]: I0525 22:43:59.104052 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:59.104142 281473864070016 cross_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]: I0525 22:43:59.104071 281473864070016 cross_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]: I0525 22:43:59.103338 281473864070016 cross_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]: I0525 22:43:59.225476 281473864070016 cross_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-3]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:43:59.245349 281473864070016 cross_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]: I0525 22:43:59.239709 281473864070016 cross_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]: I0525 22:43:59.221798 281473864070016 cross_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]: I0525 22:43:59.329438 281473864070016 cross_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]: I0525 22:43:59.323028 281473864070016 cross_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]: I0525 22:43:59.339620 281473864070016 cross_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]: I0525 22:43:59.329452 281473864070016 cross_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]: I0525 22:43:59.433768 281473864070016 cross_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]: I0525 22:43:59.450838 281473864070016 cross_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]: I0525 22:43:59.449418 281473864070016 cross_device_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]: I0525 22:43:59.469401 281473864070016 cross_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-1]: I0525 22:43:59.547016 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-2]: I0525 22:43:59.551190 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-3]: INFO:tensorflow:epoch 3 finished [worker-3]: I0525 22:43:59.556367 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-0]: I0525 22:43:59.535607 281473864070016 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]: I0525 22:43:59.579137 281473864070016 cross_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]: I0525 22:43:59.579149 281473864070016 cross_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]: I0525 22:43:59.589236 281473864070016 cross_device_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]: I0525 22:43:59.620025 281473864070016 cross_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]: I0525 22:43:59.859835 281473864070016 cross_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]: I0525 22:43:59.860053 281473864070016 cross_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]: I0525 22:43:59.859431 281473864070016 cross_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]: I0525 22:43:59.879231 281473864070016 cross_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]: I0525 22:43:59.965701 281473864070016 cross_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]: I0525 22:43:59.973312 281473864070016 cross_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]: I0525 22:43:59.981715 281473864070016 cross_device_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]: I0525 22:44:00.016836 281473864070016 cross_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]: I0525 22:44:00.129284 281473864070016 cross_device_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]: I0525 22:44:00.129286 281473864070016 cross_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]: I0525 22:44:00.146759 281473864070016 cross_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]: I0525 22:44:00.139287 281473864070016 cross_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]: I0525 22:44:00.259203 281473864070016 cross_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]: I0525 22:44:00.259203 281473864070016 cross_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]: I0525 22:44:00.270020 281473864070016 cross_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]: I0525 22:44:00.290061 281473864070016 cross_device_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-1]: I0525 22:44:00.449042 281473864070016 cross_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]: I0525 22:44:00.446618 281473864070016 cross_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]: I0525 22:44:00.444422 281473864070016 cross_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]: I0525 22:44:00.469575 281473864070016 cross_device_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]: I0525 22:44:00.538495 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0525 22:44:00.538779 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-0]: INFO:tensorflow:epoch 4 finished [worker-0]: I0525 22:44:00.556380 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: I0525 22:44:00.544783 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-0]: INFO:tensorflow:Training finished. [worker-1]: INFO:tensorflow:Training finished. [worker-0]: I0525 22:44:00.556641 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-1]: I0525 22:44:00.545052 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-2]: INFO:tensorflow:epoch 4 finished [worker-2]: I0525 22:44:00.556373 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0525 22:44:00.556637 281473864070016 gce_failure_handler_test.py:244] Training finished. INFO:tensorflow:restarting workers I0525 22:44:02.266648 281473778480000 gce_failure_handler_test.py:411] restarting workers INFO:tensorflow:workers restarted I0525 22:44:02.406469 281473778480000 gce_failure_handler_test.py:415] workers restarted [worker-0]: I0525 22:44:02.454616 281473864070016 multi_process_runner.py:840] Subprocess with PID 2654675 (worker, 0) is now being started. [worker-0]: I0525 22:44:02.455076 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:46393", "localhost:35161", "localhost:36147", "localhost:38773"]}, "task": {"type": "worker", "index": 0}, "rpc_layer": "grpc"}' [worker-1]: I0525 22:44:02.462750 281473864070016 multi_process_runner.py:840] Subprocess with PID 2654909 (worker, 1) is now being started. [worker-1]: I0525 22:44:02.463201 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:46393", "localhost:35161", "localhost:36147", "localhost:38773"]}, "task": {"type": "worker", "index": 1}, "rpc_layer": "grpc"}' [worker-2]: I0525 22:44:02.519149 281473864070016 multi_process_runner.py:840] Subprocess with PID 2654942 (worker, 2) is now being started. [worker-0]: 2023-05-25 22:44:02.584940: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:46393 [worker-0]: 2023-05-25 22:44:02.617493: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:0 has connected to coordination service. Incarnation: 6229173559074063876 [worker-0]: 2023-05-25 22:44:02.619471: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-2]: I0525 22:44:02.519633 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:46393", "localhost:35161", "localhost:36147", "localhost:38773"]}, "task": {"type": "worker", "index": 2}, "rpc_layer": "grpc"}' [worker-1]: 2023-05-25 22:44:02.638089: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:35161 [worker-3]: I0525 22:44:02.657294 281473864070016 multi_process_runner.py:840] Subprocess with PID 2654955 (worker, 3) is now being started. [worker-0]: 2023-05-25 22:44:02.736271: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:1 has connected to coordination service. Incarnation: 1394739257822918274 [worker-1]: 2023-05-25 22:44:02.737120: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-3]: I0525 22:44:02.657760 281473864070016 multi_process_runner.py:842] TF_CONFIG: '{"cluster": {"worker": ["localhost:46393", "localhost:35161", "localhost:36147", "localhost:38773"]}, "task": {"type": "worker", "index": 3}, "rpc_layer": "grpc"}' [worker-2]: 2023-05-25 22:44:02.789130: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:36147 [worker-0]: 2023-05-25 22:44:02.806490: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:2 has connected to coordination service. Incarnation: 4166046154705663209 [worker-2]: 2023-05-25 22:44:02.807278: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] Coordination agent has successfully connected. [worker-3]: 2023-05-25 22:44:03.015267: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:457] Started server with target: grpc://localhost:38773 [worker-0]: 2023-05-25 22:44:03.018594: I tensorflow/tsl/distributed_runtime/coordination/coordination_service.cc:535] /job:worker/replica:0/task:3 has connected to coordination service. Incarnation: 14602821147254326022 [worker-3]: 2023-05-25 22:44:03.019363: I tensorflow/tsl/distributed_runtime/coordination/coordination_service_agent.cc:299] 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]: I0525 22:44:03.037313 281473864070016 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]: I0525 22:44:03.022877 281473864070016 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]: I0525 22:44:03.057301 281473864070016 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]: I0525 22:44:03.101385 281473864070016 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]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:2/device:CPU:0',) [worker-2]: I0525 22:44:03.110446 281473864070016 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]: I0525 22:44:03.110951 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-2]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 2, num_workers = 4, local_devices = ('/job:worker/task:2/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-2]: I0525 22:44:03.111146 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, 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]: I0525 22:44:03.130854 281473864070016 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]: I0525 22:44:03.132080 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-0]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 0, num_workers = 4, local_devices = ('/job:worker/task:0/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-0]: I0525 22:44:03.132758 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, 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]: I0525 22:44:03.154692 281473864070016 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]: I0525 22:44:03.155740 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-1]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-1]: I0525 22:44:03.155941 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 1, num_workers = 4, local_devices = ('/job:worker/task:1/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: INFO:tensorflow:Using MirroredStrategy with devices ('/job:worker/task:3/device:CPU:0',) [worker-3]: I0525 22:44:03.221393 281473864070016 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]: I0525 22:44:03.222826 281473864070016 collective_all_reduce_strategy.py:574] Check health not enabled. [worker-3]: INFO:tensorflow:MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, task_type = 'worker', task_id = 3, num_workers = 4, local_devices = ('/job:worker/task:3/device:CPU:0',), communication = CommunicationImplementation.AUTO [worker-3]: I0525 22:44:03.223523 281473864070016 collective_all_reduce_strategy.py:576] MultiWorkerMirroredStrategy with cluster_spec = {'worker': ['localhost:46393', 'localhost:35161', 'localhost:36147', 'localhost:38773']}, 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:Start watcher for peer's signal. [worker-2]: I0525 22:44:03.338437 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: INFO:tensorflow:Start polling for termination signal. [worker-0]: INFO:tensorflow:Start watcher for peer's signal. [worker-0]: I0525 22:44:03.357091 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: INFO:tensorflow:Start watcher for peer's signal. [worker-1]: I0525 22:44:03.367892 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-2]: I0525 22:44:03.356761 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-3]: INFO:tensorflow:Start watcher for peer's signal. [worker-2]: Exception in thread WorkerTerminationSignalWatcher-2: [worker-2]: Traceback (most recent call last): [worker-2]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-0]: INFO:tensorflow:Start polling for termination signal. [worker-0]: I0525 22:44:03.376798 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: INFO:tensorflow:Start polling for termination signal. [worker-1]: I0525 22:44:03.386762 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-2]: self.run() [worker-0]: Exception in thread WorkerTerminationSignalWatcher-0: [worker-3]: I0525 22:44:03.367909 281473864070016 failure_handling.py:634] Start watcher for peer's signal. [worker-1]: Exception in thread WorkerTerminationSignalWatcher-1: [worker-2]: File "/usr/lib/python3.11/threading.py", line 975, in run [worker-1]: Traceback (most recent call last): [worker-3]: INFO:tensorflow:Start polling for termination signal. [worker-3]: I0525 22:44:03.386756 281473864070016 failure_handling.py:683] Start polling for termination signal. [worker-1]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-2]: self._target(*self._args, **self._kwargs) [worker-3]: Exception in thread WorkerTerminationSignalWatcher-3: [worker-1]: 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/failure_handling/failure_handling.py", line 692, in _poll_termination_signal [worker-3]: Traceback (most recent call last): [worker-1]: File "/usr/lib/python3.11/threading.py", line 975, in run [worker-1]: self._target(*self._args, **self._kwargs) [worker-2]: 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/failure_handling.py", line 692, in _poll_termination_signal [worker-2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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-1]: if self._termination_watcher_fn(): [worker-2]: elif frequent_send and not maintenance_event.is_set(): [worker-1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: ^^^^^^^^^^^^^^^^^^^^^^^^ [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]: AttributeError: 'str' object has no attribute 'is_set' [worker-1]: elif frequent_send and not maintenance_event.is_set(): [worker-2]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-2]: I0525 22:44:03.378093 281473864070016 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-1]: AttributeError: 'str' object has no attribute 'is_set' [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]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-1]: I0525 22:44:03.408097 281473864070016 failure_handling.py:538] PreemptionCheckpointHandler initialized or restored. [worker-2]: Instructions for updating: [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]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: W0525 22:44:03.378420 281473864070016 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-2]: Instructions for updating: [worker-1]: W0525 22:44:03.408445 281473864070016 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]: Track steps using a tf.Variable saved in checkpoint instead. [worker-2]: INFO:tensorflow:Start training at 0 [worker-1]: Instructions for updating: [worker-2]: I0525 22:44:03.378575 281473864070016 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]: I0525 22:44:03.408606 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-0]: Traceback (most recent call last): [worker-0]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-0]: self.run() [worker-0]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-0]: AttributeError: 'str' object has no attribute 'is_set' [worker-0]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-0]: I0525 22:44:03.398066 281473864070016 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]: W0525 22:44:03.398404 281473864070016 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]: I0525 22:44:03.398566 281473864070016 gce_failure_handler_test.py:194] Start training at 0 [worker-3]: File "/usr/lib/python3.11/threading.py", line 1038, in _bootstrap_inner [worker-3]: self.run() [worker-3]: File "/usr/lib/python3.11/threading.py", line 975, 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]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [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]: ^^^^^^^^^^^^^^^^^^^^^^^^ [worker-3]: AttributeError: 'str' object has no attribute 'is_set' [worker-3]: INFO:tensorflow:PreemptionCheckpointHandler initialized or restored. [worker-3]: I0525 22:44:03.424765 281473864070016 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]: W0525 22:44:03.425105 281473864070016 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]: I0525 22:44:03.425263 281473864070016 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]: I0525 22:44:03.588519 281473864070016 cross_device_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]: I0525 22:44:03.607067 281473864070016 cross_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]: I0525 22:44:03.665595 281473864070016 cross_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]: I0525 22:44:03.706750 281473864070016 cross_device_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-1]: INFO:tensorflow:Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-0]: I0525 22:44:03.907219 281473864070016 cross_device_ops.py:1152] Collective all_reduce tensors: 1 all_reduces, num_devices = 1, group_size = 4, implementation = CommunicationImplementation.AUTO, num_packs = 1 [worker-3]: I0525 22:44:03.889501 281473864070016 cross_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]: I0525 22:44:03.892121 281473864070016 cross_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]: I0525 22:44:03.910428 281473864070016 cross_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]: I0525 22:44:04.109694 281473864070016 cross_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]: I0525 22:44:04.119292 281473864070016 cross_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]: I0525 22:44:04.129280 281473864070016 cross_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]: I0525 22:44:04.199398 281473864070016 cross_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]: I0525 22:44:04.327163 281473864070016 cross_device_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]: I0525 22:44:04.349283 281473864070016 cross_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]: I0525 22:44:04.346609 281473864070016 cross_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]: I0525 22:44:04.347276 281473864070016 cross_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]: I0525 22:44:04.448046 281473864070016 cross_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]: I0525 22:44:04.448074 281473864070016 cross_device_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]: I0525 22:44:04.460208 281473864070016 cross_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]: I0525 22:44:04.459609 281473864070016 cross_device_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 0xffff12a87600> 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]: W0525 22:44:04.557642 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a87600> 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]: I0525 22:44:04.565012 281473864070016 cross_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 0xffffba64b740> 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 0xffffba64ba60> 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]: W0525 22:44:04.596421 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64b740> 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]: I0525 22:44:04.603168 281473864070016 cross_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 0xffff12a86d40> 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]: W0525 22:44:04.600453 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffff12a86d40> 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]: I0525 22:44:04.607073 281473864070016 cross_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]: W0525 22:44:04.596524 281473864070016 polymorphic_function.py:154] 5 out of the last 5 calls to .wrapped_fn at 0xffffba64ba60> 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]: I0525 22:44:04.607295 281473864070016 cross_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 0xffff1734fc40> 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]: W0525 22:44:04.648769 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1734fc40> 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]: I0525 22:44:04.649055 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: WARNING:tensorflow:6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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 0xffffba670220> 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]: W0525 22:44:04.648979 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba670220> 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-3]: W0525 22:44:04.648696 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffff1598f600> 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-1]: I0525 22:44:04.649264 281473864070016 gce_failure_handler_test.py:192] epoch 0 finished [worker-3]: I0525 22:44:04.648998 281473864070016 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]: I0525 22:44:04.655471 281473864070016 cross_device_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]: I0525 22:44:04.655797 281473864070016 cross_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 0xffffba670220> 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]: W0525 22:44:04.652673 281473864070016 polymorphic_function.py:154] 6 out of the last 6 calls to .wrapped_fn at 0xffffba670220> 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]: I0525 22:44:04.652960 281473864070016 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]: I0525 22:44:04.659289 281473864070016 cross_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]: I0525 22:44:04.699385 281473864070016 cross_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]: I0525 22:44:04.755438 281473864070016 cross_device_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]: I0525 22:44:04.769994 281473864070016 cross_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]: I0525 22:44:04.780028 281473864070016 cross_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]: I0525 22:44:04.795027 281473864070016 cross_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]: I0525 22:44:04.901872 281473864070016 cross_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]: I0525 22:44:04.905444 281473864070016 cross_device_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]: I0525 22:44:04.922807 281473864070016 cross_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]: I0525 22:44:04.919959 281473864070016 cross_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]: I0525 22:44:05.049356 281473864070016 cross_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]: I0525 22:44:05.059328 281473864070016 cross_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]: I0525 22:44:05.069329 281473864070016 cross_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]: I0525 22:44:05.050146 281473864070016 cross_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]: I0525 22:44:05.174880 281473864070016 cross_device_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]: I0525 22:44:05.180224 281473864070016 cross_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]: I0525 22:44:05.199773 281473864070016 cross_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]: I0525 22:44:05.219560 281473864070016 cross_device_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]: I0525 22:44:05.270003 281473864070016 cross_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]: I0525 22:44:05.271317 281473864070016 cross_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]: I0525 22:44:05.280814 281473864070016 cross_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]: I0525 22:44:05.289374 281473864070016 cross_device_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]: I0525 22:44:05.333558 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-1]: INFO:tensorflow:epoch 1 finished [worker-2]: INFO:tensorflow:epoch 1 finished [worker-1]: I0525 22:44:05.337251 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-2]: I0525 22:44:05.341201 281473864070016 gce_failure_handler_test.py:192] epoch 1 finished [worker-0]: INFO:tensorflow:epoch 1 finished [worker-0]: I0525 22:44:05.341484 281473864070016 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]: I0525 22:44:05.340787 281473864070016 cross_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]: I0525 22:44:05.348968 281473864070016 cross_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]: I0525 22:44:05.359460 281473864070016 cross_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]: I0525 22:44:05.369906 281473864070016 cross_device_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-3]: I0525 22:44:05.529261 281473864070016 cross_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]: I0525 22:44:05.549180 281473864070016 cross_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]: I0525 22:44:05.549178 281473864070016 cross_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]: I0525 22:44:05.569194 281473864070016 cross_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]: I0525 22:44:05.656064 281473864070016 cross_device_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]: I0525 22:44:05.669148 281473864070016 cross_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]: I0525 22:44:05.668571 281473864070016 cross_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]: I0525 22:44:05.669268 281473864070016 cross_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]: I0525 22:44:05.777799 281473864070016 cross_device_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]: I0525 22:44:05.782595 281473864070016 cross_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]: I0525 22:44:05.816793 281473864070016 cross_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]: I0525 22:44:05.811608 281473864070016 cross_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]: I0525 22:44:05.895004 281473864070016 cross_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]: I0525 22:44:05.907118 281473864070016 cross_device_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]: I0525 22:44:05.909270 281473864070016 cross_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]: I0525 22:44:05.929471 281473864070016 cross_device_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]: I0525 22:44:06.074594 281473864070016 cross_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]: I0525 22:44:06.090795 281473864070016 cross_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]: I0525 22:44:06.082612 281473864070016 cross_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]: I0525 22:44:06.109154 281473864070016 cross_device_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]: I0525 22:44:06.227151 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-0]: INFO:tensorflow:epoch 2 finished [worker-0]: I0525 22:44:06.231727 281473864070016 gce_failure_handler_test.py:192] epoch 2 finished [worker-2]: INFO:tensorflow:epoch 2 finished [worker-2]: I0525 22:44:06.236366 281473864070016 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]: I0525 22:44:06.237572 281473864070016 cross_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]: I0525 22:44:06.236162 281473864070016 gce_failure_handler_test.py:192] epoch 2 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]: I0525 22:44:06.242427 281473864070016 cross_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]: I0525 22:44:06.249202 281473864070016 cross_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]: I0525 22:44:06.259763 281473864070016 cross_device_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]: I0525 22:44:06.342147 281473864070016 cross_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]: I0525 22:44:06.359438 281473864070016 cross_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]: I0525 22:44:06.399102 281473864070016 cross_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]: I0525 22:44:06.399094 281473864070016 cross_device_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]: I0525 22:44:06.502739 281473864070016 cross_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]: I0525 22:44:06.499246 281473864070016 cross_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]: I0525 22:44:06.519181 281473864070016 cross_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]: I0525 22:44:06.618148 281473864070016 cross_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]: I0525 22:44:06.779773 281473864070016 cross_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]: I0525 22:44:06.779371 281473864070016 cross_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]: I0525 22:44:06.791101 281473864070016 cross_device_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]: I0525 22:44:06.869132 281473864070016 cross_device_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]: I0525 22:44:06.999150 281473864070016 cross_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]: I0525 22:44:07.009212 281473864070016 cross_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]: I0525 22:44:07.019237 281473864070016 cross_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]: I0525 22:44:07.029079 281473864070016 cross_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]: I0525 22:44:07.099921 281473864070016 cross_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]: I0525 22:44:07.112774 281473864070016 cross_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]: I0525 22:44:07.109329 281473864070016 cross_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]: I0525 22:44:07.129251 281473864070016 cross_device_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]: I0525 22:44:07.210597 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: INFO:tensorflow:epoch 3 finished [worker-1]: INFO:tensorflow:epoch 3 finished [worker-0]: INFO:tensorflow:epoch 3 finished [worker-0]: I0525 22:44:07.216459 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-1]: I0525 22:44:07.216472 281473864070016 gce_failure_handler_test.py:192] epoch 3 finished [worker-2]: I0525 22:44:07.219632 281473864070016 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]: I0525 22:44:07.234772 281473864070016 cross_device_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]: I0525 22:44:07.229324 281473864070016 cross_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]: I0525 22:44:07.243714 281473864070016 cross_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]: I0525 22:44:07.249250 281473864070016 cross_device_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]: I0525 22:44:07.322203 281473864070016 cross_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]: I0525 22:44:07.333198 281473864070016 cross_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]: I0525 22:44:07.336748 281473864070016 cross_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]: I0525 22:44:07.353941 281473864070016 cross_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]: I0525 22:44:07.399787 281473864070016 cross_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]: I0525 22:44:07.399850 281473864070016 cross_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]: I0525 22:44:07.439316 281473864070016 cross_device_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]: I0525 22:44:07.459827 281473864070016 cross_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]: I0525 22:44:07.570069 281473864070016 cross_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]: I0525 22:44:07.617567 281473864070016 cross_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]: I0525 22:44:07.658825 281473864070016 cross_device_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]: I0525 22:44:07.729547 281473864070016 cross_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]: I0525 22:44:07.809039 281473864070016 cross_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]: I0525 22:44:07.826823 281473864070016 cross_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]: I0525 22:44:07.808577 281473864070016 cross_device_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]: I0525 22:44:07.830166 281473864070016 cross_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]: I0525 22:44:07.949239 281473864070016 cross_device_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]: I0525 22:44:07.969755 281473864070016 cross_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]: I0525 22:44:08.009141 281473864070016 cross_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]: I0525 22:44:08.030054 281473864070016 cross_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-2]: INFO:tensorflow:epoch 4 finished [worker-0]: I0525 22:44:08.096015 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: I0525 22:44:08.097326 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-2]: INFO:tensorflow:Training finished. [worker-2]: I0525 22:44:08.097558 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-0]: INFO:tensorflow:Training finished. [worker-0]: I0525 22:44:08.097818 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-1]: INFO:tensorflow:epoch 4 finished [worker-1]: I0525 22:44:08.102937 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-1]: INFO:tensorflow:Training finished. [worker-1]: I0525 22:44:08.103158 281473864070016 gce_failure_handler_test.py:244] Training finished. [worker-3]: INFO:tensorflow:epoch 4 finished [worker-3]: I0525 22:44:08.104330 281473864070016 gce_failure_handler_test.py:192] epoch 4 finished [worker-3]: INFO:tensorflow:Training finished. [worker-3]: I0525 22:44:08.104555 281473864070016 gce_failure_handler_test.py:244] Training finished. I0525 22:44:09.366680 281473778480000 multi_process_runner.py:646] worker-0 exit code: 0 I0525 22:44:09.366902 281473778480000 multi_process_runner.py:646] worker-1 exit code: 0 I0525 22:44:09.367013 281473778480000 multi_process_runner.py:646] worker-2 exit code: 0 I0525 22:44:09.367116 281473778480000 multi_process_runner.py:646] worker-3 exit code: 0 I0525 22:44:09.369520 281473778480000 multi_process_runner.py:662] Joining log reading threads. I0525 22:44:09.369699 281473778480000 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_manager_strategyoption_MWMSmultiworker): 15.69s I0525 22:44:09.584623 281473778480000 test_util.py:2464] time(__main__.GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_7_inputarg_manager_strategyoption_MWMSmultiworker): 15.69s [ OK ] GceFailureHandlingTest.test_multiple_workers_preempted_consecutively_test_apiwrappingtrain_True_graceperiod_7_inputarg_manager_strategyoption_MWMSmultiworker ====================================================================== FAIL: test_basic_run_test_inputarg_manager_strategyoption_MWMSmultiworker (__main__.GceFailureHandlingTest) GceFailureHandlingTest.test_basic_run_test_inputarg_manager_strategyoption_MWMSmultiworker test_basic_run_test_inputarg_manager_strategyoption_MWMSmultiworker(input_arg='manager', 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/python3.11/unittest/case.py", line 703, in fail raise self.failureException(msg) ^^^^^^^^^^^^^^^^^ AssertionError: [] has length of 0. ---------------------------------------------------------------------- Ran 7 tests in 108.048s FAILED (failures=1) ================================================================================ //tensorflow/c:c_api_experimental_test PASSED in 37.6s //tensorflow/c:c_api_function_test PASSED in 38.8s //tensorflow/c:c_api_test_cpu PASSED in 41.0s //tensorflow/c:c_test PASSED in 37.2s //tensorflow/c:env_test_cpu PASSED in 26.6s //tensorflow/c:kernels_test_cpu PASSED in 37.8s //tensorflow/c:ops_test PASSED in 28.9s //tensorflow/c:while_loop_test PASSED in 40.4s //tensorflow/c/eager:c_api_cluster_test_cpu PASSED in 39.2s //tensorflow/c/eager:c_api_remote_function_test_cpu PASSED in 42.2s //tensorflow/c/eager:c_api_remote_test_cpu PASSED in 45.5s //tensorflow/c/eager:c_api_test_cpu PASSED in 42.5s //tensorflow/c/eager:custom_device_test PASSED in 32.8s //tensorflow/c/eager/parallel_device:parallel_device_lib_test PASSED in 35.8s //tensorflow/c/eager/parallel_device:parallel_device_remote_test PASSED in 41.2s //tensorflow/c/eager/parallel_device:parallel_device_test PASSED in 37.8s //tensorflow/c/experimental/filesystem/plugins/gcs:expiring_lru_cache_test PASSED in 0.7s //tensorflow/c/experimental/filesystem/plugins/gcs:ram_file_block_cache_test PASSED in 3.2s //tensorflow/c/experimental/grappler:grappler_test PASSED in 37.6s //tensorflow/c/experimental/ops/gen/common:case_format_test PASSED in 1.5s //tensorflow/c/experimental/ops/gen/cpp:cpp_generator_test PASSED in 1.1s //tensorflow/c/experimental/ops/gen/cpp/renderers:renderer_test PASSED in 0.7s //tensorflow/c/experimental/saved_model/core:constant_loading_test PASSED in 13.1s //tensorflow/c/experimental/saved_model/core:object_graph_traversal_test PASSED in 15.2s //tensorflow/c/experimental/saved_model/core:saved_variable_loading_test PASSED in 32.0s //tensorflow/c/experimental/saved_model/core:signature_flattening_test PASSED in 13.5s //tensorflow/c/experimental/saved_model/core:tf_concrete_function_loading_test PASSED in 15.6s //tensorflow/c/experimental/saved_model/core/ops:restore_ops_test PASSED in 16.0s //tensorflow/c/experimental/saved_model/core/ops:variable_ops_test PASSED in 20.5s //tensorflow/c/experimental/saved_model/internal:saved_model_api_test PASSED in 39.7s //tensorflow/c/experimental/stream_executor:stream_executor_test PASSED in 0.5s //tensorflow/c/kernels:bitcast_op_test PASSED in 0.6s //tensorflow/c/kernels:summary_op_benchmark_test PASSED in 0.8s //tensorflow/c/kernels:summary_op_test PASSED in 1.4s //tensorflow/c/kernels:tensor_shape_utils_test PASSED in 0.5s //tensorflow/cc:cc_op_gen_test PASSED in 0.3s //tensorflow/cc:client_client_session_test PASSED in 2.1s //tensorflow/cc:coordinator_test PASSED in 4.7s //tensorflow/cc:framework_cc_ops_test PASSED in 1.7s //tensorflow/cc:framework_gradient_checker_test PASSED in 3.6s //tensorflow/cc:framework_gradients_test PASSED in 4.2s //tensorflow/cc:framework_scope_test PASSED in 0.6s //tensorflow/cc:framework_while_gradients_test PASSED in 4.7s //tensorflow/cc:gradients_array_grad_test PASSED in 6.5s //tensorflow/cc:gradients_data_flow_grad_test PASSED in 2.4s //tensorflow/cc:gradients_functional_grad_test PASSED in 2.5s //tensorflow/cc:gradients_image_grad_test PASSED in 11.4s //tensorflow/cc:gradients_linalg_grad_test PASSED in 4.8s //tensorflow/cc:gradients_manip_grad_test PASSED in 2.6s //tensorflow/cc:gradients_math_grad_test PASSED in 6.2s //tensorflow/cc:gradients_nn_grad_test PASSED in 3.0s //tensorflow/cc:gradients_resource_variable_grad_test PASSED in 2.2s //tensorflow/cc:ops_const_op_test PASSED in 1.4s //tensorflow/cc:ops_while_loop_test PASSED in 2.1s //tensorflow/cc:queue_runner_test PASSED in 12.1s //tensorflow/cc/experimental/base/tests:tensor_test PASSED in 0.5s //tensorflow/cc/experimental/base/tests:tensorhandle_test PASSED in 36.1s //tensorflow/cc/experimental/libexport:load_test PASSED in 0.4s //tensorflow/cc/experimental/libexport:save_test PASSED in 1.1s //tensorflow/cc/experimental/libtf:libtf_module_test PASSED in 42.1s //tensorflow/cc/experimental/libtf:libtf_object_test PASSED in 0.1s //tensorflow/cc/experimental/libtf:libtf_perf_test PASSED in 0.7s //tensorflow/cc/experimental/libtf:libtf_runtime_test PASSED in 36.2s //tensorflow/cc/experimental/libtf:libtf_transform_test PASSED in 36.4s //tensorflow/cc/experimental/libtf:libtf_value_test PASSED in 0.6s //tensorflow/cc/experimental/libtf:libtf_visit_test PASSED in 0.2s //tensorflow/cc/experimental/libtf/impl:iostream_test PASSED in 0.7s //tensorflow/cc/experimental/libtf/impl:none_test PASSED in 0.3s //tensorflow/cc/experimental/libtf/impl:scalars_test PASSED in 0.1s //tensorflow/cc/experimental/libtf/impl:string_test PASSED in 0.4s //tensorflow/cc/experimental/libtf/impl:tensor_spec_test PASSED in 0.1s //tensorflow/cc/saved_model:bundle_v2_test PASSED in 0.5s //tensorflow/cc/saved_model:fingerprinting_test PASSED in 2.2s //tensorflow/cc/saved_model:metrics_test PASSED in 0.1s //tensorflow/cc/saved_model:reader_test PASSED in 0.3s //tensorflow/cc/saved_model:saved_model_bundle_lite_test PASSED in 9.7s //tensorflow/cc/saved_model:saved_model_bundle_test PASSED in 6.3s //tensorflow/cc/saved_model:util_test PASSED in 0.2s //tensorflow/cc/saved_model/experimental/tests:saved_model_api_test PASSED in 38.0s //tensorflow/cc/tools:freeze_saved_model_test PASSED in 2.4s //tensorflow/compiler/aot:codegen_test PASSED in 46.4s //tensorflow/compiler/jit:compilability_check_util_test PASSED in 28.0s //tensorflow/compiler/jit:deadness_analysis_test PASSED in 11.1s //tensorflow/compiler/jit:device_compilation_cache_test PASSED in 8.1s //tensorflow/compiler/jit:device_compilation_cluster_signature_test PASSED in 7.0s //tensorflow/compiler/jit:device_compilation_profiler_test PASSED in 25.3s //tensorflow/compiler/jit:device_compiler_client_test PASSED in 6.1s //tensorflow/compiler/jit:device_compiler_disable_test PASSED in 25.0s //tensorflow/compiler/jit:device_executable_persistor_test PASSED in 26.8s //tensorflow/compiler/jit:device_util_test PASSED in 6.1s //tensorflow/compiler/jit:encapsulate_util_test PASSED in 0.5s //tensorflow/compiler/jit:node_matchers_test PASSED in 1.2s //tensorflow/compiler/jit:resource_operation_safety_analysis_test PASSED in 10.6s //tensorflow/compiler/jit:shape_inference_test PASSED in 0.8s //tensorflow/compiler/jit:xla_activity_listener_test PASSED in 25.3s //tensorflow/compiler/jit:xla_cluster_util_test PASSED in 13.3s //tensorflow/compiler/jit:xla_compile_util_test PASSED in 6.7s //tensorflow/compiler/jit:xla_kernel_creator_test PASSED in 10.9s //tensorflow/compiler/jit:xla_launch_util_test PASSED in 26.8s //tensorflow/compiler/jit/tests:auto_clustering_test PASSED in 37.7s //tensorflow/compiler/mlir:mlir_graph_optimization_pass_test PASSED in 14.6s //tensorflow/compiler/mlir:register_common_dialects_test PASSED in 21.8s //tensorflow/compiler/mlir/lite:lstm_utils_test PASSED in 0.7s //tensorflow/compiler/mlir/lite:perception_ops_utils_test PASSED in 1.5s //tensorflow/compiler/mlir/lite:size_utils_test PASSED in 0.1s //tensorflow/compiler/mlir/lite:tftext_utils_test PASSED in 1.4s //tensorflow/compiler/mlir/lite/experimental/remat:rematerializer_test PASSED in 2.5s //tensorflow/compiler/mlir/lite/experimental/tac:execution_metadata_exporter_test PASSED in 3.1s //tensorflow/compiler/mlir/lite/experimental/tac/tests:compute-cost.mlir.test PASSED in 2.2s //tensorflow/compiler/mlir/lite/experimental/tac/tests:device-transform-gpu.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/experimental/tac/tests:device-transform-nnapi.mlir.test PASSED in 0.7s //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 0.6s //tensorflow/compiler/mlir/lite/experimental/tac/tests:get-op-cost.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/experimental/tac/tests:pick-subgraphs.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/experimental/tac/tests:raise-target-subgraphs.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/experimental/tac/tests:tac-filter.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/experimental/tac/tests:target-annotation.mlir.test PASSED in 0.7s //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 0.8s //tensorflow/compiler/mlir/lite/metrics:error_collector_inst_test PASSED in 0.4s //tensorflow/compiler/mlir/lite/quantization:numerical_utils_test PASSED in 0.5s //tensorflow/compiler/mlir/lite/quantization/lite:quantize_model_test PASSED in 14.9s //tensorflow/compiler/mlir/lite/quantization/lite:quantize_weights_test PASSED in 14.7s //tensorflow/compiler/mlir/lite/quantization/tensorflow/tests:fallback_to_flex_ops_default.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/quantization/tensorflow/tests:fallback_to_flex_ops_legacy.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/quantization/tensorflow/tests:tf_to_quant.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/quantization/tensorflow/tests:tf_to_quant_4bit.mlir.test PASSED in 2.2s //tensorflow/compiler/mlir/lite/quantization/tests:import_quant_stats.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/sparsity:sparsify_model_test PASSED in 0.8s //tensorflow/compiler/mlir/lite/stablehlo/tests:fold_broadcast.mlir.test PASSED in 1.1s //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 0.8s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-skip-quantization-ops.mlir.test PASSED in 4.2s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tf-fb-tf.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-add.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-broadcast_in_dim.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-clamp.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-compare.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-concat.mlir.test PASSED in 0.5s //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 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-dot.mlir.test PASSED in 1.4s //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 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-mul.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-pad.mlir.test PASSED in 0.5s //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 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-scatter.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl-sub.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-stablehlo-tfl.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-add.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-broadcast.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-clamp.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-concat.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-constant.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-conv.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-max.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-mul.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-pad.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-reshape.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-rsqrt.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo-sub.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:legalize-tfl-stablehlo.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:odml-to-stablehlo-allow-tf.mlir.test PASSED in 2.0s //tensorflow/compiler/mlir/lite/stablehlo/tests:odml-to-stablehlo-smuggle-resize.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/stablehlo/tests:optimize.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-clamp.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-concat.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-conv.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-division.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-logistic.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-serialize-stablehlo-multiply.mlir.test PASSED in 1.1s //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 1.4s //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 0.7s //tensorflow/compiler/mlir/lite/stablehlo/tests:tf-tfl-translate-tf-quantize.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/stablehlo/tests:unfuse_mhlo_batch_norm.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:analyze-variables.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:canonicalize.mlir.test PASSED in 0.6s //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 0.6s //tensorflow/compiler/mlir/lite/tests:default_quant_params.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/lite/tests:dilated-conv.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests:fuse-tftext.mlir.test PASSED in 0.9s //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 0.6s //tensorflow/compiler/mlir/lite/tests:inlining.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:insert_call_once_op.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:legalize-tf-assert.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests:legalize-tf-hashtables.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:legalize-tf-no-runtime-verification.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests:legalize-tf-variables.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:legalize-tf-while.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:legalize-tf.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/lite/tests:legalize_jax_random.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:lift_tflite_flex_ops.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/lite/tests:lower-static-tensor-list-default-to-single-batch.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:lower-static-tensor-list-enable-dynamic-update-slice.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests:lower-static-tensor-list.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:modify_io_nodes.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/tests:ops.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:optimize-after-quantization.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests:optimize.mlir.test PASSED in 2.8s //tensorflow/compiler/mlir/lite/tests:optimize_functional_ops.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:optimize_no_verify.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:optimize_op_order.mlir.test PASSED in 0.5s //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 1.1s //tensorflow/compiler/mlir/lite/tests:post-quantize-dynamic-range.mlir.test PASSED in 2.1s //tensorflow/compiler/mlir/lite/tests:post-quantize.mlir.test PASSED in 0.8s //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 2.1s //tensorflow/compiler/mlir/lite/tests:prepare-quantize-post-training-16bits.mlir.test PASSED in 2.2s //tensorflow/compiler/mlir/lite/tests:prepare-quantize-post-training.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/tests:prepare-quantize-signed.mlir.test PASSED in 2.2s //tensorflow/compiler/mlir/lite/tests:prepare-quantize.mlir.test PASSED in 2.1s //tensorflow/compiler/mlir/lite/tests:prepare-tf-fake-quant-4bit.mlir.test PASSED in 2.1s //tensorflow/compiler/mlir/lite/tests:prepare-tf-fake-quant.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:prepare-tf-with-allowing-bf16-and-f16-type-legalization.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests:prepare-tf.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests:quantize-dynamic-range.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/tests:quantize-numeric-verify.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests:quantize-variables.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests:quantize.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/tests:raise-custom-ops.mlir.test PASSED in 2.1s //tensorflow/compiler/mlir/lite/tests:reduce_while_operands.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests:shape-inference.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests:split-merged-operands.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests:tfl_while_op_licm.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests:tfl_while_outline.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests:trim-functions-tf.mlir.test PASSED in 2.0s //tensorflow/compiler/mlir/lite/tests:unfold-large-splat-constant.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/debuginfo:v1_1.0_224_frozen.wrong_attr.line.part.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/debuginfo:v1_1.0_224_frozen.wrong_attr.stack.part.pbtxt.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/end2end:add.pbtxt.test PASSED in 1.6s //tensorflow/compiler/mlir/lite/tests/end2end:back2back_fake_quant.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/end2end:control_flow_v1.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/end2end:conv_2d.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/lite/tests/end2end:conv_2d_nchw.pbtxt.test PASSED in 10.6s //tensorflow/compiler/mlir/lite/tests/end2end:custom_opdef.pbtxt.test PASSED in 0.7s //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 2.2s //tensorflow/compiler/mlir/lite/tests/end2end:fake_quant_per_channel_4bit.pbtxt.test PASSED in 2.3s //tensorflow/compiler/mlir/lite/tests/end2end:fake_quant_without_identity.pbtxt.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/end2end:fake_quant_without_identity_4bit.pbtxt.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/end2end:graph-input-node.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/end2end:graph_with_placeholder_with_default.pbtxt.test PASSED in 2.2s //tensorflow/compiler/mlir/lite/tests/end2end:if_op.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/end2end:quant_stats.pbtxt.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/end2end:unroll_batch_matmul.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/end2end:unroll_batch_matmul_disabled.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:basic_lstm.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:bucketize.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:constants.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:control_edges.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:custom_op.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:dynamic_shape.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:empty_input_output_names.json.test PASSED in 1.8s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:external_constant.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:if_op.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:import_json.json.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:importer_test_min_max.cc.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:importer_test_min_max.cc.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:input_arrays.mlir.test PASSED in 1.8s //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 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:lstm.json.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:lstm.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:many_attribute_op.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:math.mlir.test PASSED in 0.6s //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 0.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:optional.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:optional_input.json.test PASSED in 1.3s //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 0.6s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:pruning_function_input_as_output.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:quant_stats.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:quantization.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:reshape.mlir.test PASSED in 0.4s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:signature.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:signature_with_multiple_entry_points.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:simple.mlir.test PASSED in 0.7s //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 1.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:unranked_tensor.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir:while_op.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2exec:tfl_while_op.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:basic_lstm.mlir.test PASSED in 2.1s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:bucketize.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:custom_op_with_tflite_op.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:depthwise_conv2d.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:depthwise_conv2d_v2.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:disable_builtin.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:disable_custom.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:disable_flex.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:disable_flex_enable_builtin.mlir.test PASSED in 1.1s //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 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:flex_exclusively.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:flex_op_with_complex128.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:flex_op_with_f64.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:flex_op_with_tflite_op.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:fully_connected.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:fully_connected_v2.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:hashtable_resource.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:if_op.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:logical.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:low_bit_packing.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:lstm.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:lstm_asym_attr.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:lstm_quantized.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:math.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:metadata.mlir.test PASSED in 0.4s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:mul_v2.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:mul_v3.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:nn.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:numeric_verify.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:optional.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:quantization.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:reshape.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:signature_def.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:signature_def_output_override.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:signature_def_with_multiple_entry_points.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:signature_def_with_no_inputs.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:simple.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:simple_with_connected_control_nodes.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:simple_with_unconnected_control_nodes.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:svdf.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:svdf_v2.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:tf_entry_function.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:tfl_while_op.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:transpose_conv_optional.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:type_attr.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:unidirectional_sequence_lstm.mlir.test PASSED in 0.4s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:unidirectional_sequence_rnn.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:unranked_tensor.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:unsorted_segment_prod.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:variant_type_on_func.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:variant_type_on_op.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer:while_op.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/quantization/stablehlo/tests:fill_quantization_options_test PASSED in 0.2s //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 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/cc:convert_asset_args_test PASSED in 7.9s //tensorflow/compiler/mlir/quantization/tensorflow/cc:save_variables_test PASSED in 0.5s //tensorflow/compiler/mlir/quantization/tensorflow/cc:status_macro_test PASSED in 0.1s //tensorflow/compiler/mlir/quantization/tensorflow/debugging:mlir_dump_test PASSED in 0.4s //tensorflow/compiler/mlir/quantization/tensorflow/python:concurrency_test PASSED in 44.2s //tensorflow/compiler/mlir/quantization/tensorflow/python:pywrap_quantize_model_test PASSED in 16.1s //tensorflow/compiler/mlir/quantization/tensorflow/python:representative_dataset_test PASSED in 8.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:cast_bf16_ops_to_f32.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:convert_custom_aggregation_op_to_quant_stats.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:convert_fake_quant_to_qdq.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/quantization/tensorflow/tests:convert_tf_quant_ops_to_mhlo.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/quantization/tensorflow/tests:convert_tpu_model_to_cpu.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:duplicate_shape_determining_constants.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/quantization/tensorflow/tests:fake_quant_e2e_flow.mlir.test PASSED in 1.1s //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 1.4s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_main_function.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_quantized_functions.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_quantized_functions_drq.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_quantized_functions_weight_only.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:insert_restore_op.mlir.test PASSED in 1.1s //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 1.4s //tensorflow/compiler/mlir/quantization/tensorflow/tests:lift_quantizable_spots_as_functions.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:lift_quantizable_spots_as_functions_drq.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/quantization/tensorflow/tests:lift_quantizable_spots_as_functions_drq_min_elements.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/quantization/tensorflow/tests:lift_quantizable_spots_as_functions_xla.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:mark_functions_noinline.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:merge_initializer_function_ops_to_main.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/quantization/tensorflow/tests:merge_save_function_ops_to_main.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/quantization/tensorflow/tests:optimize.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_lifting.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize_drq.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize_drq_per_channel.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize_ptq.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/quantization/tensorflow/tests:prepare_quantize_ptq_per_channel.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/quantization/tensorflow/tests:preprocess_op.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/quantization/tensorflow/tests:preprocess_op_weight_only.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_composite_functions.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_composite_functions_drq.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_composite_functions_weight_only.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_composite_functions_xla.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_drq.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/quantization/tensorflow/tests:quantize_xla.mlir.test PASSED in 0.9s //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 1.1s //tensorflow/compiler/mlir/quantization/tensorflow/tests:replace_cast_hacks_with_tf_xla_ops_large_constants.mlir.test PASSED in 17.0s //tensorflow/compiler/mlir/quantization/tensorflow/tests:unfreeze_constants.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/quantization/tensorflow/utils:tf_to_xla_attribute_utils_test PASSED in 41.9s //tensorflow/compiler/mlir/stablehlo:stablehlo_test PASSED in 0.3s //tensorflow/compiler/mlir/tensorflow:bridge_logger_test PASSED in 8.4s //tensorflow/compiler/mlir/tensorflow:cluster_util_test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow:convert_tensor_test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow:convert_type_test PASSED in 0.2s //tensorflow/compiler/mlir/tensorflow:device_util_test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow:dump_graph_test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow:dump_mlir_util_test PASSED in 14.1s //tensorflow/compiler/mlir/tensorflow:error_util_test PASSED in 0.2s //tensorflow/compiler/mlir/tensorflow:tf_saved_model_test PASSED in 1.3s //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 0.6s //tensorflow/compiler/mlir/tensorflow/tests:annotate-parameter-replication.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:batchmatmul_to_einsum.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:breakup-islands.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:cannonicalize_ops_outside_compilation.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:canonicalize.mlir.test PASSED in 2.0s //tensorflow/compiler/mlir/tensorflow/tests:canonicalize_compile_and_replicate_attributes.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:check_control_dependencies.mlir.test PASSED in 0.9s //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 0.5s //tensorflow/compiler/mlir/tensorflow/tests:cluster_outlining.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:cluster_tf_ops_pass.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:constant-fold.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:constant_op_device_assignment.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:convert-tf-control-flow-to-scf.mlir.test PASSED in 1.1s //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 0.6s //tensorflow/compiler/mlir/tensorflow/tests:convert_session_initializer_to_function.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:convert_to_legacy_compile_and_replicate_attributes.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:decompose_reduce_dataset.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:decompose_resource_ops.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:device_assignment.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:device_assignment_by_func_attr.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:device_attribute_to_launch.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:device_canonicalize.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:device_copy.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:drop_while_shape_invariant.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:einsum.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:embedding_pipelining.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:empty-main.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:end-to-end-tpu-reshard-variables.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:executor_canonicalize.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:executor_island_coarsening.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests:executor_island_materialize_const.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:extract_head_tail_outside_compilation.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:extract_outside_compilation.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:extract_tpu_copy_with_dynamic_shape_op.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:fold-broadcast.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:freeze_variables.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:func-attr-invalid.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:func-attr.mlir.test PASSED in 0.5s //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 0.6s //tensorflow/compiler/mlir/tensorflow/tests:functionalize-if-fail.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:functionalize-if.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:fused_kernel_matcher.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:gpu_fusion.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:graph_pruning.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:graph_pruning_preserve_ops.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:group_by_dialect.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:guarantee-all-funcs-one-use.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests:hoist_loop_invariant.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:hoist_replicate_invariant_resource_writes.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:host_launch_to_outside_compiled.mlir.test PASSED in 0.9s //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 1.5s //tensorflow/compiler/mlir/tensorflow/tests:init_text_file_to_import_saved_model.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:inlining.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:isolate-placer.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:launch_outlining.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:launch_to_device_attribute.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:launch_to_device_attribute_legacy.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_layout_assignment_gpu_cc_60.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_layout_assignment_gpu_cc_70.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_layout_assignment_to_nchw.mlir.test PASSED in 2.0s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_layout_assignment_to_nhwc.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_move_transposes_begin.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_move_transposes_end.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_to_nchw.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:layout_optimization_to_nhwc.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:legalize_hlo.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:legalize_tfg.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:legalize_tfg_arg_control_dep.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:legalize_tfg_with_control_flow.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:localize_var_handles.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:lower_globals_to_ml_program.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:lower_globals_to_ml_program_invalid.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:lower_quantized.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:lower_tf.mlir.test PASSED in 1.2s //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 0.8s //tensorflow/compiler/mlir/tensorflow/tests:mark_ops_for_outside_compilation.mlir.test PASSED in 1.6s //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 1.3s //tensorflow/compiler/mlir/tensorflow/tests:mlprogram.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/tensorflow/tests:name_anonymous_iterators.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:optimize-arg-operand-constraint.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:optimize.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:order_by_dialect.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:outside_compiled_to_host_launch.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:parallel_execute_to_islands.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/tensorflow/tests:parallel_execute_to_islands_legacy.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:prepare_tpu_computation_for_tf_export.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:promote_resources_to_args.mlir.test PASSED in 0.8s //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 0.8s //tensorflow/compiler/mlir/tensorflow/tests:readonly_references_to_resources.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:region-control-flow-to-functional.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:remove_unused_arguments.mlir.test PASSED in 0.5s //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 0.9s //tensorflow/compiler/mlir/tensorflow/tests:replicate_invariant_op_hoisting.mlir.test PASSED in 1.8s //tensorflow/compiler/mlir/tensorflow/tests:replicate_tensor_list_init_ops.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:replicate_to_island.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:replicate_to_island_legacy.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:resource-alias-analysis-test.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:resource-device-inference.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:resource_analyzer.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:resource_inlining.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:resource_op_lifting.mlir.test PASSED in 2.0s //tensorflow/compiler/mlir/tensorflow/tests:rewrite_tpu_embedding_ops.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:roundtrip-tf-executor.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:shape_inference.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:side-effect-analysis-test.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:sink_constant.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:split_into_island_per_op.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:stack_ops_decomposition.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:strip_noinline.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests:strip_saved_module_metadata.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:strip_tf_attributes.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tensor_array_ops_decomposition.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:tensor_list_ops_decomposition.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tensorflow/tests:tf-executor-to-functional.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf-functional-to-executor.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf-ops.mlir.test PASSED in 5.7s //tensorflow/compiler/mlir/tensorflow/tests:tf-reduce-identity.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:tf_data_fuse_map_and_batch.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests:tf_data_fuse_pmap_and_batch.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_device_index_selector.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:tf_device_ops.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests:tf_device_ops_invalid.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops_invalid.mlir.test PASSED in 2.0s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops_location_roundtrip.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops_printer.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tf_executor_ops_side_effect.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_optimize.mlir.test PASSED in 1.0s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_freeze_global_tensors_mutable_tensors.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_initialize_variables_in_session_init.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_initialize_variables_in_session_init_fail.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_lift_variables.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_lift_variables_invalid_session.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_mark_initialized_variables.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_ops.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_ops_invalid.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_optimize_global_tensors.mlir.test PASSED in 1.6s //tensorflow/compiler/mlir/tensorflow/tests:tf_saved_model_optimize_global_tensors_interprocedural.mlir.test PASSED in 1.9s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tf_trait_folds.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tpu-annotate-dynamic-shape-inputs.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tpu-cluster-cleanup-attributes.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tpu-dynamic-layout-pass.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tpu-merge-variables-with-execute.mlir.test PASSED in 1.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu-multiple-while-body-func.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu-resource-read-for-write.mlir.test PASSED in 0.5s //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 1.4s //tensorflow/compiler/mlir/tensorflow/tests:tpu_colocate_composite_resource_ops.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:tpu_colocate_splits.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tpu_device_propagation.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:tpu_host_computation_expansion.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu_identity_pruning.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:tpu_parallel_execute_sink_resource_write.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tpu_partitioned_op_conversion.mlir.test PASSED in 0.6s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests:tpu_rewrite.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests:tpu_sharding_identification.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests:tpu_space_to_depth_pass.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu_tail_with_tobool_op.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:tpu_update_embedding_enqueue_op_inputs.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:tpu_validate_inputs.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests:transpose-op.mlir.test PASSED in 0.9s //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 1.1s //tensorflow/compiler/mlir/tensorflow/tests:warn_when_using_deprecated_dumps.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:while_licm.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:xla_call_module_custom_call_tf_function_renaming.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests:xla_call_module_deserialization.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:xla_call_module_round_trip.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests:xla_call_module_serialization.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:xla_cluster_formation.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests:xla_inline_device_ops.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests:xla_rewrite.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:add.mlir.test PASSED in 1.9s //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 0.6s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:graph-resource.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:graph-resource.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:graph.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:mlir-module-serialized-str-attr.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:replicate-tensor-list-init-ops.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:result-sharding.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:serialized-mlir-module-str-attr-invalid.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:serialized-mlir-module-str-attr.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:shape-inference-after-legalization.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:shape-inference.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/compile_mlir_util:stablehlo_add.mlir.test PASSED in 1.8s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_island_inlining:executor_tpuv1_inline_tpu_island.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_island_inlining:while_op.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_outline_island:case_op.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_outline_island:executor_tpuv1_outline_tpu_island.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/executor_tpuv1_outline_island:while_op.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:add.pbtxt.test PASSED in 1.0s //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 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-data-type-with-subtype.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-data-type.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-multi-data-type-with-subtype.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:arg-retval-attrs.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:case_op.pbtxt.test PASSED in 1.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:const-values.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:device-arg-retval-attr.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:empty-input-shapes.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:empty-value-attr.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:feed-as-fetch.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:feed-control-dep.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:force_shared_name_for_resource_ops.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:function-func-attr.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:functional-if-ops.pbtxt.test PASSED in 0.5s //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 1.1s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-as-function-retval-of-arg.pbtxt.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-as-function.pbtxt.test PASSED in 0.5s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-device-retval.pbtxt.test PASSED in 1.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-empty-tensor-content.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-func-attr.pbtxt.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-call.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-control-ret-diff-island.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-control-ret-same-island.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-defs.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-input-shapes.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-name-bug.pbtxt.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-function-resource-args.pbtxt.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-gradient-def.pbtxt.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-input-func-arg-name-collision.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-library.pbtxt.test PASSED in 1.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-malformed.pbtxt.test PASSED in 0.6s //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 1.1s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-version-info.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:graph-while-loop.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:invalid-output-index.pbtxt.test PASSED in 0.9s //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 0.9s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:mlir_passthrough_op.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:multi-output-feeds.pbtxt.test PASSED in 1.2s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:multiple-use-next-iteration.pbtxt.test PASSED in 1.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:node-locations.pbtxt.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:output-shapes-attr.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:output-shapes.pbtxt.test PASSED in 1.6s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:partial-device-name.pbtxt.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:prune_unused_nodes.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:quint8-const.pbtxt.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:shape-attrs.pbtxt.test PASSED in 0.7s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:switch_n.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:target.pbtxt.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:tensor-list.pbtxt.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:tf-data-pipeline.pbtxt.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir:unregistered_kernel.pbtxt.test PASSED in 1.6s //tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir/batch_use_same_function:saved_model.pbtxt.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:aliasing_arg_attr.mlir.test PASSED in 0.6s //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 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:derived_shape_attr.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:derived_size_attr.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:device-arg-retval-attr.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:export_main_to_flib.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:fetch_feed_names.mlir.test PASSED in 1.7s //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 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:function-control-ret.mlir.test PASSED in 0.7s //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 0.9s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:function-resource-args.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:functional-if-ops.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:functional-while-ops.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:graph-as-function.mlir.test PASSED in 0.8s //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 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:legalized_name.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:missing-main.mlir.test PASSED in 0.9s //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 1.5s //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 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:parse_example_v2.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:preserve-entry-func-names.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:ref-type-attr.mlir.test PASSED in 1.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:ref-while-loop.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:shape_list_attr.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:simple.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:simple_tf_dialect_op.mlir.test PASSED in 1.3s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:stringescape.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:switchn.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:tf-gradient-attr.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:tf-legacy-call.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:tf_add.mlir.test PASSED in 1.2s //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 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:type_attr.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:type_list_attr.mlir.test PASSED in 2.2s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:unique_name.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:unique_output_name.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tensorflow/tests/mlir2graphdef:while-loop.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tensorflow/tests/tf_to_hlo_pipeline:sccp-post-shape-inference.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tensorflow/tests/tpu_bridge_v1:end_to_end.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tf2xla/api/v0:compile_mlir_util_test PASSED in 5.9s //tensorflow/compiler/mlir/tf2xla/api/v0:compile_tf_graph_test PASSED in 0.6s //tensorflow/compiler/mlir/tf2xla/api/v1:legalize_tf_test PASSED in 31.4s //tensorflow/compiler/mlir/tf2xla/internal:mlir_pass_instrumentation_test PASSED in 7.5s //tensorflow/compiler/mlir/tf2xla/tests:adjust-layout.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tf2xla/tests:convert-mhlo-quant-to-int.mlir.test PASSED in 0.5s //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 0.7s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-BatchMatMulV2.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-binary-elementwise.mlir.test PASSED in 2.5s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-collective.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-communication.mlir.test PASSED in 2.3s //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 5.3s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-prefer-tf2xla.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-types.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-with-tf2xla-hlo-importer.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf-with-tf2xla.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tf2xla/tests:legalize-tf.mlir.test PASSED in 10.4s //tensorflow/compiler/mlir/tf2xla/tests:tfxla_device_specific_transformations_cpu.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tf2xla/tests:tfxla_device_specific_transformations_gpu.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tf2xla/tests:verify-tfxla-legalization-no-chlo.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tf2xla/tests:verify-tfxla-legalization.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tf2xla/transforms:tf2xla_rewriter_test PASSED in 17.7s //tensorflow/compiler/mlir/tf2xla/transforms:verify_tfxla_legalization_test PASSED in 19.1s //tensorflow/compiler/mlir/tf2xla/transforms:xla_legalize_targets_test PASSED in 0.9s //tensorflow/compiler/mlir/tf2xla/transforms:xla_legalize_tf_test PASSED in 2.9s //tensorflow/compiler/mlir/tfr:graph_decompose_test PASSED in 10.8s //tensorflow/compiler/mlir/tfr:node_expansion_test PASSED in 10.9s //tensorflow/compiler/mlir/tfr:op_reg_gen_test PASSED in 15.4s //tensorflow/compiler/mlir/tfr:tfr_decompose_ctx_test PASSED in 8.4s //tensorflow/compiler/mlir/tfr:tfr_gen_test PASSED in 16.7s //tensorflow/compiler/mlir/tfr/examples/customization:test_ops_test PASSED in 16.4s //tensorflow/compiler/mlir/tfr/examples/mnist:mnist_ops_test PASSED in 26.8s //tensorflow/compiler/mlir/tfr/examples/pad:pad_ops_test PASSED in 19.9s //tensorflow/compiler/mlir/tools/kernel_gen/tests:buffer_deallocation.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tools/kernel_gen/tests:buffer_reuse.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tools/kernel_gen/tests:bufferize.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tools/kernel_gen/tests:copy_cleanup.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tools/kernel_gen/tests:embed_tf_framework.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tools/kernel_gen/tests:invalid.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tools/kernel_gen/tests:isinf.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tools/kernel_gen/tests:ops.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tools/kernel_gen/tests:parallel_loops_to_sequential.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tools/kernel_gen/tests:rewrite_tf_framework_assert.mlir.test PASSED in 0.6s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tanh.mlir.test PASSED in 1.0s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf-legalize-to-lmhlo.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf_abi_knowledge.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf_framework_legalize_to_llvm.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf_kernel_gpu_launch_to_llvm.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tools/kernel_gen/tests:tf_to_jit_invocations.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tosa/tests:convert-tfl-uint8.mlir.test PASSED in 0.7s //tensorflow/compiler/mlir/tosa/tests:convert_metadata.mlir.test PASSED in 1.4s //tensorflow/compiler/mlir/tosa/tests:fuse-bias-tf.mlir.test PASSED in 1.6s //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 3.4s //tensorflow/compiler/mlir/tosa/tests:multi_add.mlir.test PASSED in 0.9s //tensorflow/compiler/mlir/tosa/tests:retain_call_once_funcs.mlir.test PASSED in 0.8s //tensorflow/compiler/mlir/tosa/tests:strip-quant-types.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tosa/tests:strip_metadata.mlir.test PASSED in 1.5s //tensorflow/compiler/mlir/tosa/tests:tf-tfl-to-tosa-pipeline.mlir.test PASSED in 1.1s //tensorflow/compiler/mlir/tosa/tests:tf-to-tosa-pipeline.mlir.test PASSED in 1.2s //tensorflow/compiler/mlir/tosa/tests:tfl-to-tosa-dequantize_softmax.mlir.test PASSED in 2.1s //tensorflow/compiler/mlir/tosa/tests:tfl-to-tosa-pipeline-filtered.mlir.test PASSED in 0.5s //tensorflow/compiler/mlir/tosa/tests:tfl-to-tosa-pipeline.mlir.test PASSED in 6.0s //tensorflow/compiler/mlir/tosa/tests:verify_fully_converted.mlir.test PASSED in 0.6s //tensorflow/compiler/tests:adadelta_test_cpu PASSED in 11.9s //tensorflow/compiler/tests:adagrad_da_test_cpu PASSED in 11.5s //tensorflow/compiler/tests:adagrad_test_cpu PASSED in 9.1s //tensorflow/compiler/tests:adam_test_cpu PASSED in 11.9s //tensorflow/compiler/tests:add_n_test_cpu PASSED in 7.3s //tensorflow/compiler/tests:argminmax_test_cpu PASSED in 11.4s //tensorflow/compiler/tests:argminmax_test_cpu_mlir_bridge_test PASSED in 22.7s //tensorflow/compiler/tests:bucketize_op_test_cpu PASSED in 7.5s //tensorflow/compiler/tests:bucketize_op_test_cpu_mlir_bridge_test PASSED in 8.4s //tensorflow/compiler/tests:case_test_cpu PASSED in 9.8s //tensorflow/compiler/tests:cast_ops_test_cpu PASSED in 8.6s //tensorflow/compiler/tests:cast_ops_test_cpu_mlir_bridge_test PASSED in 7.0s //tensorflow/compiler/tests:categorical_op_test_cpu PASSED in 24.9s //tensorflow/compiler/tests:categorical_op_test_cpu_mlir_bridge_test PASSED in 11.7s //tensorflow/compiler/tests:cholesky_op_test_cpu PASSED in 17.2s //tensorflow/compiler/tests:cholesky_op_test_cpu_mlir_bridge_test PASSED in 20.0s //tensorflow/compiler/tests:clustering_test_cpu PASSED in 8.8s //tensorflow/compiler/tests:clustering_test_cpu_mlir_bridge_test PASSED in 9.0s //tensorflow/compiler/tests:concat_ops_test_cpu PASSED in 8.5s //tensorflow/compiler/tests:concat_ops_test_cpu_mlir_bridge_test PASSED in 9.4s //tensorflow/compiler/tests:cond_test_cpu PASSED in 8.6s //tensorflow/compiler/tests:const_arg_test_cpu PASSED in 7.0s //tensorflow/compiler/tests:const_test_cpu PASSED in 11.5s //tensorflow/compiler/tests:data_format_ops_test_cpu PASSED in 13.4s //tensorflow/compiler/tests:data_format_ops_test_cpu_mlir_bridge_test PASSED in 18.7s //tensorflow/compiler/tests:dense_layer_test_cpu PASSED in 12.7s //tensorflow/compiler/tests:dynamic_slice_ops_test_cpu PASSED in 10.2s //tensorflow/compiler/tests:dynamic_slice_ops_test_cpu_mlir_bridge_test PASSED in 11.7s //tensorflow/compiler/tests:dynamic_stitch_test_cpu PASSED in 9.6s //tensorflow/compiler/tests:dynamic_stitch_test_cpu_mlir_bridge_test PASSED in 8.6s //tensorflow/compiler/tests:eager_test_cpu PASSED in 17.0s //tensorflow/compiler/tests:einsum_op_test_cpu PASSED in 7.6s //tensorflow/compiler/tests:einsum_op_test_cpu_mlir_bridge_test PASSED in 8.6s //tensorflow/compiler/tests:ensure_shape_op_test_cpu PASSED in 8.6s //tensorflow/compiler/tests:extract_image_patches_op_test_cpu PASSED in 8.8s //tensorflow/compiler/tests:extract_image_patches_op_test_cpu_mlir_bridge_test PASSED in 8.5s //tensorflow/compiler/tests:fake_quant_ops_test_cpu PASSED in 14.9s //tensorflow/compiler/tests:fake_quant_ops_test_cpu_mlir_bridge_test PASSED in 15.0s //tensorflow/compiler/tests:fifo_queue_test_cpu PASSED in 12.2s //tensorflow/compiler/tests:fifo_queue_test_cpu_mlir_bridge_test PASSED in 7.7s //tensorflow/compiler/tests:ftrl_ops_test_cpu PASSED in 9.1s //tensorflow/compiler/tests:ftrl_ops_test_cpu_mlir_bridge_test PASSED in 13.1s //tensorflow/compiler/tests:function_test_cpu PASSED in 7.6s //tensorflow/compiler/tests:function_test_cpu_mlir_bridge_test PASSED in 7.5s //tensorflow/compiler/tests:gather_nd_op_test_cpu PASSED in 9.3s //tensorflow/compiler/tests:gather_nd_op_test_cpu_mlir_bridge_test PASSED in 13.5s //tensorflow/compiler/tests:gather_test_cpu PASSED in 49.3s //tensorflow/compiler/tests:gather_test_cpu_mlir_bridge_test PASSED in 54.3s //tensorflow/compiler/tests:jit_test_cpu PASSED in 59.8s //tensorflow/compiler/tests:listdiff_op_test_cpu PASSED in 14.4s //tensorflow/compiler/tests:listdiff_op_test_cpu_mlir_bridge_test PASSED in 12.2s //tensorflow/compiler/tests:lrn_ops_test_cpu PASSED in 7.3s //tensorflow/compiler/tests:lrn_ops_test_cpu_mlir_bridge_test PASSED in 8.6s //tensorflow/compiler/tests:lstm_test_cpu PASSED in 21.3s //tensorflow/compiler/tests:manip_ops_test_cpu PASSED in 10.0s //tensorflow/compiler/tests:manip_ops_test_cpu_mlir_bridge_test PASSED in 14.7s //tensorflow/compiler/tests:matrix_band_part_test_cpu PASSED in 35.7s //tensorflow/compiler/tests:matrix_band_part_test_cpu_mlir_bridge_test PASSED in 37.6s //tensorflow/compiler/tests:matrix_inverse_op_test_cpu PASSED in 24.5s //tensorflow/compiler/tests:matrix_inverse_op_test_cpu_mlir_bridge_test PASSED in 21.6s //tensorflow/compiler/tests:matrix_solve_op_test_cpu PASSED in 8.1s //tensorflow/compiler/tests:matrix_solve_op_test_cpu_mlir_bridge_test PASSED in 10.6s //tensorflow/compiler/tests:matrix_triangular_solve_op_test_cpu PASSED in 24.5s //tensorflow/compiler/tests:matrix_triangular_solve_op_test_cpu_mlir_bridge_test PASSED in 24.6s //tensorflow/compiler/tests:momentum_test_cpu PASSED in 13.6s //tensorflow/compiler/tests:nary_ops_test_cpu PASSED in 12.1s //tensorflow/compiler/tests:nary_ops_test_cpu_mlir_bridge_test PASSED in 12.7s //tensorflow/compiler/tests:nullary_ops_test_cpu PASSED in 8.3s //tensorflow/compiler/tests:nullary_ops_test_cpu_mlir_bridge_test PASSED in 8.5s //tensorflow/compiler/tests:placeholder_test_cpu PASSED in 7.8s //tensorflow/compiler/tests:placeholder_test_cpu_mlir_bridge_test PASSED in 7.3s //tensorflow/compiler/tests:proximal_adagrad_test_cpu PASSED in 8.8s //tensorflow/compiler/tests:proximal_gradient_descent_test_cpu PASSED in 9.2s //tensorflow/compiler/tests:quantized_ops_test_cpu PASSED in 7.2s //tensorflow/compiler/tests:reduce_window_test_cpu PASSED in 9.3s //tensorflow/compiler/tests:reduce_window_test_cpu_mlir_bridge_test PASSED in 8.8s //tensorflow/compiler/tests:reshape_op_test_cpu PASSED in 9.4s //tensorflow/compiler/tests:reshape_op_test_cpu_mlir_bridge_test PASSED in 8.9s //tensorflow/compiler/tests:reverse_ops_test_cpu PASSED in 15.5s //tensorflow/compiler/tests:reverse_ops_test_cpu_mlir_bridge_test PASSED in 11.8s //tensorflow/compiler/tests:reverse_sequence_op_test_cpu PASSED in 9.3s //tensorflow/compiler/tests:reverse_sequence_op_test_cpu_mlir_bridge_test PASSED in 8.9s //tensorflow/compiler/tests:risc_ops_test_cpu_mlir_bridge_test PASSED in 8.4s //tensorflow/compiler/tests:rmsprop_test_cpu PASSED in 11.0s //tensorflow/compiler/tests:scatter_nd_op_test_cpu PASSED in 21.4s //tensorflow/compiler/tests:scatter_nd_op_test_cpu_mlir_bridge_test PASSED in 37.7s //tensorflow/compiler/tests:searchsorted_op_test_cpu PASSED in 9.7s //tensorflow/compiler/tests:searchsorted_op_test_cpu_mlir_bridge_test PASSED in 9.1s //tensorflow/compiler/tests:segment_reduction_ops_test_cpu PASSED in 24.6s //tensorflow/compiler/tests:segment_reduction_ops_test_cpu_mlir_bridge_test PASSED in 47.5s //tensorflow/compiler/tests:self_adjoint_eig_op_test_cpu PASSED in 17.8s //tensorflow/compiler/tests:self_adjoint_eig_op_test_cpu_mlir_bridge_test PASSED in 20.2s //tensorflow/compiler/tests:slice_ops_test_cpu PASSED in 17.2s //tensorflow/compiler/tests:slice_ops_test_cpu_mlir_bridge_test PASSED in 33.8s //tensorflow/compiler/tests:sparse_to_dense_op_test_cpu PASSED in 11.0s //tensorflow/compiler/tests:sparse_to_dense_op_test_cpu_mlir_bridge_test PASSED in 9.2s //tensorflow/compiler/tests:stack_ops_test_cpu PASSED in 11.0s //tensorflow/compiler/tests:tensor_float_32_test_cpu PASSED in 7.9s //tensorflow/compiler/tests:tensor_float_32_test_cpu_mlir_bridge_test PASSED in 10.1s //tensorflow/compiler/tests:tensor_list_ops_test_cpu PASSED in 9.2s //tensorflow/compiler/tests:tridiagonal_matmul_ops_test_cpu PASSED in 21.1s //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 13.3s //tensorflow/compiler/tests:tridiagonal_solve_ops_test_cpu_mlir_bridge_test PASSED in 15.2s //tensorflow/compiler/tests:unique_ops_test_cpu PASSED in 6.9s //tensorflow/compiler/tests:variable_ops_test_cpu PASSED in 27.7s //tensorflow/compiler/tests:variable_ops_test_cpu_mlir_bridge_test PASSED in 13.5s //tensorflow/compiler/tests:where_op_test_cpu PASSED in 8.9s //tensorflow/compiler/tests:while_test_cpu PASSED in 8.7s //tensorflow/compiler/tests:xla_call_module_test_cpu PASSED in 10.2s //tensorflow/compiler/tests:xla_custom_call_ops_test_cpu PASSED in 6.8s //tensorflow/compiler/tests:xla_device_gpu_test_cpu PASSED in 20.2s //tensorflow/compiler/tests:xla_device_test_cpu PASSED in 12.4s //tensorflow/compiler/tests:xla_device_test_cpu_mlir_bridge_test PASSED in 14.4s //tensorflow/compiler/tests:xla_ops_test_cpu PASSED in 36.2s //tensorflow/compiler/tests:xla_ops_test_cpu_mlir_bridge_test PASSED in 46.8s //tensorflow/compiler/tests:xla_test_test PASSED in 8.5s //tensorflow/compiler/tf2xla:const_analysis_test PASSED in 7.6s //tensorflow/compiler/tf2xla:cpu_function_runtime_test PASSED in 0.2s //tensorflow/compiler/tf2xla:functionalize_cond_test PASSED in 2.5s //tensorflow/compiler/tf2xla:functionalize_control_flow_test PASSED in 1.1s //tensorflow/compiler/tf2xla:fused_batchnorm_reserve_space_test_cpu PASSED in 32.7s //tensorflow/compiler/tf2xla:graph_compiler_test PASSED in 6.6s //tensorflow/compiler/tf2xla:literal_util_test PASSED in 1.2s //tensorflow/compiler/tf2xla:resource_operation_table_test PASSED in 8.3s //tensorflow/compiler/tf2xla:resource_util_test_cpu PASSED in 2.6s //tensorflow/compiler/tf2xla:sharding_util_test PASSED in 0.9s //tensorflow/compiler/tf2xla:tf2xla_opset_test PASSED in 9.7s //tensorflow/compiler/tf2xla:tf2xla_test PASSED in 27.3s //tensorflow/compiler/tf2xla:tf2xla_util_test PASSED in 1.3s //tensorflow/compiler/tf2xla:xla_compiler_test PASSED in 24.1s //tensorflow/compiler/tf2xla:xla_jit_compiled_cpu_function_test PASSED in 24.0s //tensorflow/compiler/tf2xla:xla_op_registry_test PASSED in 6.5s //tensorflow/compiler/tf2xla/kernels:rng_converter_utils_test PASSED in 2.1s //tensorflow/compiler/xla:array2d_test PASSED in 0.2s //tensorflow/compiler/xla:array3d_test PASSED in 0.3s //tensorflow/compiler/xla:array4d_test PASSED in 0.3s //tensorflow/compiler/xla:array_test PASSED in 0.2s //tensorflow/compiler/xla:bit_cast_test PASSED in 0.1s //tensorflow/compiler/xla:comparison_util_test PASSED in 0.4s //tensorflow/compiler/xla:debug_options_parsers_test PASSED in 0.5s //tensorflow/compiler/xla:index_util_test PASSED in 0.6s //tensorflow/compiler/xla:iterator_util_test PASSED in 0.2s //tensorflow/compiler/xla:layout_test PASSED in 0.3s //tensorflow/compiler/xla:layout_util_test PASSED in 0.5s //tensorflow/compiler/xla:literal_test PASSED in 0.3s //tensorflow/compiler/xla:parse_flags_from_env_test PASSED in 1.2s //tensorflow/compiler/xla:permutation_util_test PASSED in 0.8s //tensorflow/compiler/xla:primitive_util_test PASSED in 1.0s //tensorflow/compiler/xla:refcounting_hash_map_test PASSED in 0.4s //tensorflow/compiler/xla:reference_util_test PASSED in 0.7s //tensorflow/compiler/xla:shape_test PASSED in 0.9s //tensorflow/compiler/xla:shape_tree_test PASSED in 0.2s //tensorflow/compiler/xla:shape_util_test PASSED in 2.4s //tensorflow/compiler/xla:status_macros_test PASSED in 0.2s //tensorflow/compiler/xla:text_literal_reader_test PASSED in 0.3s //tensorflow/compiler/xla:text_literal_writer_test PASSED in 0.2s //tensorflow/compiler/xla:types_test PASSED in 0.4s //tensorflow/compiler/xla:util_test PASSED in 0.7s //tensorflow/compiler/xla:window_util_test PASSED in 0.4s //tensorflow/compiler/xla/client:padding_test PASSED in 0.1s //tensorflow/compiler/xla/client:xla_builder_test PASSED in 0.3s //tensorflow/compiler/xla/client/lib:arithmetic_test_cpu PASSED in 9.7s //tensorflow/compiler/xla/client/lib:comparators_test_cpu PASSED in 15.1s //tensorflow/compiler/xla/client/lib:constants_test_cpu PASSED in 13.3s //tensorflow/compiler/xla/client/lib:logdet_test_cpu PASSED in 11.9s //tensorflow/compiler/xla/client/lib:math_test_cpu PASSED in 17.4s //tensorflow/compiler/xla/client/lib:matrix_test_cpu PASSED in 17.3s //tensorflow/compiler/xla/client/lib:pooling_test_cpu PASSED in 13.6s //tensorflow/compiler/xla/client/lib:qr_test_cpu PASSED in 17.0s //tensorflow/compiler/xla/client/lib:slicing_test_cpu PASSED in 14.5s //tensorflow/compiler/xla/client/lib:sorting_test_cpu PASSED in 13.5s //tensorflow/compiler/xla/examples/axpy:stablehlo_compile_test PASSED in 13.9s //tensorflow/compiler/xla/experiments/sm_bandwidth_benchmark:sm_bw_test PASSED in 0.3s //tensorflow/compiler/xla/hlo/evaluator:hlo_evaluator_test PASSED in 4.5s //tensorflow/compiler/xla/hlo/experimental/auto_sharding:auto_sharding_test PASSED in 5.0s //tensorflow/compiler/xla/hlo/transforms:hlo_constant_splitter_test PASSED in 2.0s //tensorflow/compiler/xla/hlo/utils:hlo_live_range_test PASSED in 2.2s //tensorflow/compiler/xla/hlo/utils:hlo_matchers_test PASSED in 1.2s //tensorflow/compiler/xla/hlo/utils:hlo_sharding_util_test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:collective_ops.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:fft.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:legalize_i1_vector_transfers.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:library_ops_to_cpu_runtime.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:lmhlo_custom_call.mlir.test PASSED in 1.1s //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 0.5s //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_infeed.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:xla_cpu_memref_element_cast_to_llvm.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/backends/cpu/transforms/tests:xla_cpu_outfeed.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:add_concurrent_regions.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:add_hlo_trace.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:gpu_launch.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:gpu_memcpy.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:gpu_memset.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_case.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_custom_call.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_fft.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_gpu_cholesky.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_gpu_conv.mlir.test PASSED in 0.5s //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 0.5s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_infeed.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_outfeed.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_send_recv.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:lmhlo_while.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:memref_get_global_to_arg.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/backends/gpu/transforms/tests:outline_cuda_graphs.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/framework/tests:legalize-xla-framework.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/mlir/framework/tests:outline-with-xla-framework.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir/framework/tests:xla-framework.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/math/transforms/tests:math_optimization.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/memref/transforms/tests:aligned_allocations.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/runtime/ir/tests:ops.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/runtime/ir/tests:ops_verify.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/mlir/runtime/ir/tests:testlib.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/runtime/transforms:calling_convention_test PASSED in 0.4s //tensorflow/compiler/xla/mlir/runtime/transforms:type_converter_test PASSED in 0.9s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:compilation_pipeline.mlir.test PASSED in 0.5s //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 1.2s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:export_functions.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:ordinal_assignment.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/runtime/transforms/tests:rt_to_llvm.mlir.test PASSED in 2.6s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:erase-op-without-results.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:inline-scf-while.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:reduce-scf-forall-bounds.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:replace-op-with-constant.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:replace-op-with-value.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:replace-operand-with-constant.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:return-operands-of-terminator-operands.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/rewrites/tests:truncate-function.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/tests:bisect.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/tests:no-bug.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir/tools/mlir_bisect/tests:snapshot.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir/tools/mlir_replay/public:execution_trace_utils_test PASSED in 0.3s //tensorflow/compiler/xla/mlir/utils:error_util_test PASSED in 0.1s //tensorflow/compiler/xla/mlir/xla_cpu/tests:bufferize.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/xla_cpu/tests:invalid.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir/xla_cpu/tests:ops.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/bufferization/hlo_one_shot_bufferize.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/chlo/chlo_legalize_to_hlo_broadcasts.mlir.test PASSED in 2.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/chlo/chlo_legalize_to_hlo_no_broadcasts.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/chlo/chlo_legalize_to_mhlo.mlir.test PASSED in 2.2s //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/analysis.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/buffer_reuse.mlir.test PASSED in 0.8s //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 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/deallocate_invalid.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/deallocation/deallocation_ops.mlir.test PASSED in 0.4s //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 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/add_debug_info.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/bufferization.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/collapse-shape.mlir.test PASSED in 1.2s //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 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/conv_2d_nhwc_hwcf.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/dot.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/duplicate_fusions.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/fibonacci.mlir.test PASSED in 2.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/fusion_outlining.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/fusion_planning_for_cpu.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/inline_fusion_clusters.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/map_bcast_map.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/map_matmul.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/map_reduce_map.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/map_reshape_map.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/matmul.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reduce_1d.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reduce_1d_map.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reduce_2d.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/reduce_window.mlir.test PASSED in 0.6s //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 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/sort.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/cpu_tiling/transpose.mlir.test PASSED in 1.1s //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 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/lower_vectors.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/nested_tiling_softmax.mlir.test PASSED in 1.4s //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 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/rewrite_forall_to_for.mlir.test PASSED in 0.7s //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 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/tiling_softmax.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/vectorize_copy.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/gml_st/vectorize_for_cpu.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/lhlo-legalize-select-and-scatter.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/lhlo-legalize-to-affine.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/lhlo-legalize-to-gpu.mlir.test PASSED in 0.9s //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 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo/ops.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/lhlo_gpu/lhlo_gpu_ops.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/attrs.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/broadcast_propagation.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/bitcast.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/canonicalize.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/concatenate.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/convert.mlir.test PASSED in 0.5s //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 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/folder_limit.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/reduce.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/reshape.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/canonicalize/reverse.mlir.test PASSED in 0.8s //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 0.7s //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 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/constraint_fusion.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/convert_to_signless.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/expand_hlo_tuples.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/expand_ops_simplifier.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/group_reduction_dimensions.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-collapse-elementwise-map.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-einsum-to-dot-general.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-gather-to-torch-index-select.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-rng-to-linalg.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-shape-ops-to-standard.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-sort.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-arithmetic.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-lhlo-only-dynamic.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-lhlo-unranked.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-lhlo.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-linalg.mlir.test PASSED in 3.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-memref-unranked.mlir.test PASSED in 0.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-memref.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-stablehlo-experimental.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/hlo-legalize-to-stablehlo.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/inlining.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/invalid.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/legalize-control-flow.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/legalize-hlo-shape-computations.mlir.test PASSED in 1.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/legalize-mhlo-to-thlo.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/legalize-to-std.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/lower-complex.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/lower-general-dot.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/materialize-broadcasts.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/merge_assuming_ops.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_bytecode_customizations.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_canonicalize_dot.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_canonicalize_gather.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_canonicalize_reduction.mlir.test PASSED in 1.0s //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 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_infer_shape_type_methods.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_ops_prettyprint.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/mhlo_reduce_pretty_print.mlir.test PASSED in 1.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/ops.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/optimize-hlo.mlir.test PASSED in 1.2s //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 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/restrict_max_rank.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/shape_legalize_to_hlo.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/shape_reification.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sink-constants-to-control-flow.mlir.test PASSED in 0.3s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_gendot_lower.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_lower.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_ops.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/sparse_rewriting.mlir.test PASSED in 0.6s //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 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/symbolic-shape-optimization.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/unfuse_batch_norm.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_bounds.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_conv_op.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_reduce_op.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_reduce_window_op.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/mhlo/verifier_scatter_op.mlir.test PASSED in 0.5s //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 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/bufferize.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/canonicalize.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/invalid.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/legalize_sort.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/ops.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:Dialect/thlo/tiling.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:alloc_to_arg.mlir.test PASSED in 1.2s //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 0.5s //tensorflow/compiler/xla/mlir_hlo/tests:bufferize.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:bufferize_one_shot.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:collapse_parallel_loops_to_1d_pass.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/mlir_hlo/tests:detensorize_scf_ops.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:index_type_llvm_lowering.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:legalize-trigonometric-to-approximation.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:lower_index_cast.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tests:propagate_static_shapes.mlir.test PASSED in 0.6s //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 0.6s //tensorflow/compiler/xla/mlir_hlo/tests:shape-component-analysis.mlir.test PASSED in 1.1s //tensorflow/compiler/xla/mlir_hlo/tests:shape_simplification.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tests:test_userange.mlir.test PASSED in 0.8s //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 0.4s //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 0.1s //tensorflow/compiler/xla/mlir_hlo/tools/mlir_interpreter/framework/tests:tensor_or_memref_test PASSED in 0.1s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:binary.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:nullary.mlir.test PASSED in 1.0s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:prepare-mhlo.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:ternary.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/mlir_hlo/tosa/tests:unary.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/pjrt:host_callback_test PASSED in 0.6s //tensorflow/compiler/xla/pjrt:lru_cache_test PASSED in 0.3s //tensorflow/compiler/xla/pjrt:pjrt_api_test PASSED in 0.4s //tensorflow/compiler/xla/pjrt:pjrt_client_test_cpu PASSED in 11.8s //tensorflow/compiler/xla/pjrt:pjrt_compiler_test PASSED in 0.9s //tensorflow/compiler/xla/pjrt:pjrt_executable_test PASSED in 0.2s //tensorflow/compiler/xla/pjrt:pjrt_stream_executor_client_test PASSED in 14.1s //tensorflow/compiler/xla/pjrt:semaphore_test PASSED in 1.0s //tensorflow/compiler/xla/pjrt:tf_pjrt_client_test PASSED in 10.5s //tensorflow/compiler/xla/pjrt:tfrt_cpu_pjrt_client_test PASSED in 13.5s //tensorflow/compiler/xla/pjrt:tracked_device_buffer_test PASSED in 11.4s //tensorflow/compiler/xla/pjrt:tracked_tfrt_cpu_device_buffer_test PASSED in 0.2s //tensorflow/compiler/xla/pjrt:transpose_test PASSED in 68.1s //tensorflow/compiler/xla/pjrt/c:pjrt_c_api_cpu_test PASSED in 10.6s //tensorflow/compiler/xla/pjrt/c:pjrt_c_api_helpers_test PASSED in 0.3s //tensorflow/compiler/xla/pjrt/distributed:client_server_test PASSED in 45.2s //tensorflow/compiler/xla/pjrt/distributed:service_test PASSED in 13.2s //tensorflow/compiler/xla/pjrt/gpu:se_gpu_pjrt_client_test PASSED in 2.0s //tensorflow/compiler/xla/python:outfeed_receiver_test_cpu PASSED in 11.6s //tensorflow/compiler/xla/python/ifrt:array_test PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt:array_test_no_impl PASSED in 0.2s //tensorflow/compiler/xla/python/ifrt:client_test_no_impl PASSED in 0.2s //tensorflow/compiler/xla/python/ifrt:future_test PASSED in 0.2s //tensorflow/compiler/xla/python/ifrt:index_domain_test PASSED in 0.3s //tensorflow/compiler/xla/python/ifrt:index_test PASSED in 0.3s //tensorflow/compiler/xla/python/ifrt:shape_test PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt:sharding_test PASSED in 0.3s //tensorflow/compiler/xla/python/ifrt:tuple_test_no_impl PASSED in 0.3s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_array.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_assemble.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_attrs.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_call.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_call_loaded_executable.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_disassemble.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_loaded_executable.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/python/ifrt/ir/tests:verify_reshard.mlir.test PASSED in 0.9s //tensorflow/compiler/xla/python/ifrt/support:sharding_param_to_op_sharding_test PASSED in 0.8s //tensorflow/compiler/xla/python/pjrt_ifrt:pjrt_array_impl_test_tfrt_cpu PASSED in 15.7s //tensorflow/compiler/xla/python/pjrt_ifrt:pjrt_client_impl_test_tfrt_cpu PASSED in 11.1s //tensorflow/compiler/xla/python/pjrt_ifrt:pjrt_executable_impl_test_tfrt_cpu PASSED in 10.5s //tensorflow/compiler/xla/python/pjrt_ifrt:pjrt_tuple_impl_test_tfrt_cpu PASSED in 8.2s //tensorflow/compiler/xla/python/pjrt_ifrt:xla_executable_test_no_impl PASSED in 1.4s //tensorflow/compiler/xla/python_api:xla_literal_test PASSED in 1.5s //tensorflow/compiler/xla/python_api:xla_shape_test PASSED in 0.7s //tensorflow/compiler/xla/rpc:grpc_client_test PASSED in 1.5s //tensorflow/compiler/xla/runtime:arguments_test PASSED in 0.7s //tensorflow/compiler/xla/runtime:async_runtime_test PASSED in 0.4s //tensorflow/compiler/xla/runtime:custom_call_test PASSED in 2.3s //tensorflow/compiler/xla/runtime:diagnostics_test PASSED in 0.6s //tensorflow/compiler/xla/runtime:executable_test PASSED in 2.9s //tensorflow/compiler/xla/runtime:ffi_test PASSED in 1.2s //tensorflow/compiler/xla/runtime:map_by_type_test PASSED in 0.5s //tensorflow/compiler/xla/runtime:module_test PASSED in 0.2s //tensorflow/compiler/xla/runtime:results_test PASSED in 0.1s //tensorflow/compiler/xla/runtime:state_test PASSED in 0.6s //tensorflow/compiler/xla/runtime:symbolic_shape_test PASSED in 0.2s //tensorflow/compiler/xla/runtime:type_id_test PASSED in 0.3s //tensorflow/compiler/xla/service:algebraic_simplifier_overflow_test_cpu PASSED in 13.1s //tensorflow/compiler/xla/service:algebraic_simplifier_test PASSED in 30.5s //tensorflow/compiler/xla/service:all_gather_broadcast_reorder_test PASSED in 3.5s //tensorflow/compiler/xla/service:all_gather_combiner_test PASSED in 1.0s //tensorflow/compiler/xla/service:all_gather_decomposer_test PASSED in 10.0s //tensorflow/compiler/xla/service:all_reduce_combiner_test PASSED in 1.5s //tensorflow/compiler/xla/service:all_reduce_contiguous_test PASSED in 2.6s //tensorflow/compiler/xla/service:all_reduce_folder_test PASSED in 0.8s //tensorflow/compiler/xla/service:all_reduce_promotion_test PASSED in 1.7s //tensorflow/compiler/xla/service:all_reduce_reassociate_test PASSED in 1.7s //tensorflow/compiler/xla/service:all_reduce_simplifier_test PASSED in 2.7s //tensorflow/compiler/xla/service:ar_crs_combiner_test PASSED in 4.4s //tensorflow/compiler/xla/service:async_collective_creator_test PASSED in 1.2s //tensorflow/compiler/xla/service:async_op_canonicalizer_test PASSED in 2.0s //tensorflow/compiler/xla/service:batch_dot_simplification_test PASSED in 2.4s //tensorflow/compiler/xla/service:batchnorm_expander_test_cpu PASSED in 15.2s //tensorflow/compiler/xla/service:bfloat16_conversion_folding_test PASSED in 1.1s //tensorflow/compiler/xla/service:bfloat16_propagation_test PASSED in 1.5s //tensorflow/compiler/xla/service:bitcast_dtypes_expander_test PASSED in 0.9s //tensorflow/compiler/xla/service:broadcast_canonicalizer_test PASSED in 1.2s //tensorflow/compiler/xla/service:buffer_assignment_test PASSED in 19.0s //tensorflow/compiler/xla/service:call_graph_test PASSED in 2.5s //tensorflow/compiler/xla/service:call_inliner_test PASSED in 1.4s //tensorflow/compiler/xla/service:change_op_data_type_test PASSED in 2.0s //tensorflow/compiler/xla/service:collective_ops_utils_test PASSED in 1.9s //tensorflow/compiler/xla/service:collective_transformation_reorderer_test PASSED in 1.1s //tensorflow/compiler/xla/service:collectives_schedule_linearizer_test PASSED in 1.3s //tensorflow/compiler/xla/service:compilation_environments_test PASSED in 0.2s //tensorflow/compiler/xla/service:conditional_canonicalizer_test PASSED in 1.3s //tensorflow/compiler/xla/service:conditional_code_motion_test PASSED in 3.0s //tensorflow/compiler/xla/service:conditional_simplifier_test PASSED in 1.7s //tensorflow/compiler/xla/service:conditional_to_select_test PASSED in 1.2s //tensorflow/compiler/xla/service:convert_async_collectives_to_sync_test PASSED in 1.7s //tensorflow/compiler/xla/service:convert_mover_test PASSED in 2.3s //tensorflow/compiler/xla/service:convert_operand_folding_test PASSED in 1.6s //tensorflow/compiler/xla/service:convolution_4d_expander_test PASSED in 1.2s //tensorflow/compiler/xla/service:convolution_group_converter_test PASSED in 1.9s //tensorflow/compiler/xla/service:convolution_pred_expander_test PASSED in 1.1s //tensorflow/compiler/xla/service:copy_insertion_test PASSED in 1.1s //tensorflow/compiler/xla/service:custom_call_status_test PASSED in 0.1s //tensorflow/compiler/xla/service:defuser_test PASSED in 1.4s //tensorflow/compiler/xla/service:despecializer_test PASSED in 2.4s //tensorflow/compiler/xla/service:dfs_hlo_visitor_with_default_test PASSED in 1.2s //tensorflow/compiler/xla/service:dot_decomposer_test PASSED in 1.8s //tensorflow/compiler/xla/service:dot_dimension_merger_test PASSED in 1.6s //tensorflow/compiler/xla/service:dot_merger_test PASSED in 1.3s //tensorflow/compiler/xla/service:dynamic_dimension_inference_test PASSED in 1.3s //tensorflow/compiler/xla/service:dynamic_dimension_simplifier_test PASSED in 1.1s //tensorflow/compiler/xla/service:dynamic_index_splitter_test PASSED in 0.8s //tensorflow/compiler/xla/service:dynamic_padder_test_cpu PASSED in 29.0s //tensorflow/compiler/xla/service:dynamic_parameter_binding_test PASSED in 1.6s //tensorflow/compiler/xla/service:dynamic_update_slice_test_cpu PASSED in 13.6s //tensorflow/compiler/xla/service:elemental_ir_emitter_test_cpu PASSED in 12.4s //tensorflow/compiler/xla/service:flatten_call_graph_test PASSED in 1.4s //tensorflow/compiler/xla/service:float_normalization_test PASSED in 2.3s //tensorflow/compiler/xla/service:fusion_node_indexing_evaluation_test PASSED in 1.7s //tensorflow/compiler/xla/service:gather_expander_test PASSED in 1.1s //tensorflow/compiler/xla/service:gather_simplifier_test PASSED in 1.6s //tensorflow/compiler/xla/service:heap_simulator_test PASSED in 1.1s //tensorflow/compiler/xla/service:hlo_alias_analysis_test PASSED in 1.4s //tensorflow/compiler/xla/service:hlo_casting_utils_test PASSED in 8.5s //tensorflow/compiler/xla/service:hlo_computation_deduplicator_test PASSED in 1.4s //tensorflow/compiler/xla/service:hlo_computation_test PASSED in 2.4s //tensorflow/compiler/xla/service:hlo_constant_folding_test PASSED in 5.8s //tensorflow/compiler/xla/service:hlo_cost_analysis_test PASSED in 12.9s //tensorflow/compiler/xla/service:hlo_creation_utils_test PASSED in 4.6s //tensorflow/compiler/xla/service:hlo_cse_test PASSED in 12.6s //tensorflow/compiler/xla/service:hlo_dataflow_analysis_test PASSED in 2.2s //tensorflow/compiler/xla/service:hlo_dce_test PASSED in 3.6s //tensorflow/compiler/xla/service:hlo_domain_test PASSED in 0.9s //tensorflow/compiler/xla/service:hlo_element_type_converter_test PASSED in 1.0s //tensorflow/compiler/xla/service:hlo_execution_profile_test PASSED in 14.0s //tensorflow/compiler/xla/service:hlo_graph_dumper_test PASSED in 1.4s //tensorflow/compiler/xla/service:hlo_input_output_alias_config_test PASSED in 1.7s //tensorflow/compiler/xla/service:hlo_instruction_test PASSED in 1.2s //tensorflow/compiler/xla/service:hlo_liveness_analysis_test PASSED in 1.5s //tensorflow/compiler/xla/service:hlo_memory_scheduler_test PASSED in 1.5s //tensorflow/compiler/xla/service:hlo_module_dce_test PASSED in 1.3s //tensorflow/compiler/xla/service:hlo_module_metadata_test PASSED in 0.4s //tensorflow/compiler/xla/service:hlo_module_test PASSED in 1.2s //tensorflow/compiler/xla/service:hlo_opcode_test PASSED in 0.4s //tensorflow/compiler/xla/service:hlo_ordering_test PASSED in 1.5s //tensorflow/compiler/xla/service:hlo_parser_test PASSED in 0.5s //tensorflow/compiler/xla/service:hlo_pass_pipeline_test PASSED in 1.2s //tensorflow/compiler/xla/service:hlo_phi_graph_test PASSED in 0.2s //tensorflow/compiler/xla/service:hlo_proto_util_test PASSED in 1.3s //tensorflow/compiler/xla/service:hlo_reachability_test PASSED in 2.6s //tensorflow/compiler/xla/service:hlo_rematerialization_test PASSED in 2.7s //tensorflow/compiler/xla/service:hlo_rematerialization_test_utils_test PASSED in 1.5s //tensorflow/compiler/xla/service:hlo_replication_analysis_test PASSED in 2.4s //tensorflow/compiler/xla/service:hlo_schedule_test PASSED in 1.4s //tensorflow/compiler/xla/service:hlo_sharding_test PASSED in 1.6s //tensorflow/compiler/xla/service:hlo_value_semantics_analysis_test PASSED in 1.8s //tensorflow/compiler/xla/service:hlo_verifier_test PASSED in 4.2s //tensorflow/compiler/xla/service:indexed_array_analysis_test PASSED in 1.4s //tensorflow/compiler/xla/service:instruction_fusion_test PASSED in 1.4s //tensorflow/compiler/xla/service:latency_hiding_scheduler_test PASSED in 2.0s //tensorflow/compiler/xla/service:layout_assignment_test PASSED in 6.2s //tensorflow/compiler/xla/service:layout_normalization_test PASSED in 2.6s //tensorflow/compiler/xla/service:logistic_expander_test PASSED in 1.5s //tensorflow/compiler/xla/service:loop_schedule_linearizer_test PASSED in 1.4s //tensorflow/compiler/xla/service:map_inliner_test PASSED in 1.4s //tensorflow/compiler/xla/service:mapped_ptr_container_sorter_test PASSED in 0.7s //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 2.9s //tensorflow/compiler/xla/service:memory_space_propagation_test PASSED in 0.9s //tensorflow/compiler/xla/service:name_uniquer_test PASSED in 0.3s //tensorflow/compiler/xla/service:operand_upcaster_test PASSED in 3.1s //tensorflow/compiler/xla/service:optimize_input_output_buffer_alias_test PASSED in 2.5s //tensorflow/compiler/xla/service:pattern_matcher_gmock_test PASSED in 0.3s //tensorflow/compiler/xla/service:pattern_matcher_test PASSED in 1.8s //tensorflow/compiler/xla/service:profile_guided_latency_estimator_test PASSED in 1.0s //tensorflow/compiler/xla/service:real_imag_expander_test PASSED in 1.7s //tensorflow/compiler/xla/service:reduce_decomposer_test PASSED in 1.1s //tensorflow/compiler/xla/service:reduce_scatter_combiner_test PASSED in 2.2s //tensorflow/compiler/xla/service:reduce_scatter_decomposer_test PASSED in 3.4s //tensorflow/compiler/xla/service:reduce_scatter_reassociate_test PASSED in 1.3s //tensorflow/compiler/xla/service:reshape_decomposer_test PASSED in 1.2s //tensorflow/compiler/xla/service:reshape_mover_test PASSED in 0.9s //tensorflow/compiler/xla/service:result_caster_test PASSED in 1.7s //tensorflow/compiler/xla/service:root_instruction_sinker_test PASSED in 1.0s //tensorflow/compiler/xla/service:scatter_expander_test PASSED in 1.3s //tensorflow/compiler/xla/service:scatter_simplifier_test PASSED in 2.8s //tensorflow/compiler/xla/service:select_and_scatter_expander_test PASSED in 1.6s //tensorflow/compiler/xla/service:shape_inference_test PASSED in 0.7s //tensorflow/compiler/xla/service:shaped_buffer_test PASSED in 14.3s //tensorflow/compiler/xla/service:sharding_propagation_test PASSED in 21.8s //tensorflow/compiler/xla/service:sharding_remover_test PASSED in 1.4s //tensorflow/compiler/xla/service:simplify_fp_conversions_test PASSED in 1.2s //tensorflow/compiler/xla/service:slice_sinker_test PASSED in 1.4s //tensorflow/compiler/xla/service:sort_simplifier_test PASSED in 1.3s //tensorflow/compiler/xla/service:space_to_batch_converter_test PASSED in 1.2s //tensorflow/compiler/xla/service:stable_sort_expander_test PASSED in 1.6s //tensorflow/compiler/xla/service:stochastic_convert_decomposer_test PASSED in 0.8s //tensorflow/compiler/xla/service:stream_pool_test PASSED in 0.8s //tensorflow/compiler/xla/service:topk_rewriter_test PASSED in 3.7s //tensorflow/compiler/xla/service:transpose_folding_test PASSED in 2.6s //tensorflow/compiler/xla/service:tuple_points_to_analysis_test PASSED in 1.3s //tensorflow/compiler/xla/service:tuple_simplifier_test PASSED in 1.7s //tensorflow/compiler/xla/service:tuple_util_test PASSED in 0.8s //tensorflow/compiler/xla/service:while_loop_all_reduce_code_motion_test PASSED in 2.9s //tensorflow/compiler/xla/service:while_loop_analysis_test PASSED in 1.9s //tensorflow/compiler/xla/service:while_loop_concat_code_motion_test PASSED in 1.4s //tensorflow/compiler/xla/service:while_loop_constant_sinking_test PASSED in 1.2s //tensorflow/compiler/xla/service:while_loop_expensive_invariant_code_motion_test PASSED in 1.4s //tensorflow/compiler/xla/service:while_loop_invariant_code_motion_test PASSED in 1.2s //tensorflow/compiler/xla/service:while_loop_simplifier_test PASSED in 2.1s //tensorflow/compiler/xla/service:while_loop_trip_count_annotator_test PASSED in 1.4s //tensorflow/compiler/xla/service:while_util_test PASSED in 1.7s //tensorflow/compiler/xla/service:xla_aot_compile_stablehlo_cpu_test PASSED in 11.9s //tensorflow/compiler/xla/service:xla_debug_info_manager_test PASSED in 1.2s //tensorflow/compiler/xla/service:zero_sized_hlo_elimination_test PASSED in 0.9s //tensorflow/compiler/xla/service/cpu:conv_canonicalization_test PASSED in 1.3s //tensorflow/compiler/xla/service/cpu:cpu_eigen_tensor_alignment_test PASSED in 1.2s //tensorflow/compiler/xla/service/cpu:cpu_instruction_fusion_test PASSED in 1.3s //tensorflow/compiler/xla/service/cpu:cpu_layout_assignment_test PASSED in 2.0s //tensorflow/compiler/xla/service/cpu:ir_emission_utils_test PASSED in 1.6s //tensorflow/compiler/xla/service/cpu:parallel_task_assignment_test PASSED in 3.3s //tensorflow/compiler/xla/service/cpu:runtime_fft_test PASSED in 0.5s //tensorflow/compiler/xla/service/cpu:shape_partition_test PASSED in 1.0s //tensorflow/compiler/xla/service/cpu:xfeed_manager_test PASSED in 0.6s //tensorflow/compiler/xla/service/cpu/tests:cpu_bytesizeof_test PASSED in 0.8s //tensorflow/compiler/xla/service/cpu/tests:cpu_dyn_shape_test PASSED in 13.4s //tensorflow/compiler/xla/service/cpu/tests:cpu_eigen_dot_operation_test PASSED in 13.2s //tensorflow/compiler/xla/service/cpu/tests:cpu_external_constants_test PASSED in 29.4s //tensorflow/compiler/xla/service/cpu/tests:cpu_fusion_test PASSED in 8.3s //tensorflow/compiler/xla/service/cpu/tests:cpu_infeed_test PASSED in 10.3s //tensorflow/compiler/xla/service/cpu/tests:cpu_intrinsic_test PASSED in 14.7s //tensorflow/compiler/xla/service/cpu/tests:cpu_key_value_sort_test PASSED in 11.7s //tensorflow/compiler/xla/service/cpu/tests:cpu_literal_caching_test PASSED in 10.4s //tensorflow/compiler/xla/service/cpu/tests:cpu_noalias_test PASSED in 10.6s //tensorflow/compiler/xla/service/cpu/tests:cpu_outfeed_test PASSED in 10.4s //tensorflow/compiler/xla/service/cpu/tests:cpu_profiling_test PASSED in 12.6s //tensorflow/compiler/xla/service/cpu/tests:cpu_spmd_compile_test PASSED in 9.9s //tensorflow/compiler/xla/service/cpu/tests:cpu_topk_test PASSED in 11.5s //tensorflow/compiler/xla/service/cpu/tests:cpu_vectorization_test PASSED in 13.2s //tensorflow/compiler/xla/service/cpu/tests:cpu_while_test PASSED in 16.7s //tensorflow/compiler/xla/service/cpu/tests:tree_reduction_rewriter_test PASSED in 13.5s //tensorflow/compiler/xla/service/gpu:alias_passthrough_params_test PASSED in 1.0s //tensorflow/compiler/xla/service/gpu:all_reduce_blueconnect_test PASSED in 1.4s //tensorflow/compiler/xla/service/gpu:backend_configs_test PASSED in 0.8s //tensorflow/compiler/xla/service/gpu:cublas_pad_for_gemms_test PASSED in 2.1s //tensorflow/compiler/xla/service/gpu:cudnn_pad_for_convolutions_test PASSED in 2.8s //tensorflow/compiler/xla/service/gpu:cudnn_simplify_padding_test PASSED in 2.1s //tensorflow/compiler/xla/service/gpu:cudnn_support_utils_test PASSED in 2.1s //tensorflow/compiler/xla/service/gpu:cudnn_vectorize_convolutions_test PASSED in 1.0s //tensorflow/compiler/xla/service/gpu:fusion_merger_test PASSED in 2.5s //tensorflow/compiler/xla/service/gpu:gemm_rewriter_triton_test PASSED in 2.8s //tensorflow/compiler/xla/service/gpu:gpu_async_collective_annotator_test PASSED in 1.2s //tensorflow/compiler/xla/service/gpu:gpu_conv_padding_legalization_test PASSED in 1.3s //tensorflow/compiler/xla/service/gpu:gpu_conv_rewriter_test PASSED in 2.8s //tensorflow/compiler/xla/service/gpu:gpu_convert_async_collectives_to_sync_test PASSED in 2.2s //tensorflow/compiler/xla/service/gpu:gpu_copy_insertion_test PASSED in 12.8s //tensorflow/compiler/xla/service/gpu:gpu_fusible_test PASSED in 2.3s //tensorflow/compiler/xla/service/gpu:gpu_hlo_cost_analysis_test PASSED in 2.0s //tensorflow/compiler/xla/service/gpu:gpu_performance_model_test PASSED in 2.2s //tensorflow/compiler/xla/service/gpu:gpu_sanitize_constant_names_test PASSED in 2.5s //tensorflow/compiler/xla/service/gpu:hlo_algorithm_denylist_test PASSED in 0.3s //tensorflow/compiler/xla/service/gpu:hlo_fusion_stats_test PASSED in 1.3s //tensorflow/compiler/xla/service/gpu:instruction_fusion_test PASSED in 1.7s //tensorflow/compiler/xla/service/gpu:ir_emission_utils_test PASSED in 2.5s //tensorflow/compiler/xla/service/gpu:matmul_utils_test PASSED in 1.9s //tensorflow/compiler/xla/service/gpu:move_copy_to_users_test PASSED in 2.6s //tensorflow/compiler/xla/service/gpu:multi_output_fusion_test PASSED in 2.1s //tensorflow/compiler/xla/service/gpu:non_atomically_upgradeable_rw_lock_test PASSED in 0.1s //tensorflow/compiler/xla/service/gpu:reduction_splitter_test PASSED in 2.5s //tensorflow/compiler/xla/service/gpu:scatter_slice_simplifier_test PASSED in 1.1s //tensorflow/compiler/xla/service/gpu:target_util_test PASSED in 0.4s //tensorflow/compiler/xla/service/gpu:topk_splitter_test PASSED in 35.9s //tensorflow/compiler/xla/service/gpu:variadic_op_splitter_test PASSED in 2.4s //tensorflow/compiler/xla/service/gpu:while_transformer_test PASSED in 2.6s //tensorflow/compiler/xla/service/gpu/llvm_gpu_backend:utils_test PASSED in 0.8s //tensorflow/compiler/xla/service/gpu/tests:gpu_reduce_scatter_creator_test PASSED in 2.6s //tensorflow/compiler/xla/service/gpu/tests:reduction_degenerate_dim_remover_test PASSED in 2.5s //tensorflow/compiler/xla/service/gpu/tests:reduction_dimension_grouper_test PASSED in 2.2s //tensorflow/compiler/xla/service/gpu/tests:tree_reduction_rewriter_test PASSED in 3.4s //tensorflow/compiler/xla/service/graphcycles:graphcycles_test PASSED in 0.8s //tensorflow/compiler/xla/service/graphcycles:ordered_set_test PASSED in 0.3s //tensorflow/compiler/xla/service/llvm_ir:alias_analysis_test PASSED in 9.8s //tensorflow/compiler/xla/service/llvm_ir:ir_array_test PASSED in 1.0s //tensorflow/compiler/xla/service/spmd:canonicalize_all_gather_for_cse_test PASSED in 1.1s //tensorflow/compiler/xla/service/spmd:collective_permute_motion_test PASSED in 1.1s //tensorflow/compiler/xla/service/spmd:partition_assignment_test PASSED in 2.0s //tensorflow/compiler/xla/service/spmd:schedule_aware_collective_ops_cse_test PASSED in 2.3s //tensorflow/compiler/xla/service/spmd:spmd_partitioner_test PASSED in 3.0s //tensorflow/compiler/xla/service/spmd:stateful_rng_spmd_partitioner_test PASSED in 1.1s //tensorflow/compiler/xla/stream_executor:dnn_test PASSED in 0.1s //tensorflow/compiler/xla/stream_executor:stream_test PASSED in 0.5s //tensorflow/compiler/xla/stream_executor/host:host_stream_test PASSED in 0.9s //tensorflow/compiler/xla/tests:all_reduce_test_cpu PASSED in 15.2s //tensorflow/compiler/xla/tests:axpy_simple_test_cpu PASSED in 9.8s //tensorflow/compiler/xla/tests:bad_rng_shape_validation_test_cpu PASSED in 12.0s //tensorflow/compiler/xla/tests:binop_scaling_test_cpu PASSED in 13.5s //tensorflow/compiler/xla/tests:bitcast_convert_test_cpu PASSED in 11.6s //tensorflow/compiler/xla/tests:broadcast_simple_test_cpu PASSED in 15.8s //tensorflow/compiler/xla/tests:broadcast_test_cpu PASSED in 14.5s //tensorflow/compiler/xla/tests:buffer_donation_test_cpu PASSED in 13.0s //tensorflow/compiler/xla/tests:call_test_cpu PASSED in 15.7s //tensorflow/compiler/xla/tests:check_execution_arity_test_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests:cholesky_test_cpu PASSED in 25.4s //tensorflow/compiler/xla/tests:client_test_cpu PASSED in 11.0s //tensorflow/compiler/xla/tests:collective_ops_test_cpu PASSED in 28.0s //tensorflow/compiler/xla/tests:compilation_cache_test_cpu PASSED in 10.4s //tensorflow/compiler/xla/tests:compute_constant_test_cpu PASSED in 12.1s //tensorflow/compiler/xla/tests:concat_test_cpu PASSED in 15.2s //tensorflow/compiler/xla/tests:constant_reduction_function_test_cpu PASSED in 13.9s //tensorflow/compiler/xla/tests:constants_test_cpu PASSED in 12.0s //tensorflow/compiler/xla/tests:convert_test_cpu PASSED in 12.8s //tensorflow/compiler/xla/tests:copy_test_cpu PASSED in 13.2s //tensorflow/compiler/xla/tests:cpu_gpu_fusion_test_cpu PASSED in 25.3s //tensorflow/compiler/xla/tests:custom_call_test_cpu PASSED in 17.9s //tensorflow/compiler/xla/tests:deallocation_test_cpu PASSED in 14.1s //tensorflow/compiler/xla/tests:deconstruct_tuple_test_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests:deep_graph_test_cpu PASSED in 13.3s //tensorflow/compiler/xla/tests:execution_profile_test_cpu PASSED in 11.7s //tensorflow/compiler/xla/tests:fft_test_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests:float8_test_cpu PASSED in 10.3s //tensorflow/compiler/xla/tests:floor_ceil_test_cpu PASSED in 11.7s //tensorflow/compiler/xla/tests:fmax_fmin_test_cpu PASSED in 16.0s //tensorflow/compiler/xla/tests:gather_operation_test_cpu PASSED in 16.8s //tensorflow/compiler/xla/tests:get_dimension_size_test_cpu PASSED in 9.5s //tensorflow/compiler/xla/tests:half_test_cpu PASSED in 12.6s //tensorflow/compiler/xla/tests:hlo_metadata_test PASSED in 10.9s //tensorflow/compiler/xla/tests:literal_test_util_test PASSED in 9.6s //tensorflow/compiler/xla/tests:local_client_allocation_test_cpu PASSED in 12.9s //tensorflow/compiler/xla/tests:local_client_aot_test PASSED in 0.1s //tensorflow/compiler/xla/tests:log_test_cpu PASSED in 13.4s //tensorflow/compiler/xla/tests:map_test_cpu PASSED in 13.1s //tensorflow/compiler/xla/tests:matrix_ops_simple_test_cpu PASSED in 23.3s //tensorflow/compiler/xla/tests:multidimensional_slice_test_cpu PASSED in 12.0s //tensorflow/compiler/xla/tests:multiple_devices_on_host_test PASSED in 8.7s //tensorflow/compiler/xla/tests:multithreaded_compilation_test_cpu PASSED in 11.6s //tensorflow/compiler/xla/tests:outfeed_in_nested_computation_test_cpu PASSED in 14.4s //tensorflow/compiler/xla/tests:pad_test_cpu PASSED in 12.6s //tensorflow/compiler/xla/tests:pred_test_cpu PASSED in 14.1s //tensorflow/compiler/xla/tests:query_inferred_shape_test_cpu PASSED in 14.5s //tensorflow/compiler/xla/tests:reduce_hlo_test_cpu PASSED in 14.1s //tensorflow/compiler/xla/tests:reduce_precision_test_cpu PASSED in 11.5s //tensorflow/compiler/xla/tests:replay_test_cpu PASSED in 10.6s //tensorflow/compiler/xla/tests:reshape_motion_test_cpu PASSED in 12.2s //tensorflow/compiler/xla/tests:reverse_test_cpu PASSED in 11.2s //tensorflow/compiler/xla/tests:round_trip_packed_literal_test_cpu PASSED in 12.7s //tensorflow/compiler/xla/tests:round_trip_transfer_test_cpu PASSED in 12.8s //tensorflow/compiler/xla/tests:sample_text_test_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests:scatter_test_cpu PASSED in 25.2s //tensorflow/compiler/xla/tests:select_test_cpu PASSED in 12.5s //tensorflow/compiler/xla/tests:test_utils_test_cpu PASSED in 12.7s //tensorflow/compiler/xla/tests:token_hlo_test_cpu PASSED in 16.8s //tensorflow/compiler/xla/tests:topk_test_cpu PASSED in 10.7s //tensorflow/compiler/xla/tests:transfer_manager_test_cpu PASSED in 18.9s //tensorflow/compiler/xla/tests:transpose_test_cpu PASSED in 13.5s //tensorflow/compiler/xla/tests:tuple_test_cpu PASSED in 15.0s //tensorflow/compiler/xla/tests:unary_op_test_cpu PASSED in 12.7s //tensorflow/compiler/xla/tests:value_inference_test_cpu PASSED in 12.0s //tensorflow/compiler/xla/tests:vector_ops_reduce_test_cpu PASSED in 10.8s //tensorflow/compiler/xla/tests:vector_ops_simple_test_cpu PASSED in 21.5s //tensorflow/compiler/xla/tests:while_test_cpu PASSED in 15.8s //tensorflow/compiler/xla/tests/fuzz:rand_000000_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests/fuzz:rand_000003_cpu PASSED in 12.0s //tensorflow/compiler/xla/tests/fuzz:rand_000005_cpu PASSED in 12.1s //tensorflow/compiler/xla/tests/fuzz:rand_000006_cpu PASSED in 12.0s //tensorflow/compiler/xla/tests/fuzz:rand_000007_cpu PASSED in 12.4s //tensorflow/compiler/xla/tests/fuzz:rand_000008_cpu PASSED in 11.5s //tensorflow/compiler/xla/tests/fuzz:rand_000009_cpu PASSED in 12.9s //tensorflow/compiler/xla/tests/fuzz:rand_000013_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests/fuzz:rand_000015_cpu PASSED in 13.8s //tensorflow/compiler/xla/tests/fuzz:rand_000016_cpu PASSED in 14.9s //tensorflow/compiler/xla/tests/fuzz:rand_000017_cpu PASSED in 13.0s //tensorflow/compiler/xla/tests/fuzz:rand_000018_cpu PASSED in 12.4s //tensorflow/compiler/xla/tests/fuzz:rand_000019_cpu PASSED in 11.3s //tensorflow/compiler/xla/tests/fuzz:rand_000020_cpu PASSED in 11.2s //tensorflow/compiler/xla/tests/fuzz:rand_000022_cpu PASSED in 13.7s //tensorflow/compiler/xla/tests/fuzz:rand_000024_cpu PASSED in 10.9s //tensorflow/compiler/xla/tests/fuzz:rand_000025_cpu PASSED in 11.6s //tensorflow/compiler/xla/tests/fuzz:rand_000026_cpu PASSED in 10.7s //tensorflow/compiler/xla/tests/fuzz:rand_000030_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests/fuzz:rand_000031_cpu PASSED in 11.5s //tensorflow/compiler/xla/tests/fuzz:rand_000032_cpu PASSED in 16.8s //tensorflow/compiler/xla/tests/fuzz:rand_000033_cpu PASSED in 15.1s //tensorflow/compiler/xla/tests/fuzz:rand_000034_cpu PASSED in 15.3s //tensorflow/compiler/xla/tests/fuzz:rand_000035_cpu PASSED in 10.8s //tensorflow/compiler/xla/tests/fuzz:rand_000036_cpu PASSED in 11.5s //tensorflow/compiler/xla/tests/fuzz:rand_000039_cpu PASSED in 16.7s //tensorflow/compiler/xla/tests/fuzz:rand_000040_cpu PASSED in 15.2s //tensorflow/compiler/xla/tests/fuzz:rand_000041_cpu PASSED in 14.8s //tensorflow/compiler/xla/tests/fuzz:rand_000043_cpu PASSED in 11.6s //tensorflow/compiler/xla/tests/fuzz:rand_000049_cpu PASSED in 11.2s //tensorflow/compiler/xla/tests/fuzz:rand_000053_cpu PASSED in 12.6s //tensorflow/compiler/xla/tests/fuzz:rand_000056_cpu PASSED in 16.1s //tensorflow/compiler/xla/tests/fuzz:rand_000059_cpu PASSED in 10.7s //tensorflow/compiler/xla/tests/fuzz:rand_000061_cpu PASSED in 15.0s //tensorflow/compiler/xla/tests/fuzz:rand_000062_cpu PASSED in 16.5s //tensorflow/compiler/xla/tests/fuzz:rand_000064_cpu PASSED in 13.3s //tensorflow/compiler/xla/tests/fuzz:rand_000066_cpu PASSED in 11.4s //tensorflow/compiler/xla/tests/fuzz:rand_000069_cpu PASSED in 13.3s //tensorflow/compiler/xla/tests/fuzz:rand_000071_cpu PASSED in 10.6s //tensorflow/compiler/xla/tests/fuzz:rand_000077_cpu PASSED in 11.7s //tensorflow/compiler/xla/tests/fuzz:rand_000078_cpu PASSED in 11.0s //tensorflow/compiler/xla/tests/fuzz:rand_000079_cpu PASSED in 12.4s //tensorflow/compiler/xla/tests/fuzz:rand_000081_cpu PASSED in 13.8s //tensorflow/compiler/xla/tests/fuzz:rand_000084_cpu PASSED in 9.9s //tensorflow/compiler/xla/tests/fuzz:rand_000085_cpu PASSED in 16.0s //tensorflow/compiler/xla/tests/fuzz:rand_000086_cpu PASSED in 10.9s //tensorflow/compiler/xla/tests/fuzz:rand_000088_cpu PASSED in 17.0s //tensorflow/compiler/xla/tests/fuzz:rand_000089_cpu PASSED in 10.9s //tensorflow/compiler/xla/tests/fuzz:rand_000090_cpu PASSED in 9.7s //tensorflow/compiler/xla/tests/fuzz:rand_000092_cpu PASSED in 13.9s //tensorflow/compiler/xla/tests/fuzz:rand_000094_cpu PASSED in 11.9s //tensorflow/compiler/xla/tests/fuzz:rand_000095_cpu PASSED in 12.8s //tensorflow/compiler/xla/tools:hlo_control_flow_flattening_test PASSED in 1.0s //tensorflow/compiler/xla/tools:hlo_extractor_test PASSED in 1.2s //tensorflow/compiler/xla/tools:hlo_module_loader_test PASSED in 1.7s //tensorflow/compiler/xla/tools:interactive_graphviz_bin_test PASSED in 1.0s //tensorflow/compiler/xla/tools:run_hlo_module_bin_test PASSED in 0.6s //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 0.9s //tensorflow/compiler/xla/translate/hlo_to_mhlo:mlir_hlo_builder_test PASSED in 1.2s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:bool_compare.hlotxt.test PASSED in 0.9s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:case_conditional.hlotxt.test PASSED in 0.5s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:dynamic_param.hlo.test PASSED in 0.9s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:entry_computation_layout.hlotxt.test PASSED in 0.6s //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 1.3s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:fusion.hlotxt.test PASSED in 1.1s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:if_conditional.hlotxt.test PASSED in 0.5s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:import.hlotxt.test PASSED in 0.5s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:import_async.hlotxt.test PASSED in 1.2s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:layouts_and_names.hlotxt.test PASSED in 0.5s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:location.hlotxt.test PASSED in 0.8s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:module_attributes.hlo.test PASSED in 1.3s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:simple.hlo.test PASSED in 0.5s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:spmd_module_sharding.hlo.test PASSED in 1.2s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:types.hlotxt.test PASSED in 1.1s //tensorflow/compiler/xla/translate/hlo_to_mhlo/tests:while.hlotxt.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo:type_to_shape_test PASSED in 1.0s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:add.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:case.mlir.test PASSED in 1.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:dynamic.mlir.test PASSED in 0.8s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export-with-layouts.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export.mlir.test PASSED in 1.8s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export_and_check_layouts.mlir.test PASSED in 1.2s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export_large_constants.mlir.test PASSED in 1.9s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:export_replicas.mlir.test PASSED in 0.4s //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 1.4s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:if.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:input_output_aliasing.mlir.test PASSED in 1.3s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:layouts_and_names.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:location_to_op_metadata.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:missing_main.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:module_attributes.mlir.test PASSED in 0.5s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:multiple_return_tuple.mlir.test PASSED in 0.6s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:opaque_elements_attr.mlir.test PASSED in 0.7s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:rng_get_and_update_state.mlir.test PASSED in 0.4s //tensorflow/compiler/xla/translate/mhlo_to_hlo/tests:sharding.mlir.test PASSED in 0.6s //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 1.4s //tensorflow/compiler/xla/translate/mhlo_to_lhlo_with_xla/tests:hlo_text_to_lhlo_no_opt.hlotxt.test PASSED in 3.7s //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 0.7s //tensorflow/compiler/xla/translate/mhlo_to_lhlo_with_xla/tests:ops.mlir.test PASSED in 2.4s //tensorflow/compiler/xla/translate/mhlo_to_lhlo_with_xla/tests:passthrough.mlir.test PASSED in 0.6s //tensorflow/core:__tensorflow_core_lib_core_legacy_lib_core_all_tests PASSED in 10.1s //tensorflow/core:__tensorflow_core_lib_gtl_legacy_lib_gtl_tests PASSED in 0.7s //tensorflow/core:__tensorflow_core_lib_monitoring_cell_reader_test PASSED in 37.5s //tensorflow/core:__tensorflow_core_lib_monitoring_collection_registry_test PASSED in 0.5s //tensorflow/core:__tensorflow_core_lib_monitoring_counter_test PASSED in 0.1s //tensorflow/core:__tensorflow_core_lib_monitoring_gauge_test PASSED in 0.2s //tensorflow/core:__tensorflow_core_lib_monitoring_metric_def_test PASSED in 0.4s //tensorflow/core:__tensorflow_core_lib_monitoring_percentile_sampler_test PASSED in 0.1s //tensorflow/core:__tensorflow_core_lib_monitoring_sampler_test PASSED in 0.6s //tensorflow/core:__tensorflow_core_lib_monitoring_test_utils_test PASSED in 0.6s //tensorflow/core:__tensorflow_core_lib_strings_legacy_low_level_library_tests PASSED in 0.3s //tensorflow/core:__tensorflow_core_lib_wav_wav_io_test PASSED in 0.1s //tensorflow/core:__tensorflow_core_util_mkl_util_test_srcs PASSED in 0.1s //tensorflow/core:__tensorflow_tsl_lib_core_legacy_lib_core_all_tests PASSED in 0.6s //tensorflow/core:lib_strings_ordered_code_test PASSED in 1.7s //tensorflow/core:lib_strings_proto_serialization_test PASSED in 0.3s //tensorflow/core/api_def:api_test PASSED in 7.1s //tensorflow/core/api_def:update_api_def_test PASSED in 0.3s //tensorflow/core/common_runtime:all_to_all_test_cpu PASSED in 0.9s //tensorflow/core/common_runtime:arg_ret_placement_test PASSED in 0.5s //tensorflow/core/common_runtime:buf_rendezvous_test PASSED in 1.4s //tensorflow/core/common_runtime:collective_executor_mgr_test PASSED in 0.8s //tensorflow/core/common_runtime:collective_param_resolver_local_test PASSED in 7.0s //tensorflow/core/common_runtime:collective_rma_local_test PASSED in 1.5s //tensorflow/core/common_runtime:composite_device_test PASSED in 1.1s //tensorflow/core/common_runtime:cost_measurement_registry_test PASSED in 2.6s //tensorflow/core/common_runtime:cost_util_test PASSED in 0.3s //tensorflow/core/common_runtime:device_mgr_test PASSED in 0.8s //tensorflow/core/common_runtime:device_propagation_test PASSED in 0.8s //tensorflow/core/common_runtime:device_resolver_local_test PASSED in 2.1s //tensorflow/core/common_runtime:device_set_test PASSED in 1.3s //tensorflow/core/common_runtime:direct_session_test_cpu PASSED in 3.6s //tensorflow/core/common_runtime:direct_session_with_debug_test PASSED in 5.4s //tensorflow/core/common_runtime:direct_session_with_tracking_alloc_test PASSED in 1.5s //tensorflow/core/common_runtime:dynamic_device_mgr_test PASSED in 1.3s //tensorflow/core/common_runtime:eval_const_tensor_test PASSED in 1.2s //tensorflow/core/common_runtime:executor_test PASSED in 4.7s //tensorflow/core/common_runtime:function_optimization_registration_test PASSED in 1.2s //tensorflow/core/common_runtime:function_optimization_registry_no_pass_test PASSED in 0.7s //tensorflow/core/common_runtime:function_optimization_registry_pass_failure_test PASSED in 0.9s //tensorflow/core/common_runtime:function_optimization_registry_test PASSED in 2.0s //tensorflow/core/common_runtime:function_threadpool_test PASSED in 1.7s //tensorflow/core/common_runtime:graph_constructor_test PASSED in 2.7s //tensorflow/core/common_runtime:graph_runner_test PASSED in 2.1s //tensorflow/core/common_runtime:hierarchical_tree_broadcaster_test_cpu PASSED in 6.6s //tensorflow/core/common_runtime:inline_function_utils_test PASSED in 0.7s //tensorflow/core/common_runtime:input_colocation_exemption_registry_test PASSED in 0.7s //tensorflow/core/common_runtime:int32_fulltype_test PASSED in 0.6s //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 2.1s //tensorflow/core/common_runtime:lower_function_call_test PASSED in 2.1s //tensorflow/core/common_runtime:lower_functional_ops_test PASSED in 1.9s //tensorflow/core/common_runtime:lower_if_op_test PASSED in 2.3s //tensorflow/core/common_runtime:lower_while_op_test PASSED in 3.4s //tensorflow/core/common_runtime:mkl_cpu_allocator_test PASSED in 0.4s //tensorflow/core/common_runtime:mkl_threadpool_device_test PASSED in 0.3s //tensorflow/core/common_runtime:no_op_cost_measurement_test PASSED in 0.7s //tensorflow/core/common_runtime:null_request_cost_accessor_test PASSED in 0.2s //tensorflow/core/common_runtime:optimization_registry_test PASSED in 1.7s //tensorflow/core/common_runtime:optimize_cross_host_control_deps_test PASSED in 7.0s //tensorflow/core/common_runtime:optimize_function_graph_utils_test PASSED in 0.8s //tensorflow/core/common_runtime:partitioning_utils_test PASSED in 0.6s //tensorflow/core/common_runtime:pending_counts_test PASSED in 1.4s //tensorflow/core/common_runtime:permuter_test_cpu PASSED in 3.7s //tensorflow/core/common_runtime:placer_inspection_required_ops_utils_test PASSED in 1.1s //tensorflow/core/common_runtime:placer_test PASSED in 1.7s //tensorflow/core/common_runtime:process_function_library_runtime_test_cpu PASSED in 1.1s //tensorflow/core/common_runtime:process_util_test PASSED in 0.7s //tensorflow/core/common_runtime:quantize_training_test PASSED in 2.4s //tensorflow/core/common_runtime:rendezvous_util_test PASSED in 0.7s //tensorflow/core/common_runtime:replicate_per_replica_nodes_test PASSED in 0.9s //tensorflow/core/common_runtime:request_cost_accessor_registry_test PASSED in 2.1s //tensorflow/core/common_runtime:request_cost_test PASSED in 0.2s //tensorflow/core/common_runtime:ring_gatherer_test_cpu PASSED in 3.5s //tensorflow/core/common_runtime:ring_reducer_test_cpu PASSED in 7.0s //tensorflow/core/common_runtime:scoped_allocator_mgr_test PASSED in 5.1s //tensorflow/core/common_runtime:session_test PASSED in 1.5s //tensorflow/core/common_runtime:shape_refiner_test PASSED in 0.9s //tensorflow/core/common_runtime:single_threaded_executor_test PASSED in 1.4s //tensorflow/core/common_runtime:threadpool_device_test PASSED in 1.9s //tensorflow/core/common_runtime:type_inference_test PASSED in 2.7s //tensorflow/core/common_runtime/eager:attr_builder_test PASSED in 29.7s //tensorflow/core/common_runtime/eager:context_test PASSED in 13.3s //tensorflow/core/common_runtime/eager:custom_device_test PASSED in 13.5s //tensorflow/core/common_runtime/eager:eager_executor_test PASSED in 12.9s //tensorflow/core/common_runtime/eager:eager_op_rewrite_registry_test PASSED in 0.9s //tensorflow/core/common_runtime/eager:eager_operation_test PASSED in 11.3s //tensorflow/core/common_runtime/eager:execute_node_test PASSED in 17.6s //tensorflow/core/common_runtime/eager:execute_test PASSED in 36.7s //tensorflow/core/common_runtime/eager:kernel_and_device_test PASSED in 0.9s //tensorflow/core/common_runtime/eager:mkl_eager_op_rewrite_test PASSED in 20.0s //tensorflow/core/common_runtime/eager:placement_test PASSED in 14.3s //tensorflow/core/common_runtime/eager:placement_utils_test PASSED in 15.5s //tensorflow/core/common_runtime/eager:tensor_handle_data_test PASSED in 12.8s //tensorflow/core/common_runtime/eager:tensor_handle_test PASSED in 20.1s //tensorflow/core/common_runtime/gpu:gpu_device_on_non_gpu_machine_test PASSED in 0.9s //tensorflow/core/common_runtime/next_pluggable_device/c:plugin_c_api_test PASSED in 40.7s //tensorflow/core/config:flags_py_test PASSED in 6.6s //tensorflow/core/config:flags_test PASSED in 0.1s //tensorflow/core/data:compression_utils_test PASSED in 2.0s //tensorflow/core/data:dataset_utils_test PASSED in 1.4s //tensorflow/core/data:hash_utils_test PASSED in 1.0s //tensorflow/core/data:metric_utils_test PASSED in 6.2s //tensorflow/core/data:name_utils_test PASSED in 0.1s //tensorflow/core/data:rewrite_utils_test PASSED in 1.0s //tensorflow/core/data:serialization_utils_test PASSED in 1.8s //tensorflow/core/data:snapshot_utils_test PASSED in 1.4s //tensorflow/core/data:split_utils_test PASSED in 0.7s //tensorflow/core/data:standalone_save_restore_test PASSED in 2.3s //tensorflow/core/data:standalone_test PASSED in 1.4s //tensorflow/core/data:tfdataz_metrics_test PASSED in 3.6s //tensorflow/core/data:unbounded_thread_pool_test PASSED in 1.3s //tensorflow/core/data/service:auto_shard_rewriter_test PASSED in 0.8s //tensorflow/core/data/service:common_test PASSED in 0.5s //tensorflow/core/data/service:credentials_factory_test PASSED in 1.7s //tensorflow/core/data/service:cross_trainer_cache_test PASSED in 1.6s //tensorflow/core/data/service:data_service_test PASSED in 19.6s //tensorflow/core/data/service:data_transfer_test PASSED in 0.8s //tensorflow/core/data/service:dataset_store_test PASSED in 0.9s //tensorflow/core/data/service:dispatcher_client_test PASSED in 3.6s //tensorflow/core/data/service:dispatcher_state_test PASSED in 1.4s //tensorflow/core/data/service:grpc_dispatcher_impl_test PASSED in 3.1s //tensorflow/core/data/service:grpc_util_test PASSED in 0.8s //tensorflow/core/data/service:grpc_worker_impl_test PASSED in 4.7s //tensorflow/core/data/service:journal_test PASSED in 0.6s //tensorflow/core/data/service:logging_utils_test PASSED in 0.6s //tensorflow/core/data/service:task_runner_test PASSED in 4.0s //tensorflow/core/data/service:test_util_test PASSED in 3.7s //tensorflow/core/data/service:url_test PASSED in 0.2s //tensorflow/core/data/service:utils_test PASSED in 0.6s //tensorflow/core/data/service:validate_utils_test PASSED in 0.3s //tensorflow/core/data/service:worker_client_test PASSED in 8.1s //tensorflow/core/data/service:worker_impl_test PASSED in 6.2s //tensorflow/core/data/service/client:data_service_client_test PASSED in 4.5s //tensorflow/core/data/service/client:utils_test PASSED in 2.9s //tensorflow/core/data/service/client:validate_utils_test PASSED in 2.4s //tensorflow/core/data/service/snapshot:distributed_snapshot_test PASSED in 19.3s //tensorflow/core/data/service/snapshot:file_utils_test PASSED in 0.7s //tensorflow/core/data/service/snapshot:path_utils_test PASSED in 0.6s //tensorflow/core/data/service/snapshot:snapshot_manager_test PASSED in 3.8s //tensorflow/core/data/service/snapshot:snapshot_split_provider_test PASSED in 1.0s //tensorflow/core/data/service/snapshot:snapshot_stream_writer_checkpoint_test PASSED in 3.9s //tensorflow/core/data/service/snapshot:snapshot_stream_writer_test PASSED in 2.6s //tensorflow/core/data/service/snapshot:utils_test PASSED in 0.6s //tensorflow/core/debug:debug_graph_utils_test PASSED in 0.8s //tensorflow/core/distributed_runtime:call_options_test PASSED in 0.4s //tensorflow/core/distributed_runtime:cluster_function_library_runtime_test PASSED in 5.2s //tensorflow/core/distributed_runtime:collective_param_resolver_distributed_test PASSED in 1.1s //tensorflow/core/distributed_runtime:collective_rma_distributed_test PASSED in 0.5s //tensorflow/core/distributed_runtime:device_resolver_distributed_test PASSED in 0.7s //tensorflow/core/distributed_runtime:message_wrappers_test PASSED in 0.3s //tensorflow/core/distributed_runtime:partial_run_mgr_test PASSED in 1.4s //tensorflow/core/distributed_runtime:recent_request_ids_test PASSED in 0.1s //tensorflow/core/distributed_runtime:request_id_test PASSED in 0.7s //tensorflow/core/distributed_runtime:rpc_collective_executor_mgr_test PASSED in 0.8s //tensorflow/core/distributed_runtime:server_lib_test PASSED in 0.3s //tensorflow/core/distributed_runtime:session_mgr_test PASSED in 1.4s //tensorflow/core/distributed_runtime:tensor_coding_test PASSED in 0.2s //tensorflow/core/distributed_runtime/coordination:coordination_service_barrier_proxy_test PASSED in 3.5s //tensorflow/core/distributed_runtime/eager:eager_service_impl_test PASSED in 21.7s //tensorflow/core/distributed_runtime/eager:remote_mgr_test PASSED in 12.0s //tensorflow/core/distributed_runtime/integration_test:c_api_multi_client_test_cpu PASSED in 39.4s //tensorflow/core/distributed_runtime/integration_test:c_api_recoverable_jobs_test_cpu PASSED in 51.3s //tensorflow/core/distributed_runtime/integration_test:c_api_session_coordination_test_cpu PASSED in 40.3s //tensorflow/core/distributed_runtime/rpc:grpc_tensor_coding_test PASSED in 3.4s //tensorflow/core/distributed_runtime/rpc:grpc_worker_cache_test PASSED in 1.4s //tensorflow/core/distributed_runtime/rpc/eager:grpc_eager_client_test PASSED in 0.7s //tensorflow/core/example:example_parser_configuration_test PASSED in 0.6s //tensorflow/core/example:feature_util_test PASSED in 0.4s //tensorflow/core/framework:allocator_test PASSED in 5.6s //tensorflow/core/framework:attr_value_util_test PASSED in 0.9s //tensorflow/core/framework:batch_util_test PASSED in 1.4s //tensorflow/core/framework:bfloat16_test PASSED in 1.0s //tensorflow/core/framework:common_shape_fns_test PASSED in 1.0s //tensorflow/core/framework:dataset_test PASSED in 1.4s //tensorflow/core/framework:device_base_test PASSED in 1.5s //tensorflow/core/framework:disable_jit_test PASSED in 0.8s //tensorflow/core/framework:framework_op_gen_lib_test PASSED in 0.1s //tensorflow/core/framework:framework_op_segment_test PASSED in 1.3s //tensorflow/core/framework:framework_resource_var_test PASSED in 0.1s //tensorflow/core/framework:framework_run_handler_test PASSED in 1.9s //tensorflow/core/framework:framework_run_handler_util_test PASSED in 2.3s //tensorflow/core/framework:full_type_inference_util_test PASSED in 1.6s //tensorflow/core/framework:full_type_util_test PASSED in 0.8s //tensorflow/core/framework:function_test PASSED in 0.9s //tensorflow/core/framework:graph_def_util_test PASSED in 0.7s //tensorflow/core/framework:graph_to_functiondef_test PASSED in 2.6s //tensorflow/core/framework:kernel_def_builder_test PASSED in 1.4s //tensorflow/core/framework:kernel_def_util_test PASSED in 0.8s //tensorflow/core/framework:memory_types_test PASSED in 1.1s //tensorflow/core/framework:model_test PASSED in 1.3s //tensorflow/core/framework:node_def_builder_test PASSED in 1.0s //tensorflow/core/framework:node_def_util_test PASSED in 1.4s //tensorflow/core/framework:node_properties_test PASSED in 0.9s //tensorflow/core/framework:op_compatibility_test PASSED in 1.7s //tensorflow/core/framework:op_def_builder_test PASSED in 1.4s //tensorflow/core/framework:op_def_util_test PASSED in 1.0s //tensorflow/core/framework:op_kernel_test PASSED in 0.9s //tensorflow/core/framework:op_registration_test PASSED in 0.8s //tensorflow/core/framework:partial_tensor_shape_test PASSED in 0.7s //tensorflow/core/framework:rendezvous_test PASSED in 5.7s //tensorflow/core/framework:resource_handle_test PASSED in 0.1s //tensorflow/core/framework:resource_mgr_test PASSED in 1.9s //tensorflow/core/framework:resource_op_kernel_test PASSED in 1.0s //tensorflow/core/framework:shape_inference_test PASSED in 1.5s //tensorflow/core/framework:shape_inference_testutil_test PASSED in 1.4s //tensorflow/core/framework:tensor_shape_test PASSED in 6.8s //tensorflow/core/framework:tensor_slice_test PASSED in 1.0s //tensorflow/core/framework:tensor_test PASSED in 29.8s //tensorflow/core/framework:tensor_testutil_test PASSED in 2.5s //tensorflow/core/framework:tensor_util_test PASSED in 2.9s //tensorflow/core/framework:tracking_allocator_test PASSED in 1.9s //tensorflow/core/framework:types_test PASSED in 1.1s //tensorflow/core/framework:variant_op_registry_test PASSED in 20.4s //tensorflow/core/framework:variant_test PASSED in 1.0s //tensorflow/core/framework/registration:registration_test PASSED in 0.7s //tensorflow/core/function/capture:by_ref_capture_test PASSED in 6.8s //tensorflow/core/function/capture:capture_container_test PASSED in 7.4s //tensorflow/core/function/integration_test:side_inputs_manual_api_test PASSED in 16.6s //tensorflow/core/function/integration_test:side_inputs_test PASSED in 19.0s //tensorflow/core/function/polymorphism:function_cache_test PASSED in 7.0s //tensorflow/core/function/polymorphism:function_type_test PASSED in 8.6s //tensorflow/core/function/polymorphism:type_dispatch_test PASSED in 7.2s //tensorflow/core/function/runtime_client:runtime_client_cc_test PASSED in 48.8s //tensorflow/core/function/trace_type:default_types_test PASSED in 7.0s //tensorflow/core/function/trace_type:serialization_test PASSED in 7.9s //tensorflow/core/function/trace_type:trace_type_test PASSED in 11.5s //tensorflow/core/graph:algorithm_test PASSED in 2.8s //tensorflow/core/graph:collective_order_test PASSED in 0.8s //tensorflow/core/graph:control_flow_test PASSED in 0.9s //tensorflow/core/graph:costmodel_test PASSED in 1.7s //tensorflow/core/graph:edgeset_test PASSED in 0.9s //tensorflow/core/graph:graph_debug_info_builder_test PASSED in 1.0s //tensorflow/core/graph:graph_def_builder_test PASSED in 1.2s //tensorflow/core/graph:graph_partition_test PASSED in 1.3s //tensorflow/core/graph:graph_test PASSED in 1.1s //tensorflow/core/graph:node_builder_test PASSED in 1.0s //tensorflow/core/graph:optimizer_cse_test PASSED in 1.2s //tensorflow/core/graph:subgraph_test PASSED in 0.9s //tensorflow/core/graph:tensor_id_test PASSED in 1.0s //tensorflow/core/graph:validate_test PASSED in 1.2s //tensorflow/core/graph/regularization:simple_delete_test PASSED in 0.8s //tensorflow/core/graph/regularization:util_test PASSED in 0.2s //tensorflow/core/grappler:graph_topology_view_test PASSED in 0.4s //tensorflow/core/grappler:graph_view_test PASSED in 1.8s //tensorflow/core/grappler:grappler_item_builder_test PASSED in 1.8s //tensorflow/core/grappler:grappler_item_test PASSED in 1.7s //tensorflow/core/grappler:mutable_graph_view_test PASSED in 1.5s //tensorflow/core/grappler:utils_test PASSED in 2.7s //tensorflow/core/grappler/clusters:single_machine_test PASSED in 24.3s //tensorflow/core/grappler/clusters:virtual_cluster_test PASSED in 2.8s //tensorflow/core/grappler/costs:analytical_cost_estimator_test PASSED in 1.7s //tensorflow/core/grappler/costs:cost_estimator_test PASSED in 0.4s //tensorflow/core/grappler/costs:graph_memory_test PASSED in 2.2s //tensorflow/core/grappler/costs:graph_properties_test PASSED in 12.1s //tensorflow/core/grappler/costs:robust_stats_test PASSED in 0.4s //tensorflow/core/grappler/costs:utils_test PASSED in 1.9s //tensorflow/core/grappler/costs:virtual_placer_test PASSED in 1.3s //tensorflow/core/grappler/costs:virtual_scheduler_test PASSED in 3.9s //tensorflow/core/grappler/graph_analyzer:gen_node_test PASSED in 1.8s //tensorflow/core/grappler/graph_analyzer:graph_analyzer_test PASSED in 2.5s //tensorflow/core/grappler/graph_analyzer:hash_tools_test PASSED in 1.7s //tensorflow/core/grappler/graph_analyzer:sig_node_test PASSED in 3.1s //tensorflow/core/grappler/graph_analyzer:subgraph_test PASSED in 2.0s //tensorflow/core/grappler/inputs:utils_test PASSED in 0.1s //tensorflow/core/grappler/optimizers:arithmetic_optimizer_test_cpu PASSED in 4.6s //tensorflow/core/grappler/optimizers:auto_mixed_precision_test_cpu PASSED in 2.6s //tensorflow/core/grappler/optimizers:auto_parallel_test_cpu PASSED in 3.4s //tensorflow/core/grappler/optimizers:common_subgraph_elimination_test_cpu PASSED in 1.2s //tensorflow/core/grappler/optimizers:custom_graph_optimizer_registry_test_cpu PASSED in 4.5s //tensorflow/core/grappler/optimizers:debug_stripper_test_cpu PASSED in 1.8s //tensorflow/core/grappler/optimizers:dependency_optimizer_test_cpu PASSED in 3.1s //tensorflow/core/grappler/optimizers:evaluation_utils_test PASSED in 0.5s //tensorflow/core/grappler/optimizers:function_api_info_test PASSED in 0.2s //tensorflow/core/grappler/optimizers:function_optimizer_test_cpu PASSED in 5.1s //tensorflow/core/grappler/optimizers:generic_layout_optimizer_test_cpu PASSED in 1.6s //tensorflow/core/grappler/optimizers:generic_layout_optimizer_transposer_factory_test PASSED in 0.2s //tensorflow/core/grappler/optimizers:generic_layout_optimizer_transposer_test_cpu PASSED in 2.0s //tensorflow/core/grappler/optimizers:graph_optimizer_stage_test_cpu PASSED in 1.8s //tensorflow/core/grappler/optimizers:implementation_selector_test PASSED in 3.3s //tensorflow/core/grappler/optimizers:loop_optimizer_test_cpu PASSED in 2.5s //tensorflow/core/grappler/optimizers:memory_optimizer_test_cpu PASSED in 2.1s //tensorflow/core/grappler/optimizers:meta_optimizer_test_cpu PASSED in 9.7s //tensorflow/core/grappler/optimizers:mkl_remapper_test PASSED in 2.6s //tensorflow/core/grappler/optimizers:model_pruner_test_cpu PASSED in 2.2s //tensorflow/core/grappler/optimizers:pin_to_host_optimizer_test_cpu PASSED in 2.9s //tensorflow/core/grappler/optimizers:remapper_test_cpu PASSED in 2.7s //tensorflow/core/grappler/optimizers:scoped_allocator_optimizer_test PASSED in 1.8s //tensorflow/core/grappler/optimizers:shape_optimizer_test_cpu PASSED in 2.8s //tensorflow/core/grappler/optimizers:static_schedule_test_cpu PASSED in 1.7s //tensorflow/core/grappler/optimizers:tfg_optimizer_hook_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:auto_shard_test PASSED in 0.6s //tensorflow/core/grappler/optimizers/data:autotune_buffer_sizes_test PASSED in 1.4s //tensorflow/core/grappler/optimizers/data:batch_parallelization_test PASSED in 0.7s //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 0.9s //tensorflow/core/grappler/optimizers/data:enable_gradient_descent_test PASSED in 1.8s //tensorflow/core/grappler/optimizers/data:filter_fusion_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:filter_parallelization_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:function_utils_test PASSED in 0.7s //tensorflow/core/grappler/optimizers/data:fusion_utils_test PASSED in 1.2s //tensorflow/core/grappler/optimizers/data:graph_utils_test PASSED in 0.5s //tensorflow/core/grappler/optimizers/data:inject_prefetch_test PASSED in 0.8s //tensorflow/core/grappler/optimizers/data:make_deterministic_test PASSED in 0.6s //tensorflow/core/grappler/optimizers/data:make_sloppy_test PASSED in 2.8s //tensorflow/core/grappler/optimizers/data:map_and_batch_fusion_test PASSED in 1.1s //tensorflow/core/grappler/optimizers/data:map_and_filter_fusion_test PASSED in 0.6s //tensorflow/core/grappler/optimizers/data:map_fusion_test PASSED in 0.9s //tensorflow/core/grappler/optimizers/data:map_parallelization_test PASSED in 1.1s //tensorflow/core/grappler/optimizers/data:noop_elimination_test PASSED in 0.4s //tensorflow/core/grappler/optimizers/data:parallel_batch_test PASSED in 1.4s //tensorflow/core/grappler/optimizers/data:replicate_on_split_test PASSED in 1.4s //tensorflow/core/grappler/optimizers/data:shuffle_and_repeat_fusion_test PASSED in 0.9s //tensorflow/core/grappler/optimizers/data:slack_test PASSED in 1.8s //tensorflow/core/grappler/optimizers/data:split_utils_test PASSED in 1.5s //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 0.2s //tensorflow/core/grappler/utils:canonicalizer_test PASSED in 2.1s //tensorflow/core/grappler/utils:colocation_test PASSED in 2.1s //tensorflow/core/grappler/utils:frame_test PASSED in 0.1s //tensorflow/core/grappler/utils:functions_test PASSED in 1.7s //tensorflow/core/grappler/utils:graph_view_internal_test PASSED in 1.1s //tensorflow/core/grappler/utils:graph_view_test PASSED in 2.3s //tensorflow/core/grappler/utils:grappler_test_test PASSED in 8.4s //tensorflow/core/grappler/utils:pattern_utils_test PASSED in 1.1s //tensorflow/core/grappler/utils:scc_test PASSED in 1.2s //tensorflow/core/grappler/utils:symbolic_shapes_test PASSED in 0.1s //tensorflow/core/grappler/utils:topological_sort_test PASSED in 1.4s //tensorflow/core/grappler/utils:tpu_test PASSED in 0.2s //tensorflow/core/grappler/utils:transitive_fanin_test PASSED in 0.6s //tensorflow/core/grappler/utils:traversal_test PASSED in 0.5s //tensorflow/core/grappler/verifiers:structure_verifier_test PASSED in 1.3s //tensorflow/core/ir:interfaces_test PASSED in 0.7s //tensorflow/core/ir:ops_test PASSED in 0.2s //tensorflow/core/ir:shape_inference_utils_test PASSED in 0.5s //tensorflow/core/ir:tf_op_registry_test PASSED in 0.4s //tensorflow/core/ir:tf_op_wrapper_test PASSED in 0.4s //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 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:backedge_segment.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:empty.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:error_during_backedge.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:import_case_with_attr_inference.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:import_if_with_attr_inference.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:import_iterator_get_next_attr_inference.pbtxt.test PASSED in 0.8s //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 0.4s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:infer_arg_handle_type.pbtxt.test PASSED in 1.3s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:infer_with_output_shapes.pbtxt.test PASSED in 1.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_arg_name.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_backedge_input_size.pbtxt.test PASSED in 1.0s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_duplicated_node_name.pbtxt.test PASSED in 0.7s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_edge_index.pbtxt.test PASSED in 0.4s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_edge_name.pbtxt.test PASSED in 0.6s //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 1.1s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_empty_func_attr_name.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_empty_op_type.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_func_with_empty_name.pbtxt.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_function_import.pbtxt.test PASSED in 0.7s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_func_with_empty_control_result.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_func_with_empty_input.pbtxt.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_func_with_empty_name.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_func_with_empty_result.pbtxt.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_generic_function_attr_name.pbtxt.test PASSED in 1.4s //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 0.4s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_control_input.pbtxt.test PASSED in 0.7s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_control_result.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_control_result_value.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_data_result.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_data_result_value.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_input.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_missing_two_inputs.pbtxt.test PASSED in 2.0s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_named_edge_index.pbtxt.test PASSED in 0.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_op_name.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:invalid_type_list.pbtxt.test PASSED in 0.7s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:legacy_call.pbtxt.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:negative_shape.pbtxt.test PASSED in 0.7s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:negative_zero_constant.pbtxt.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:three_nodes_with_attrs.pbtxt.test PASSED in 2.9s //tensorflow/core/ir/importexport/tests/graphdef_to_mlir:version.pbtxt.test PASSED in 1.3s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:empty.mlir.test PASSED in 0.8s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:fulltype.mlir.test PASSED in 0.6s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:func_with_no_args_or_results.mlir.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:negative_zero_constant.mlir.test PASSED in 1.2s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:nested_legacy_call.mlir.test PASSED in 0.5s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:three_nodes_with_attrs.mlir.test PASSED in 1.1s //tensorflow/core/ir/importexport/tests/mlir_to_graphdef:version.mlir.test PASSED in 1.8s //tensorflow/core/ir/importexport/tests/saved_model:saved_model_roundtrip_test PASSED in 1.0s //tensorflow/core/ir/tests:attributes.mlir.test PASSED in 0.9s //tensorflow/core/ir/tests:canonicalize.mlir.test PASSED in 0.6s //tensorflow/core/ir/tests:compatible_types.mlir.test PASSED in 0.5s //tensorflow/core/ir/tests:concrete-ops.mlir.test PASSED in 0.7s //tensorflow/core/ir/tests:generic_concrete_ops.mlir.test PASSED in 0.4s //tensorflow/core/ir/tests:invalid-concrete-ops.mlir.test PASSED in 1.0s //tensorflow/core/ir/tests:invalid-preserved-attrs.mlir.test PASSED in 0.4s //tensorflow/core/ir/tests:invalid.mlir.test PASSED in 0.7s //tensorflow/core/ir/tests:invalid_types.mlir.test PASSED in 1.3s //tensorflow/core/ir/tests:ops.mlir.test PASSED in 1.1s //tensorflow/core/ir/tests:region-invalid-ops.mlir.test PASSED in 0.4s //tensorflow/core/ir/tests:region-ops-graph.mlir.test PASSED in 0.6s //tensorflow/core/ir/tests:region-ops.mlir.test PASSED in 1.4s //tensorflow/core/ir/tests:types.mlir.test PASSED in 0.5s //tensorflow/core/ir/types:dialect_test PASSED in 0.2s //tensorflow/core/kernels:as_string_op_test PASSED in 0.7s //tensorflow/core/kernels:basic_ops_benchmark_test PASSED in 1.5s //tensorflow/core/kernels:batch_kernels_env_test PASSED in 1.9s //tensorflow/core/kernels:batch_kernels_test PASSED in 1.4s //tensorflow/core/kernels:bias_op_test PASSED in 0.9s //tensorflow/core/kernels:bincount_op_test_cpu PASSED in 1.3s //tensorflow/core/kernels:broadcast_to_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:cast_op_test_cpu PASSED in 6.9s //tensorflow/core/kernels:checkpoint_callback_manager_test PASSED in 0.9s //tensorflow/core/kernels:clustering_ops_test PASSED in 0.5s //tensorflow/core/kernels:composite_tensor_variant_test PASSED in 0.6s //tensorflow/core/kernels:concat_op_test PASSED in 0.9s //tensorflow/core/kernels:constant_op_test_cpu PASSED in 1.4s //tensorflow/core/kernels:control_flow_ops_test PASSED in 9.8s //tensorflow/core/kernels:conv_grad_filter_ops_benchmark_test_cpu PASSED in 1.0s //tensorflow/core/kernels:conv_grad_input_ops_benchmark_test_cpu PASSED in 0.6s //tensorflow/core/kernels:conv_ops_benchmark_test_cpu PASSED in 0.6s //tensorflow/core/kernels:conv_ops_test_cpu PASSED in 5.5s //tensorflow/core/kernels:count_ops_test PASSED in 1.0s //tensorflow/core/kernels:cross_op_test PASSED in 0.7s //tensorflow/core/kernels:cwise_ops_test_cpu PASSED in 1.1s //tensorflow/core/kernels:debug_ops_test PASSED in 2.6s //tensorflow/core/kernels:decode_wav_op_test PASSED in 3.0s //tensorflow/core/kernels:deep_conv2d_test PASSED in 0.5s //tensorflow/core/kernels:dequantize_op_test PASSED in 0.9s //tensorflow/core/kernels:diag_op_test_cpu PASSED in 1.1s //tensorflow/core/kernels:dynamic_partition_op_test_cpu PASSED in 0.8s //tensorflow/core/kernels:dynamic_stitch_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:eigen_activations_test PASSED in 0.1s //tensorflow/core/kernels:eigen_attention_test PASSED in 0.1s //tensorflow/core/kernels:eigen_backward_cuboid_convolutions_test PASSED in 0.7s //tensorflow/core/kernels:eigen_backward_spatial_convolutions_test PASSED in 0.3s //tensorflow/core/kernels:eigen_benchmark_cpu_test PASSED in 0.7s //tensorflow/core/kernels:eigen_mkldnn_contraction_kernel_test PASSED in 0.5s //tensorflow/core/kernels:eigen_pooling_test PASSED in 0.9s //tensorflow/core/kernels:encode_wav_op_test PASSED in 3.2s //tensorflow/core/kernels:fingerprint_op_test PASSED in 1.2s //tensorflow/core/kernels:fused_batch_norm_ex_op_test_cpu PASSED in 1.3s //tensorflow/core/kernels:fused_batch_norm_op_test_cpu PASSED in 0.6s //tensorflow/core/kernels:gather_nd_op_test_cpu PASSED in 0.5s //tensorflow/core/kernels:gather_op_test_cpu PASSED in 1.1s //tensorflow/core/kernels:guarantee_const_op_test PASSED in 0.6s //tensorflow/core/kernels:identity_n_op_test PASSED in 0.8s //tensorflow/core/kernels:identity_op_test PASSED in 0.8s //tensorflow/core/kernels:immutable_constant_op_test PASSED in 1.2s //tensorflow/core/kernels:in_topk_op_test PASSED in 1.0s //tensorflow/core/kernels:isotonic_regression_op_test PASSED in 0.6s //tensorflow/core/kernels:logging_ops_test PASSED in 1.6s //tensorflow/core/kernels:lookup_ops_test PASSED in 1.0s //tensorflow/core/kernels:loss_test PASSED in 0.1s //tensorflow/core/kernels:lrn_op_test_cpu PASSED in 0.6s //tensorflow/core/kernels:matmul_op_test_cpu PASSED in 2.5s //tensorflow/core/kernels:merge_v2_checkpoints_op_test PASSED in 0.9s //tensorflow/core/kernels:mfcc_dct_test PASSED in 0.3s //tensorflow/core/kernels:mfcc_mel_filterbank_test PASSED in 0.7s //tensorflow/core/kernels:mfcc_op_test_cpu PASSED in 3.2s //tensorflow/core/kernels:mfcc_test PASSED in 0.4s //tensorflow/core/kernels:multinomial_op_test_cpu PASSED in 1.0s //tensorflow/core/kernels:nn_ops_test_cpu PASSED in 1.4s //tensorflow/core/kernels:one_hot_op_test PASSED in 1.6s //tensorflow/core/kernels:ops_testutil_test PASSED in 1.7s //tensorflow/core/kernels:ops_util_test PASSED in 0.4s //tensorflow/core/kernels:parameterized_truncated_normal_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:parse_tensor_test PASSED in 0.6s //tensorflow/core/kernels:quantization_utils_test PASSED in 0.7s //tensorflow/core/kernels:quantize_and_dequantize_op_test_cpu PASSED in 1.8s //tensorflow/core/kernels:quantize_down_and_shrink_range_op_test PASSED in 2.1s //tensorflow/core/kernels:quantize_op_test PASSED in 0.5s //tensorflow/core/kernels:quantized_activation_ops_test PASSED in 1.3s //tensorflow/core/kernels:quantized_add_op_test PASSED in 2.0s //tensorflow/core/kernels:quantized_batch_norm_op_test PASSED in 0.5s //tensorflow/core/kernels:quantized_bias_add_op_test PASSED in 1.6s //tensorflow/core/kernels:quantized_concat_op_test PASSED in 1.4s //tensorflow/core/kernels:quantized_conv_ops_test PASSED in 1.5s //tensorflow/core/kernels:quantized_instance_norm_test PASSED in 1.9s //tensorflow/core/kernels:quantized_matmul_op_test PASSED in 2.0s //tensorflow/core/kernels:quantized_mul_op_test PASSED in 1.1s //tensorflow/core/kernels:quantized_pooling_ops_test PASSED in 0.7s //tensorflow/core/kernels:quantized_reshape_op_test PASSED in 1.1s //tensorflow/core/kernels:quantized_resize_bilinear_op_test PASSED in 2.4s //tensorflow/core/kernels:ragged_fill_empty_rows_op_test PASSED in 0.8s //tensorflow/core/kernels:ragged_gather_op_test PASSED in 0.7s //tensorflow/core/kernels:ragged_range_op_test PASSED in 1.6s //tensorflow/core/kernels:ragged_tensor_from_variant_op_test PASSED in 1.6s //tensorflow/core/kernels:ragged_tensor_to_sparse_kernel_test PASSED in 0.6s //tensorflow/core/kernels:ragged_tensor_to_tensor_op_test PASSED in 0.5s //tensorflow/core/kernels:ragged_tensor_to_variant_op_test PASSED in 1.4s //tensorflow/core/kernels:random_binomial_op_test_cpu PASSED in 0.5s //tensorflow/core/kernels:random_index_shuffle_test PASSED in 0.3s //tensorflow/core/kernels:random_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:random_poisson_op_test_cpu PASSED in 1.5s //tensorflow/core/kernels:range_sampler_test PASSED in 0.4s //tensorflow/core/kernels:reduction_ops_test_cpu PASSED in 1.0s //tensorflow/core/kernels:regex_replace_op_test PASSED in 1.0s //tensorflow/core/kernels:requantization_range_op_test PASSED in 0.6s //tensorflow/core/kernels:requantize_op_test PASSED in 1.0s //tensorflow/core/kernels:resource_ops_test PASSED in 1.2s //tensorflow/core/kernels:restore_op_test PASSED in 0.5s //tensorflow/core/kernels:restore_v2_op_test PASSED in 0.6s //tensorflow/core/kernels:reverse_op_test PASSED in 1.3s //tensorflow/core/kernels:roll_op_test PASSED in 1.2s //tensorflow/core/kernels:save_op_test PASSED in 0.9s //tensorflow/core/kernels:save_v2_op_test PASSED in 0.8s //tensorflow/core/kernels:scan_ops_test_cpu PASSED in 0.5s //tensorflow/core/kernels:scatter_nd_op_test_cpu PASSED in 1.4s //tensorflow/core/kernels:scatter_op_test PASSED in 1.3s //tensorflow/core/kernels:scoped_allocator_ops_test_cpu PASSED in 7.8s //tensorflow/core/kernels:sdca_ops_test PASSED in 1.8s //tensorflow/core/kernels:segment_reduction_ops_test PASSED in 0.6s //tensorflow/core/kernels:sendrecv_ops_test PASSED in 0.5s //tensorflow/core/kernels:sequence_ops_test PASSED in 1.6s //tensorflow/core/kernels:shape_ops_test PASSED in 1.2s //tensorflow/core/kernels:slice_op_test PASSED in 0.7s //tensorflow/core/kernels:spacetobatch_benchmark_test_cpu PASSED in 0.6s //tensorflow/core/kernels:sparse_add_op_test PASSED in 0.7s //tensorflow/core/kernels:sparse_dense_binary_op_shared_test PASSED in 1.2s //tensorflow/core/kernels:sparse_fill_empty_rows_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels:sparse_matmul_op_test_cpu PASSED in 0.6s //tensorflow/core/kernels:sparse_reduce_sum_op_test PASSED in 0.8s //tensorflow/core/kernels:sparse_tensor_dense_matmul_op_test_cpu PASSED in 1.8s //tensorflow/core/kernels:sparse_to_dense_op_test_cpu PASSED in 2.1s //tensorflow/core/kernels:sparse_utils_test PASSED in 0.4s //tensorflow/core/kernels:sparse_xent_op_test_cpu PASSED in 0.5s //tensorflow/core/kernels:spectrogram_op_test_cpu PASSED in 1.6s //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 0.8s //tensorflow/core/kernels:strided_slice_op_test PASSED in 0.6s //tensorflow/core/kernels:string_format_op_test PASSED in 0.7s //tensorflow/core/kernels:string_ngrams_op_test PASSED in 1.5s //tensorflow/core/kernels:string_split_op_test PASSED in 1.3s //tensorflow/core/kernels:substr_op_test PASSED in 1.6s //tensorflow/core/kernels:summary_audio_op_test PASSED in 0.6s //tensorflow/core/kernels:summary_image_op_test PASSED in 0.9s //tensorflow/core/kernels:summary_op_test PASSED in 1.9s //tensorflow/core/kernels:summary_tensor_op_test PASSED in 1.0s //tensorflow/core/kernels:tensor_cord_test PASSED in 0.1s //tensorflow/core/kernels:tensor_flag_utils_test PASSED in 0.5s //tensorflow/core/kernels:tensor_map_test PASSED in 0.7s //tensorflow/core/kernels:training_ops_test PASSED in 0.7s //tensorflow/core/kernels:transpose_util_test PASSED in 0.4s //tensorflow/core/kernels:unary_ops_composition_test_cpu PASSED in 4.4s //tensorflow/core/kernels:unique_op_test PASSED in 0.7s //tensorflow/core/kernels:variable_ops_test PASSED in 2.6s //tensorflow/core/kernels:while_op_test PASSED in 1.8s //tensorflow/core/kernels:xent_op_test_cpu PASSED in 0.9s //tensorflow/core/kernels/batching_util:basic_batch_scheduler_test PASSED in 0.6s //tensorflow/core/kernels/batching_util:batch_input_task_test PASSED in 1.7s //tensorflow/core/kernels/batching_util:batch_resource_base_test PASSED in 0.1s //tensorflow/core/kernels/batching_util:batch_scheduler_test PASSED in 0.1s //tensorflow/core/kernels/batching_util:bounded_executor_test PASSED in 20.4s //tensorflow/core/kernels/batching_util:input_split_metadata_test PASSED in 0.4s //tensorflow/core/kernels/batching_util:periodic_function_test PASSED in 1.9s //tensorflow/core/kernels/batching_util:serial_device_batch_scheduler_test PASSED in 2.6s //tensorflow/core/kernels/batching_util:shared_batch_scheduler_test PASSED in 5.5s //tensorflow/core/kernels/batching_util:threadsafe_status_test PASSED in 0.2s //tensorflow/core/kernels/data:batch_dataset_op_test PASSED in 1.3s //tensorflow/core/kernels/data:cache_dataset_ops_test PASSED in 1.1s //tensorflow/core/kernels/data:concatenate_dataset_op_test PASSED in 2.5s //tensorflow/core/kernels/data:filter_dataset_op_test PASSED in 1.8s //tensorflow/core/kernels/data:finalize_dataset_op_test PASSED in 1.1s //tensorflow/core/kernels/data:fixed_length_record_dataset_op_test PASSED in 1.1s //tensorflow/core/kernels/data:flat_map_dataset_op_test PASSED in 2.1s //tensorflow/core/kernels/data:get_options_op_test PASSED in 1.2s //tensorflow/core/kernels/data:interleave_dataset_op_test PASSED in 1.6s //tensorflow/core/kernels/data:iterator_ops_test PASSED in 1.9s //tensorflow/core/kernels/data:map_dataset_op_test PASSED in 1.1s //tensorflow/core/kernels/data:map_defun_op_test PASSED in 1.2s //tensorflow/core/kernels/data:optimize_dataset_op_test PASSED in 1.7s //tensorflow/core/kernels/data:options_dataset_op_test PASSED in 2.0s //tensorflow/core/kernels/data:padded_batch_dataset_op_test PASSED in 1.9s //tensorflow/core/kernels/data:parallel_batch_dataset_op_test PASSED in 1.6s //tensorflow/core/kernels/data:parallel_filter_dataset_op_test PASSED in 3.2s //tensorflow/core/kernels/data:parallel_interleave_dataset_op_test PASSED in 3.5s //tensorflow/core/kernels/data:parallel_map_dataset_op_test PASSED in 3.3s //tensorflow/core/kernels/data:prefetch_autotuner_test PASSED in 0.3s //tensorflow/core/kernels/data:prefetch_dataset_op_test PASSED in 1.7s //tensorflow/core/kernels/data:range_dataset_op_test PASSED in 1.0s //tensorflow/core/kernels/data:reduce_dataset_op_test PASSED in 1.2s //tensorflow/core/kernels/data:repeat_dataset_op_test PASSED in 1.4s //tensorflow/core/kernels/data:rewrite_dataset_op_test PASSED in 1.4s //tensorflow/core/kernels/data:shard_dataset_op_test PASSED in 1.8s //tensorflow/core/kernels/data:shuffle_dataset_op_test PASSED in 2.8s //tensorflow/core/kernels/data:skip_dataset_op_test PASSED in 3.0s //tensorflow/core/kernels/data:sparse_tensor_slice_dataset_op_test PASSED in 2.5s //tensorflow/core/kernels/data:take_dataset_op_test PASSED in 0.9s //tensorflow/core/kernels/data:tensor_dataset_op_test PASSED in 2.0s //tensorflow/core/kernels/data:tensor_slice_dataset_op_test PASSED in 3.0s //tensorflow/core/kernels/data:text_line_dataset_op_test PASSED in 1.5s //tensorflow/core/kernels/data:tf_record_dataset_op_test PASSED in 1.6s //tensorflow/core/kernels/data:window_dataset_op_test PASSED in 2.1s //tensorflow/core/kernels/data:zip_dataset_op_test PASSED in 0.6s //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 1.0s //tensorflow/core/kernels/data/experimental:auto_shard_dataset_op_test PASSED in 1.3s //tensorflow/core/kernels/data/experimental:directed_interleave_dataset_op_test PASSED in 0.6s //tensorflow/core/kernels/data/experimental:list_dataset_op_test PASSED in 1.0s //tensorflow/core/kernels/data/experimental:map_and_batch_dataset_op_test PASSED in 2.5s //tensorflow/core/kernels/data/experimental:parallel_interleave_dataset_op_test PASSED in 4.7s //tensorflow/core/kernels/data/experimental:random_dataset_op_test PASSED in 1.0s //tensorflow/core/kernels/data/experimental:sampling_dataset_op_test PASSED in 1.6s //tensorflow/core/kernels/data/experimental:save_dataset_op_test PASSED in 1.5s //tensorflow/core/kernels/data/experimental:unique_dataset_op_test PASSED in 0.9s //tensorflow/core/kernels/image:adjust_contrast_op_benchmark_test_cpu PASSED in 1.1s //tensorflow/core/kernels/image:adjust_contrast_op_test PASSED in 0.7s //tensorflow/core/kernels/image:colorspace_op_test PASSED in 0.6s //tensorflow/core/kernels/image:crop_and_resize_op_benchmark_test_cpu PASSED in 0.7s //tensorflow/core/kernels/image:crop_and_resize_op_test PASSED in 3.1s //tensorflow/core/kernels/image:encode_jpeg_op_test PASSED in 0.5s //tensorflow/core/kernels/image:mirror_pad_op_benchmark_test_cpu PASSED in 0.6s //tensorflow/core/kernels/image:mirror_pad_op_test PASSED in 1.7s //tensorflow/core/kernels/image:non_max_suppression_op_benchmark_test PASSED in 0.8s //tensorflow/core/kernels/image:non_max_suppression_op_test PASSED in 2.0s //tensorflow/core/kernels/image:resize_area_op_test PASSED in 1.6s //tensorflow/core/kernels/image:resize_benchmark_test_cpu PASSED in 1.8s //tensorflow/core/kernels/image:resize_bicubic_op_test PASSED in 4.4s //tensorflow/core/kernels/image:resize_ops_test_cpu PASSED in 2.6s //tensorflow/core/kernels/image:sampling_kernels_test PASSED in 1.3s //tensorflow/core/kernels/image:scale_and_translate_op_test PASSED in 3.1s //tensorflow/core/kernels/linalg:banded_triangular_solve_op_test_cpu PASSED in 1.2s //tensorflow/core/kernels/linalg:matrix_triangular_solve_op_test_cpu PASSED in 0.7s //tensorflow/core/kernels/mkl:mkl_conv_ops_test PASSED in 0.2s //tensorflow/core/kernels/mkl:mkl_dequantize_op_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_fused_batch_norm_op_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_fused_ops_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_matmul_op_benchmark PASSED in 0.2s //tensorflow/core/kernels/mkl:mkl_qmatmul_op_test PASSED in 0.6s //tensorflow/core/kernels/mkl:mkl_quantize_op_test PASSED in 0.6s //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 0.5s //tensorflow/core/kernels/mkl:mkl_quantized_pooling_ops_test PASSED in 0.2s //tensorflow/core/kernels/mkl:mkl_relu_op_test PASSED in 0.1s //tensorflow/core/kernels/mkl:mkl_requantize_ops_test PASSED in 0.2s //tensorflow/core/kernels/mkl:mkl_swish_op_test PASSED in 0.6s //tensorflow/core/kernels/mkl:onednn_nn_ops_benchmark PASSED in 0.2s //tensorflow/core/kernels/sparse:kernels_test PASSED in 0.9s //tensorflow/core/kernels/uniform_quant_ops:math_utils_test PASSED in 0.7s //tensorflow/core/kernels/uniform_quant_ops:tensor_utils_test PASSED in 0.8s //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 0.7s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantized_add_op_test PASSED in 0.8s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantized_clip_by_value_op_test PASSED in 1.6s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantized_convolution_ops_test PASSED in 1.5s //tensorflow/core/kernels/uniform_quant_ops:uniform_quantized_dot_ops_test PASSED in 1.4s //tensorflow/core/kernels/uniform_quant_ops:uniform_requantize_op_test PASSED in 1.1s //tensorflow/core/lib/db:sqlite_test PASSED in 1.1s //tensorflow/core/lib/gif:lib_gif_io_test PASSED in 1.6s //tensorflow/core/lib/jpeg:lib_jpeg_jpeg_mem_unittest PASSED in 0.5s //tensorflow/core/ops:cudnn_rnn_ops_test_cc PASSED in 1.6s //tensorflow/core/ops:ops_array_grad_test PASSED in 2.9s //tensorflow/core/ops:ops_math_grad_test PASSED in 7.7s //tensorflow/core/ops:ops_tests PASSED in 0.7s //tensorflow/core/ops/compat:backwards_compatibility_test PASSED in 1.4s //tensorflow/core/platform:__tensorflow_tsl_platform_profile_utils_cpu_utils_test PASSED in 0.3s //tensorflow/core/platform:enable_tf2_utils_test PASSED in 0.1s //tensorflow/core/platform:env_test PASSED in 5.0s //tensorflow/core/platform:fake_python_env_test PASSED in 0.6s //tensorflow/core/platform:file_system_test PASSED in 1.2s //tensorflow/core/platform:platform_strings_test PASSED in 0.5s //tensorflow/core/platform:ram_file_system_test PASSED in 26.7s //tensorflow/core/platform:resource_loader_test PASSED in 0.2s //tensorflow/core/platform:vmodule_benchmark_test PASSED in 0.7s //tensorflow/core/platform:vmodule_test PASSED in 0.3s //tensorflow/core/profiler/backends/cpu:host_tracer_test PASSED in 0.2s //tensorflow/core/profiler/convert:dcn_utils_test PASSED in 0.3s //tensorflow/core/profiler/convert:hlo_proto_to_graph_view_test PASSED in 0.4s //tensorflow/core/profiler/convert:hlo_proto_to_memory_visualization_utils_test PASSED in 0.2s //tensorflow/core/profiler/convert:op_stats_to_pod_stats_test PASSED in 0.6s //tensorflow/core/profiler/convert:op_stats_to_pod_viewer_test PASSED in 0.2s //tensorflow/core/profiler/convert:op_stats_to_tf_stats_test PASSED in 1.0s //tensorflow/core/profiler/convert:repository_test PASSED in 0.7s //tensorflow/core/profiler/convert:xplane_to_kernel_stats_db_test PASSED in 0.6s //tensorflow/core/profiler/convert:xplane_to_memory_profile_test PASSED in 0.1s //tensorflow/core/profiler/convert:xplane_to_op_metrics_db_test PASSED in 0.2s //tensorflow/core/profiler/convert:xplane_to_op_stats_test PASSED in 0.6s //tensorflow/core/profiler/convert:xplane_to_step_events_test PASSED in 0.4s //tensorflow/core/profiler/convert:xplane_to_tf_functions_test PASSED in 0.4s //tensorflow/core/profiler/convert:xplane_to_tool_names_test PASSED in 0.1s //tensorflow/core/profiler/convert/trace_viewer:trace_viewer_visibility_test PASSED in 0.5s //tensorflow/core/profiler/internal:tfprof_show_test PASSED in 3.2s //tensorflow/core/profiler/internal:tfprof_stats_test PASSED in 1.9s //tensorflow/core/profiler/internal:tfprof_tensor_test PASSED in 0.8s //tensorflow/core/profiler/internal:tfprof_timeline_test PASSED in 1.0s //tensorflow/core/profiler/internal/advisor:tfprof_advisor_test PASSED in 0.9s //tensorflow/core/profiler/lib:profiler_disabled_test PASSED in 0.6s //tensorflow/core/profiler/utils:derived_timeline_test PASSED in 0.5s //tensorflow/core/profiler/utils:kernel_stats_utils_test PASSED in 0.1s //tensorflow/core/profiler/utils:op_metrics_db_utils_test PASSED in 0.1s //tensorflow/core/profiler/utils:step_intersection_test PASSED in 0.6s //tensorflow/core/summary:schema_test PASSED in 0.6s //tensorflow/core/summary:summary_db_writer_test PASSED in 0.1s //tensorflow/core/summary:summary_file_writer_test PASSED in 0.2s //tensorflow/core/tfrt/common:pjrt_cpu_client_registration_test PASSED in 8.6s //tensorflow/core/tfrt/common:pjrt_state_test PASSED in 9.7s //tensorflow/core/tfrt/common:pjrt_util_test PASSED in 9.6s //tensorflow/core/tfrt/fallback:cost_recorder_test PASSED in 1.2s //tensorflow/core/tfrt/fallback:fallback_state_test PASSED in 0.7s //tensorflow/core/transforms:eval_utils_test PASSED in 2.2s //tensorflow/core/transforms:graph_transform_wrapper_test PASSED in 0.2s //tensorflow/core/util:bcast_test PASSED in 1.2s //tensorflow/core/util:command_line_flags_test PASSED in 1.3s //tensorflow/core/util:debug_data_dumper_test PASSED in 1.8s //tensorflow/core/util:debug_events_writer_test PASSED in 0.7s //tensorflow/core/util:dump_graph_test PASSED in 0.7s //tensorflow/core/util:equal_graph_def_test PASSED in 1.7s //tensorflow/core/util:events_writer_test PASSED in 2.7s //tensorflow/core/util:example_proto_fast_parsing_test PASSED in 1.6s //tensorflow/core/util:example_proto_helper_test PASSED in 1.5s //tensorflow/core/util:exec_on_stall_test PASSED in 2.3s //tensorflow/core/util:fake_clock_env_test PASSED in 1.5s //tensorflow/core/util:incremental_barrier_test PASSED in 0.2s //tensorflow/core/util:matmul_bcast_test PASSED in 1.9s //tensorflow/core/util:memmapped_file_system_test PASSED in 0.8s //tensorflow/core/util:overflow_test PASSED in 0.1s //tensorflow/core/util:presized_cuckoo_map_test PASSED in 3.6s //tensorflow/core/util:ragged_to_dense_util_test PASSED in 0.9s //tensorflow/core/util:reffed_status_callback_test PASSED in 1.4s //tensorflow/core/util:reporter_test PASSED in 3.2s //tensorflow/core/util:saved_tensor_slice_util_test PASSED in 1.2s //tensorflow/core/util:semver_test PASSED in 1.0s //tensorflow/core/util:stat_summarizer_test PASSED in 1.0s //tensorflow/core/util:strided_slice_op_test PASSED in 0.7s //tensorflow/core/util:tensor_format_test PASSED in 0.8s //tensorflow/core/util:tensor_slice_reader_test PASSED in 2.0s //tensorflow/core/util:tensor_slice_set_test PASSED in 1.2s //tensorflow/core/util:tensor_slice_util_test PASSED in 1.4s //tensorflow/core/util:tensor_slice_writer_test PASSED in 2.2s //tensorflow/core/util:work_sharder_test PASSED in 1.1s //tensorflow/core/util/ctc:ctc_beam_search_test PASSED in 0.2s //tensorflow/core/util/proto:descriptor_pool_registry_test PASSED in 0.6s //tensorflow/core/util/proto:proto_utils_test PASSED in 1.5s //tensorflow/core/util/quantization:uniform_quant_ops_params_test PASSED in 0.8s //tensorflow/core/util/sparse:sparse_tensor_test PASSED in 0.2s //tensorflow/core/util/tensor_bundle:tensor_bundle_test PASSED in 46.6s //tensorflow/dtensor/mlir:dtensor_location_test PASSED in 0.2s //tensorflow/dtensor/mlir:group_assignment_test PASSED in 0.2s //tensorflow/dtensor/mlir/tests:annotate_global_shape.mlir.test PASSED in 1.4s //tensorflow/dtensor/mlir/tests:cluster_function_conversion.mlir.test PASSED in 1.6s //tensorflow/dtensor/mlir/tests:constant_folding.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:designate_resource_handle_mesh.mlir.test PASSED in 1.1s //tensorflow/dtensor/mlir/tests:device_mesh_cluster_coarsening.mlir.test PASSED in 1.3s //tensorflow/dtensor/mlir/tests:dtensor_all_gather.mlir.test PASSED in 2.9s //tensorflow/dtensor/mlir/tests:dtensor_all_scatter.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:dtensor_allreduce_combine_optimization.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:dtensor_allreduce_lowering.mlir.test PASSED in 1.2s //tensorflow/dtensor/mlir/tests:dtensor_allreduce_scatter_optimization.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:dtensor_allreduce_sum_optimization.mlir.test PASSED in 0.9s //tensorflow/dtensor/mlir/tests:dtensor_alltoall_lowering.mlir.test PASSED in 1.4s //tensorflow/dtensor/mlir/tests:dtensor_layout_must_execute.mlir.test PASSED in 0.4s //tensorflow/dtensor/mlir/tests:dtensor_layout_to_xla_sharding_op.mlir.test PASSED in 1.0s //tensorflow/dtensor/mlir/tests:dtensor_mixed_precision_reduce.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:dtensor_reduce_scatter_lowering.mlir.test PASSED in 1.4s //tensorflow/dtensor/mlir/tests:dtensor_remove_dtensorlayout.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:dtensor_replace_auxiliary_layout_op.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:dtensor_replace_relayout_with_identity.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:dtensor_set_hlo_sharding.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:dtensor_set_hlo_sharding_default.mlir.test PASSED in 1.8s //tensorflow/dtensor/mlir/tests:dtensor_xla_spmd_integration.mlir.test PASSED in 1.2s //tensorflow/dtensor/mlir/tests:elide_identity_before_copy_to_mesh.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:function_renaming.mlir.test PASSED in 0.9s //tensorflow/dtensor/mlir/tests:handle_cross_cluster_dependencies.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:handle_sparsetensors.mlir.test PASSED in 1.2s //tensorflow/dtensor/mlir/tests:layout_propagation_v2.mlir.test PASSED in 1.8s //tensorflow/dtensor/mlir/tests:lower_send_recv.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:merge_clusters.mlir.test PASSED in 1.0s //tensorflow/dtensor/mlir/tests:mesh_propagation.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:multi_device_expansion.mlir.test PASSED in 1.2s //tensorflow/dtensor/mlir/tests:op_to_device_cluster.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:propagate_default_layout.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:propagate_device_id_to_function.mlir.test PASSED in 1.8s //tensorflow/dtensor/mlir/tests:restore_and_assign.mlir.test PASSED in 1.0s //tensorflow/dtensor/mlir/tests:restore_shape_inference.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:set_default_sharding.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:sparse_expansion.mlir.test PASSED in 1.5s //tensorflow/dtensor/mlir/tests:spmd_batchparallel.mlir.test PASSED in 0.7s //tensorflow/dtensor/mlir/tests:spmd_concat.mlir.test PASSED in 0.5s //tensorflow/dtensor/mlir/tests:spmd_conv.mlir.test PASSED in 1.3s //tensorflow/dtensor/mlir/tests:spmd_einsum.mlir.test PASSED in 1.2s //tensorflow/dtensor/mlir/tests:spmd_expansion.mlir.test PASSED in 1.3s //tensorflow/dtensor/mlir/tests:spmd_io_ops.mlir.test PASSED in 0.8s //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 0.6s //tensorflow/dtensor/mlir/tests:spmd_save_restore.mlir.test PASSED in 1.4s //tensorflow/dtensor/mlir/tests:spmd_segment_sum.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:spmd_slice.mlir.test PASSED in 0.9s //tensorflow/dtensor/mlir/tests:spmd_softmax_loss.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:spmd_squeeze.mlir.test PASSED in 0.8s //tensorflow/dtensor/mlir/tests:spmd_var_handle.mlir.test PASSED in 1.0s //tensorflow/dtensor/mlir/tests:tf_dtensor_ops.mlir.test PASSED in 1.4s //tensorflow/dtensor/mlir/tests:tpu_add_resource_device_attribute.mlir.test PASSED in 0.6s //tensorflow/dtensor/mlir/tests:tpu_integration.mlir.test PASSED in 1.3s //tensorflow/dtensor/mlir/tests:undo_merge_const_across_mesh.mlir.test PASSED in 1.2s //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 18.8s //tensorflow/dtensor/python/tests:collective_test_cpu PASSED in 16.5s //tensorflow/dtensor/python/tests:config_test_cpu PASSED in 6.8s //tensorflow/dtensor/python/tests:device_test_cpu PASSED in 33.2s //tensorflow/dtensor/python/tests:layout_test_cpu PASSED in 15.2s //tensorflow/dtensor/python/tests:multi_client_test_cpu PASSED in 13.1s //tensorflow/dtensor/python/tests:numpy_util_test_cpu PASSED in 13.0s //tensorflow/dtensor/tests:executable_manager_test PASSED in 40.0s //tensorflow/dtensor/tests:layout_to_xla_sharding_test PASSED in 0.3s //tensorflow/dtensor/tests:slice_util_test PASSED in 0.1s //tensorflow/dtensor/tests:spmd_expander_test PASSED in 6.8s //tensorflow/dtensor/tests:tensor_layout_test PASSED in 0.1s //tensorflow/examples/adding_an_op:fact_test PASSED in 15.8s //tensorflow/examples/adding_an_op:zero_out_1_test PASSED in 15.4s //tensorflow/examples/adding_an_op:zero_out_2_test PASSED in 27.0s //tensorflow/examples/adding_an_op:zero_out_3_test PASSED in 16.9s //tensorflow/examples/custom_ops_doc/multiplex_1:multiplex_1_test PASSED in 14.4s //tensorflow/examples/custom_ops_doc/multiplex_2:multiplex_2_test_cpu PASSED in 17.1s //tensorflow/examples/custom_ops_doc/multiplex_3:multiplex_3_test PASSED in 16.7s //tensorflow/examples/custom_ops_doc/multiplex_4:multiplex_4_test PASSED in 16.9s //tensorflow/examples/custom_ops_doc/simple_hash_table:simple_hash_table_test PASSED in 17.2s //tensorflow/examples/custom_ops_doc/sleep:sleep_test PASSED in 16.3s //tensorflow/examples/speech_commands:accuracy_utils_test PASSED in 2.0s //tensorflow/examples/speech_commands:models_test PASSED in 28.3s //tensorflow/examples/speech_commands:recognize_commands_test PASSED in 2.2s //tensorflow/examples/wav_to_spectrogram:wav_to_spectrogram_test PASSED in 2.2s //tensorflow/js:ts_op_gen_test PASSED in 0.2s //tensorflow/python:array_grad_test_cpu PASSED in 11.1s //tensorflow/python:autograph_ops_test PASSED in 7.0s //tensorflow/python:batch_norm_benchmark_cpu PASSED in 10.5s //tensorflow/python:bincount_ops_test_cpu PASSED in 10.2s //tensorflow/python:bitwise_ops_test_cpu PASSED in 20.2s //tensorflow/python:clip_ops_test PASSED in 12.6s //tensorflow/python:clustering_ops_test PASSED in 32.4s //tensorflow/python:collective_ops_benchmark_cpu PASSED in 7.4s //tensorflow/python:collective_ops_gpu_test_2gpu PASSED in 7.8s //tensorflow/python:collective_ops_gpu_test_cpu PASSED in 7.9s //tensorflow/python:collective_ops_test PASSED in 21.7s //tensorflow/python:collective_ops_xla_test PASSED in 11.0s //tensorflow/python:compiled_collective_ops_gpu_test_2gpu PASSED in 9.8s //tensorflow/python:compiled_collective_ops_gpu_test_cpu PASSED in 8.5s //tensorflow/python:concat_benchmark_cpu PASSED in 7.5s //tensorflow/python:control_flow_ops_benchmark_cpu PASSED in 8.8s //tensorflow/python:control_flow_v2_enable_test PASSED in 7.8s //tensorflow/python:control_flow_v2_toggles_test PASSED in 20.0s //tensorflow/python:dequantize_op_test PASSED in 10.0s //tensorflow/python:embedding_ops_test_cpu PASSED in 10.1s //tensorflow/python:factory_ops_test_cpu PASSED in 8.3s //tensorflow/python:functional_ops_test PASSED in 7.8s //tensorflow/python:gradient_checker_v2_test_cpu PASSED in 29.9s //tensorflow/python:gradients_test_cpu PASSED in 17.8s //tensorflow/python:init_ops_test_cpu PASSED in 9.9s //tensorflow/python:init_ops_v2_test_cpu PASSED in 10.6s //tensorflow/python:math_grad_test_cpu PASSED in 27.1s //tensorflow/python:math_ops_linspace_test_cpu PASSED in 7.1s //tensorflow/python:math_ops_test_cpu PASSED in 27.1s //tensorflow/python:matmul_benchmark_cpu PASSED in 11.1s //tensorflow/python:nn_grad_test_cpu PASSED in 11.2s //tensorflow/python:nn_loss_scaling_utilities_test PASSED in 11.3s //tensorflow/python:nn_test_cpu PASSED in 54.2s //tensorflow/python:nn_xent_test_cpu PASSED in 9.9s //tensorflow/python:op_selector_test PASSED in 6.9s //tensorflow/python:ops/array_ops_shape_test PASSED in 9.8s //tensorflow/python:ops/array_ops_test PASSED in 18.6s //tensorflow/python:quantized_conv_ops_test PASSED in 7.5s //tensorflow/python:quantized_ops_test PASSED in 8.6s //tensorflow/python:raw_ops_test_cpu PASSED in 9.6s //tensorflow/python:rnn_grad_test_cpu PASSED in 8.7s //tensorflow/python:script_ops_test PASSED in 8.7s //tensorflow/python:sort_ops_test PASSED in 8.4s //tensorflow/python:sparse_ops_test PASSED in 14.8s //tensorflow/python:split_benchmark_cpu PASSED in 7.1s //tensorflow/python:tensor_array_ops_test PASSED in 8.2s //tensorflow/python:transpose_benchmark_cpu PASSED in 8.3s //tensorflow/python:variable_spec_test PASSED in 8.1s //tensorflow/python/autograph/converters:asserts_test PASSED in 20.0s //tensorflow/python/autograph/converters:break_statements_test PASSED in 7.8s //tensorflow/python/autograph/converters:call_trees_test PASSED in 7.8s //tensorflow/python/autograph/converters:conditional_expressions_test PASSED in 7.1s //tensorflow/python/autograph/converters:continue_statements_test PASSED in 9.8s //tensorflow/python/autograph/converters:control_flow_test PASSED in 13.0s //tensorflow/python/autograph/converters:directives_test PASSED in 8.3s //tensorflow/python/autograph/converters:functions_test PASSED in 7.6s //tensorflow/python/autograph/converters:list_comprehensions_test PASSED in 6.1s //tensorflow/python/autograph/converters:lists_test PASSED in 10.8s //tensorflow/python/autograph/converters:logical_expressions_test PASSED in 8.3s //tensorflow/python/autograph/converters:return_statements_test PASSED in 7.8s //tensorflow/python/autograph/converters:slices_test PASSED in 7.4s //tensorflow/python/autograph/converters:variables_test PASSED in 10.7s //tensorflow/python/autograph/core:converter_test PASSED in 6.9s //tensorflow/python/autograph/core:function_wrappers_test PASSED in 17.9s //tensorflow/python/autograph/impl:api_test PASSED in 13.8s //tensorflow/python/autograph/impl:conversion_test PASSED in 9.3s //tensorflow/python/autograph/lang:special_functions_test PASSED in 7.0s //tensorflow/python/autograph/operators:conditional_expressions_test PASSED in 7.1s //tensorflow/python/autograph/operators:control_flow_test PASSED in 19.7s //tensorflow/python/autograph/operators:data_structures_test PASSED in 7.8s //tensorflow/python/autograph/operators:exceptions_test PASSED in 9.3s //tensorflow/python/autograph/operators:logical_test PASSED in 9.2s //tensorflow/python/autograph/operators:py_builtins_test PASSED in 13.7s //tensorflow/python/autograph/operators:slices_test PASSED in 7.1s //tensorflow/python/autograph/operators:variables_test PASSED in 8.3s //tensorflow/python/autograph/pyct:anno_test PASSED in 8.2s //tensorflow/python/autograph/pyct:ast_util_test PASSED in 9.9s //tensorflow/python/autograph/pyct:cache_test PASSED in 6.9s //tensorflow/python/autograph/pyct:cfg_test PASSED in 7.7s //tensorflow/python/autograph/pyct:error_utils_test PASSED in 6.7s //tensorflow/python/autograph/pyct:inspect_utils_test PASSED in 8.6s //tensorflow/python/autograph/pyct:loader_test PASSED in 7.8s //tensorflow/python/autograph/pyct:naming_test PASSED in 6.4s //tensorflow/python/autograph/pyct:origin_info_test PASSED in 7.1s //tensorflow/python/autograph/pyct:parser_test PASSED in 7.4s //tensorflow/python/autograph/pyct:pretty_printer_test PASSED in 7.0s //tensorflow/python/autograph/pyct:qual_names_test PASSED in 8.4s //tensorflow/python/autograph/pyct:templates_test PASSED in 8.5s //tensorflow/python/autograph/pyct:transformer_test PASSED in 7.3s //tensorflow/python/autograph/pyct:transpiler_test PASSED in 9.0s //tensorflow/python/autograph/pyct/static_analysis:activity_test PASSED in 7.2s //tensorflow/python/autograph/pyct/static_analysis:liveness_test PASSED in 7.1s //tensorflow/python/autograph/pyct/static_analysis:reaching_definitions_test PASSED in 7.7s //tensorflow/python/autograph/pyct/static_analysis:reaching_fndefs_test PASSED in 8.9s //tensorflow/python/autograph/pyct/static_analysis:type_inference_test PASSED in 7.5s //tensorflow/python/autograph/tests:assertion_test PASSED in 15.3s //tensorflow/python/autograph/tests:basic_ifexp_test PASSED in 30.1s //tensorflow/python/autograph/tests:call_to_builtin_function_test PASSED in 18.2s //tensorflow/python/autograph/tests:call_to_lambda_function_test PASSED in 17.8s //tensorflow/python/autograph/tests:call_to_named_tuple_test PASSED in 15.9s //tensorflow/python/autograph/tests:call_to_numpy_function_test PASSED in 15.5s //tensorflow/python/autograph/tests:call_to_print_function_test PASSED in 14.7s //tensorflow/python/autograph/tests:call_to_tf_api_test PASSED in 15.1s //tensorflow/python/autograph/tests:call_to_user_function_test PASSED in 15.3s //tensorflow/python/autograph/tests:composite_names_in_control_flow_test PASSED in 32.0s //tensorflow/python/autograph/tests:cond_basic_test PASSED in 26.6s //tensorflow/python/autograph/tests:datasets_test PASSED in 33.5s //tensorflow/python/autograph/tests:early_return_test PASSED in 18.5s //tensorflow/python/autograph/tests:ext_slice_test PASSED in 15.4s //tensorflow/python/autograph/tests:generator_test PASSED in 16.8s //tensorflow/python/autograph/tests:logical_expression_test PASSED in 16.6s //tensorflow/python/autograph/tests:loop_basic_test PASSED in 96.0s //tensorflow/python/autograph/tests:loop_control_flow_illegal_cases_test PASSED in 18.3s //tensorflow/python/autograph/tests:loop_created_variables_test PASSED in 17.8s //tensorflow/python/autograph/tests:loop_scoping_test PASSED in 21.3s //tensorflow/python/autograph/tests:loop_with_function_call_test PASSED in 31.8s //tensorflow/python/autograph/tests:loop_with_variable_type_illegal_cases_test PASSED in 20.7s //tensorflow/python/autograph/tests:loop_with_variable_type_test PASSED in 31.7s //tensorflow/python/autograph/tests:nested_control_flow_test PASSED in 41.3s //tensorflow/python/autograph/tests:type_annotations_test PASSED in 15.7s //tensorflow/python/autograph/utils:context_managers_test PASSED in 6.9s //tensorflow/python/autograph/utils:misc_test PASSED in 8.5s //tensorflow/python/autograph/utils:tensor_list_test PASSED in 7.8s //tensorflow/python/autograph/utils:tensors_test PASSED in 11.8s //tensorflow/python/checkpoint:benchmarks_test PASSED in 8.1s //tensorflow/python/checkpoint:checkpoint_management_test_cpu PASSED in 14.8s //tensorflow/python/checkpoint:checkpoint_metrics_test PASSED in 15.3s //tensorflow/python/checkpoint:checkpoint_test PASSED in 23.8s //tensorflow/python/checkpoint:checkpoint_view_test PASSED in 9.3s //tensorflow/python/checkpoint:checkpoint_with_v1_optimizers_test PASSED in 10.4s //tensorflow/python/checkpoint:functional_saver_test_cpu PASSED in 9.9s //tensorflow/python/checkpoint:restore_test PASSED in 8.2s //tensorflow/python/checkpoint:save_util_v1_test PASSED in 7.2s //tensorflow/python/checkpoint:saveable_compat_test PASSED in 9.7s //tensorflow/python/checkpoint:tensor_callable_test PASSED in 10.3s //tensorflow/python/checkpoint:trackable_view_test PASSED in 7.0s //tensorflow/python/client:device_lib_test_cpu PASSED in 9.0s //tensorflow/python/client:events_writer_test PASSED in 6.9s //tensorflow/python/client:session_benchmark_cpu PASSED in 9.9s //tensorflow/python/client:session_list_devices_test PASSED in 9.6s //tensorflow/python/client:session_partial_run_test PASSED in 11.7s //tensorflow/python/client:timeline_test_cpu PASSED in 8.2s //tensorflow/python/client:virtual_gpu_test_cpu PASSED in 10.5s //tensorflow/python/compat:compat_test PASSED in 18.7s //tensorflow/python/compat:disable_v2_behavior_test PASSED in 7.9s //tensorflow/python/compiler/mlir:mlir_test PASSED in 8.8s //tensorflow/python/compiler/tensorrt:trt_convert_test_cpu PASSED in 10.3s //tensorflow/python/compiler/tensorrt/test:batch_matmul_test_cpu PASSED in 11.9s //tensorflow/python/compiler/tensorrt/test:biasadd_matmul_test_cpu PASSED in 8.7s //tensorflow/python/compiler/tensorrt/test:binary_tensor_weight_broadcast_test_cpu PASSED in 9.6s //tensorflow/python/compiler/tensorrt/test:bool_test_cpu PASSED in 10.7s //tensorflow/python/compiler/tensorrt/test:cast_test_cpu PASSED in 8.4s //tensorflow/python/compiler/tensorrt/test:concatenation_test_cpu PASSED in 9.9s //tensorflow/python/compiler/tensorrt/test:const_broadcast_test_cpu PASSED in 10.9s //tensorflow/python/compiler/tensorrt/test:data_dependent_shape_test_cpu PASSED in 9.9s //tensorflow/python/compiler/tensorrt/test:dynamic_input_shapes_test_cpu PASSED in 10.2s //tensorflow/python/compiler/tensorrt/test:identity_output_test_cpu PASSED in 11.9s //tensorflow/python/compiler/tensorrt/test:int32_test_cpu PASSED in 10.4s //tensorflow/python/compiler/tensorrt/test:lru_cache_test_cpu PASSED in 7.8s //tensorflow/python/compiler/tensorrt/test:memory_alignment_test_cpu PASSED in 8.4s //tensorflow/python/compiler/tensorrt/test:multi_connection_neighbor_engine_test_cpu PASSED in 7.6s //tensorflow/python/compiler/tensorrt/test:neighboring_engine_test_cpu PASSED in 8.8s //tensorflow/python/compiler/tensorrt/test:quantization_test_cpu PASSED in 21.1s //tensorflow/python/compiler/tensorrt/test:rank_two_test_cpu PASSED in 9.7s //tensorflow/python/compiler/tensorrt/test:reshape_transpose_test_cpu PASSED in 8.5s //tensorflow/python/compiler/tensorrt/test:topk_test_cpu PASSED in 20.2s //tensorflow/python/compiler/tensorrt/test:trt_engine_op_shape_test_cpu PASSED in 7.5s //tensorflow/python/compiler/tensorrt/test:trt_mode_test_cpu PASSED in 8.4s //tensorflow/python/compiler/tensorrt/test:unary_test_cpu PASSED in 9.4s //tensorflow/python/compiler/tensorrt/test:vgg_block_nchw_test_cpu PASSED in 8.8s //tensorflow/python/compiler/tensorrt/test:vgg_block_test_cpu PASSED in 8.1s //tensorflow/python/compiler/xla:jit_compile_test_cpu PASSED in 8.3s //tensorflow/python/compiler/xla:jit_test_cpu PASSED in 11.4s //tensorflow/python/compiler/xla:xla_test_cpu PASSED in 18.0s //tensorflow/python/compiler/xla/experimental:xla_sharding_test PASSED in 7.6s //tensorflow/python/data/benchmarks:batch_benchmark PASSED in 6.8s //tensorflow/python/data/benchmarks:filter_benchmark PASSED in 8.8s //tensorflow/python/data/benchmarks:from_tensor_slices_benchmark PASSED in 11.6s //tensorflow/python/data/benchmarks:interleave_benchmark PASSED in 7.6s //tensorflow/python/data/benchmarks:list_files_benchmark PASSED in 8.8s //tensorflow/python/data/benchmarks:map_benchmark PASSED in 7.8s //tensorflow/python/data/benchmarks:meta_benchmark PASSED in 9.0s //tensorflow/python/data/benchmarks:prefetch_benchmark PASSED in 8.8s //tensorflow/python/data/benchmarks:range_benchmark PASSED in 7.5s //tensorflow/python/data/experimental/benchmarks:autotune_benchmark PASSED in 8.1s //tensorflow/python/data/experimental/benchmarks:csv_dataset_benchmark PASSED in 7.1s //tensorflow/python/data/experimental/benchmarks:map_and_batch_benchmark PASSED in 7.9s //tensorflow/python/data/experimental/benchmarks:map_defun_benchmark PASSED in 10.7s //tensorflow/python/data/experimental/benchmarks:matching_files_benchmark PASSED in 8.8s //tensorflow/python/data/experimental/benchmarks:optimize_benchmark PASSED in 9.0s //tensorflow/python/data/experimental/benchmarks:parameter_value_benchmark PASSED in 7.9s //tensorflow/python/data/experimental/benchmarks:rejection_resample_benchmark PASSED in 7.4s //tensorflow/python/data/experimental/benchmarks:snapshot_dataset_benchmark PASSED in 6.7s //tensorflow/python/data/experimental/benchmarks:unbatch_benchmark PASSED in 9.1s //tensorflow/python/data/experimental/kernel_tests:assert_cardinality_test PASSED in 40.8s //tensorflow/python/data/experimental/kernel_tests:assert_next_test PASSED in 8.6s //tensorflow/python/data/experimental/kernel_tests:assert_prev_test PASSED in 17.8s //tensorflow/python/data/experimental/kernel_tests:checkpoint_input_pipeline_hook_test PASSED in 14.8s //tensorflow/python/data/experimental/kernel_tests:compression_ops_test PASSED in 10.9s //tensorflow/python/data/experimental/kernel_tests:copy_to_device_test_cpu PASSED in 12.5s //tensorflow/python/data/experimental/kernel_tests:dense_to_sparse_batch_test PASSED in 19.2s //tensorflow/python/data/experimental/kernel_tests:from_list_test PASSED in 39.9s //tensorflow/python/data/experimental/kernel_tests:io_test PASSED in 82.8s //tensorflow/python/data/experimental/kernel_tests:lookup_ops_test PASSED in 10.0s //tensorflow/python/data/experimental/kernel_tests:make_csv_dataset_test PASSED in 23.8s //tensorflow/python/data/experimental/kernel_tests:make_saveable_from_iterator_test PASSED in 8.1s //tensorflow/python/data/experimental/kernel_tests:make_tf_record_dataset_test PASSED in 50.0s //tensorflow/python/data/experimental/kernel_tests:map_defun_op_test PASSED in 7.9s //tensorflow/python/data/experimental/kernel_tests:matching_files_dataset_test PASSED in 28.2s //tensorflow/python/data/experimental/kernel_tests:model_dataset_test PASSED in 9.7s //tensorflow/python/data/experimental/kernel_tests:non_serializable_test PASSED in 12.0s //tensorflow/python/data/experimental/kernel_tests:pad_to_cardinality_test PASSED in 8.4s //tensorflow/python/data/experimental/kernel_tests:prefetch_to_device_test_cpu PASSED in 11.1s //tensorflow/python/data/experimental/kernel_tests:prefetch_with_slack_test PASSED in 10.7s //tensorflow/python/data/experimental/kernel_tests:shuffle_and_repeat_test PASSED in 29.3s //tensorflow/python/data/experimental/kernel_tests:sleep_test PASSED in 9.3s //tensorflow/python/data/experimental/kernel_tests:tf_record_writer_test PASSED in 11.9s //tensorflow/python/data/experimental/kernel_tests:variant_test PASSED in 11.8s //tensorflow/python/data/experimental/kernel_tests:wrap_unwrap_test_cpu PASSED in 8.6s //tensorflow/python/data/experimental/kernel_tests/optimization:filter_fusion_test PASSED in 33.5s //tensorflow/python/data/experimental/kernel_tests/optimization:filter_parallelization_test PASSED in 54.7s //tensorflow/python/data/experimental/kernel_tests/optimization:grappler_test_cpu PASSED in 8.1s //tensorflow/python/data/experimental/kernel_tests/optimization:make_deterministic_test PASSED in 32.8s //tensorflow/python/data/experimental/kernel_tests/optimization:map_and_batch_fusion_test PASSED in 10.9s //tensorflow/python/data/experimental/kernel_tests/optimization:map_and_filter_fusion_test PASSED in 29.2s //tensorflow/python/data/experimental/kernel_tests/optimization:map_fusion_test PASSED in 34.9s //tensorflow/python/data/experimental/kernel_tests/optimization:map_parallelization_test PASSED in 15.1s //tensorflow/python/data/experimental/kernel_tests/optimization:noop_elimination_test PASSED in 19.6s //tensorflow/python/data/experimental/kernel_tests/service:multi_device_test PASSED in 16.9s //tensorflow/python/data/experimental/service:server_lib_test PASSED in 8.2s //tensorflow/python/data/kernel_tests:as_numpy_iterator_test PASSED in 11.6s //tensorflow/python/data/kernel_tests:bucket_by_sequence_length_test PASSED in 19.2s //tensorflow/python/data/kernel_tests:cache_test PASSED in 47.9s //tensorflow/python/data/kernel_tests:cardinality_test PASSED in 15.3s //tensorflow/python/data/kernel_tests:checkpoint_test PASSED in 16.5s //tensorflow/python/data/kernel_tests:concatenate_test PASSED in 24.1s //tensorflow/python/data/kernel_tests:counter_test PASSED in 26.1s //tensorflow/python/data/kernel_tests:dataset_spec_test PASSED in 10.1s //tensorflow/python/data/kernel_tests:dataset_test PASSED in 24.4s //tensorflow/python/data/kernel_tests:enumerate_test PASSED in 29.2s //tensorflow/python/data/kernel_tests:from_sparse_tensor_slices_test PASSED in 10.8s //tensorflow/python/data/kernel_tests:from_tensor_slices_test PASSED in 27.3s //tensorflow/python/data/kernel_tests:from_tensors_test PASSED in 27.2s //tensorflow/python/data/kernel_tests:get_single_element_test PASSED in 11.8s //tensorflow/python/data/kernel_tests:ignore_errors_test PASSED in 20.7s //tensorflow/python/data/kernel_tests:io_test PASSED in 88.6s //tensorflow/python/data/kernel_tests:iterator_test_cpu PASSED in 19.8s //tensorflow/python/data/kernel_tests:len_test PASSED in 6.9s //tensorflow/python/data/kernel_tests:list_files_test PASSED in 17.6s //tensorflow/python/data/kernel_tests:optional_test_cpu PASSED in 14.4s //tensorflow/python/data/kernel_tests:options_test PASSED in 10.6s //tensorflow/python/data/kernel_tests:placement_test_cpu PASSED in 10.9s //tensorflow/python/data/kernel_tests:prefetch_test PASSED in 40.1s //tensorflow/python/data/kernel_tests:random_test PASSED in 37.9s //tensorflow/python/data/kernel_tests:range_test PASSED in 55.3s //tensorflow/python/data/kernel_tests:rebatch_test PASSED in 6.9s //tensorflow/python/data/kernel_tests:reduce_test_cpu PASSED in 26.0s //tensorflow/python/data/kernel_tests:scan_test_cpu PASSED in 37.0s //tensorflow/python/data/kernel_tests:sparse_batch_test PASSED in 15.3s //tensorflow/python/data/kernel_tests:unbatch_test PASSED in 48.4s //tensorflow/python/data/util:convert_test PASSED in 8.8s //tensorflow/python/data/util:nest_test PASSED in 8.5s //tensorflow/python/data/util:options_test PASSED in 7.8s //tensorflow/python/data/util:random_seed_test PASSED in 8.6s //tensorflow/python/data/util:sparse_test PASSED in 12.6s //tensorflow/python/data/util:structure_test PASSED in 9.9s //tensorflow/python/data/util:traverse_test PASSED in 13.0s //tensorflow/python/debug/cli:analyzer_cli_test_cpu PASSED in 12.2s //tensorflow/python/debug/cli:cli_config_test PASSED in 9.3s //tensorflow/python/debug/cli:cli_shared_test PASSED in 7.3s //tensorflow/python/debug/cli:command_parser_test PASSED in 7.2s //tensorflow/python/debug/cli:curses_ui_test PASSED in 7.5s //tensorflow/python/debug/cli:debugger_cli_common_test PASSED in 7.2s //tensorflow/python/debug/cli:evaluator_test PASSED in 7.1s //tensorflow/python/debug/cli:profile_analyzer_cli_test PASSED in 6.0s //tensorflow/python/debug/cli:readline_ui_test PASSED in 9.8s //tensorflow/python/debug/cli:tensor_format_test PASSED in 7.3s //tensorflow/python/debug/lib:check_numerics_callback_test_cpu PASSED in 10.0s //tensorflow/python/debug/lib:common_test PASSED in 6.6s //tensorflow/python/debug/lib:debug_data_test PASSED in 10.3s //tensorflow/python/debug/lib:debug_events_monitors_test PASSED in 11.4s //tensorflow/python/debug/lib:debug_events_writer_test PASSED in 12.3s //tensorflow/python/debug/lib:debug_gradients_test_cpu PASSED in 7.1s //tensorflow/python/debug/lib:debug_graph_reconstruction_test_cpu PASSED in 12.6s //tensorflow/python/debug/lib:debug_graphs_test PASSED in 8.6s //tensorflow/python/debug/lib:debug_grappler_test_cpu PASSED in 8.5s //tensorflow/python/debug/lib:debug_utils_test PASSED in 8.7s //tensorflow/python/debug/lib:debug_v2_ops_test_cpu PASSED in 18.2s //tensorflow/python/debug/lib:profiling_test PASSED in 6.7s //tensorflow/python/debug/lib:session_debug_file_test_cpu PASSED in 13.0s //tensorflow/python/debug/lib:session_debug_multi_gpu_test_cpu PASSED in 8.0s //tensorflow/python/debug/lib:source_utils_test PASSED in 13.6s //tensorflow/python/debug/wrappers:disk_usage_test PASSED in 7.7s //tensorflow/python/debug/wrappers:dumping_wrapper_test PASSED in 8.8s //tensorflow/python/debug/wrappers:framework_test PASSED in 7.1s //tensorflow/python/debug/wrappers:local_cli_wrapper_test PASSED in 7.7s //tensorflow/python/distribute:checkpoint_utils_test_2gpu PASSED in 11.8s //tensorflow/python/distribute:checkpoint_utils_test_cpu PASSED in 10.2s //tensorflow/python/distribute:checkpointing_test_2gpu PASSED in 8.1s //tensorflow/python/distribute:checkpointing_test_cpu PASSED in 8.5s //tensorflow/python/distribute:collective_util_test PASSED in 6.7s //tensorflow/python/distribute:combinations_test_2gpu PASSED in 20.3s //tensorflow/python/distribute:combinations_test_cpu PASSED in 24.5s //tensorflow/python/distribute:cross_device_utils_test_cpu PASSED in 9.1s //tensorflow/python/distribute:custom_training_loop_gradient_test_2gpu PASSED in 11.5s //tensorflow/python/distribute:custom_training_loop_gradient_test_cpu PASSED in 10.7s //tensorflow/python/distribute:device_util_test_cpu PASSED in 9.6s //tensorflow/python/distribute:distribute_coordinator_test PASSED in 16.2s //tensorflow/python/distribute:distribute_lib_test PASSED in 15.7s //tensorflow/python/distribute:distribute_utils_test_2gpu PASSED in 8.9s //tensorflow/python/distribute:distribute_utils_test_cpu PASSED in 9.4s //tensorflow/python/distribute:input_ops_test_cpu PASSED in 15.1s //tensorflow/python/distribute:metrics_v1_test_2gpu PASSED in 32.5s //tensorflow/python/distribute:metrics_v1_test_cpu PASSED in 38.7s //tensorflow/python/distribute:mirrored_values_test_2gpu PASSED in 9.1s //tensorflow/python/distribute:mirrored_values_test_cpu PASSED in 11.2s //tensorflow/python/distribute:mirrored_variable_test_2gpu PASSED in 17.4s //tensorflow/python/distribute:mirrored_variable_test_cpu PASSED in 19.8s //tensorflow/python/distribute:multi_process_runner_no_init_test PASSED in 12.8s //tensorflow/python/distribute:multi_worker_continuous_run_test_cpu PASSED in 22.3s //tensorflow/python/distribute:multi_worker_util_test PASSED in 6.3s //tensorflow/python/distribute:numpy_dataset_test PASSED in 10.6s //tensorflow/python/distribute:one_device_strategy_test_cpu PASSED in 25.5s //tensorflow/python/distribute:packed_distributed_variable_test PASSED in 6.9s //tensorflow/python/distribute:parameter_server_strategy_test_2gpu PASSED in 28.3s //tensorflow/python/distribute:parameter_server_strategy_test_cpu PASSED in 29.6s //tensorflow/python/distribute:parameter_server_strategy_v2_test_2gpu PASSED in 25.5s //tensorflow/python/distribute:parameter_server_strategy_v2_test_cpu PASSED in 27.0s //tensorflow/python/distribute:per_replica_test_2gpu PASSED in 8.2s //tensorflow/python/distribute:per_replica_test_cpu PASSED in 10.4s //tensorflow/python/distribute:ps_values_test_2gpu PASSED in 13.3s //tensorflow/python/distribute:ps_values_test_cpu PASSED in 10.8s //tensorflow/python/distribute:remote_mirrored_strategy_eager_test_cpu PASSED in 10.0s //tensorflow/python/distribute:sharded_variable_test PASSED in 24.8s //tensorflow/python/distribute:shared_variable_creator_test PASSED in 9.1s //tensorflow/python/distribute:strategy_combinations_test_cpu PASSED in 44.2s //tensorflow/python/distribute:template_mirrored_strategy_test_cpu PASSED in 7.7s //tensorflow/python/distribute:test_util_test_2gpu PASSED in 18.2s //tensorflow/python/distribute:test_util_test_cpu PASSED in 15.0s //tensorflow/python/distribute:tf_function_test_2gpu PASSED in 10.0s //tensorflow/python/distribute:tf_function_test_cpu PASSED in 9.7s //tensorflow/python/distribute:values_v2_test_cpu PASSED in 12.0s //tensorflow/python/distribute:warm_starting_util_test_2gpu PASSED in 12.3s //tensorflow/python/distribute:warm_starting_util_test_cpu PASSED in 10.5s //tensorflow/python/distribute/cluster_resolver:base_cluster_resolver_py_test PASSED in 7.9s //tensorflow/python/distribute/cluster_resolver:gce_cluster_resolver_py_test PASSED in 6.9s //tensorflow/python/distribute/cluster_resolver:kubernetes_cluster_resolver_py_test PASSED in 10.5s //tensorflow/python/distribute/cluster_resolver:sagemaker_cluster_resolver_py_test PASSED in 9.0s //tensorflow/python/distribute/cluster_resolver:slurm_cluster_resolver_py_test PASSED in 7.1s //tensorflow/python/distribute/cluster_resolver:tfconfig_cluster_resolver_py_test PASSED in 8.5s //tensorflow/python/distribute/cluster_resolver/tpu:tpu_cluster_resolver_py_test PASSED in 8.3s //tensorflow/python/distribute/coordinator:metric_utils_test PASSED in 11.4s //tensorflow/python/distribute/coordinator:watchdog_test PASSED in 61.7s //tensorflow/python/distribute/experimental:dtensor_util_test_cpu PASSED in 11.6s //tensorflow/python/distribute/experimental:mirrored_strategy_test_cpu PASSED in 27.4s //tensorflow/python/distribute/experimental:multi_worker_mirrored_strategy_test_cpu PASSED in 17.1s //tensorflow/python/distribute/integration_test:saved_model_test_cpu PASSED in 34.7s //tensorflow/python/distribute/parallel_device:parallel_device_test_cpu PASSED in 10.1s //tensorflow/python/distribute/v1:all_reduce_test PASSED in 42.2s //tensorflow/python/distribute/v1:cross_device_ops_test_2gpu PASSED in 63.7s //tensorflow/python/distribute/v1:cross_device_ops_test_cpu PASSED in 50.2s //tensorflow/python/dlpack:dlpack_test_cpu PASSED in 8.4s //tensorflow/python/eager:backprop_test_cpu PASSED in 122.0s //tensorflow/python/eager:benchmarks_test_cpu PASSED in 9.5s //tensorflow/python/eager:cancellation_test_cpu PASSED in 7.6s //tensorflow/python/eager:context_test_cpu PASSED in 8.3s //tensorflow/python/eager:core_test_cpu PASSED in 26.0s //tensorflow/python/eager:gradient_input_output_exclusions_test PASSED in 35.2s //tensorflow/python/eager:graph_only_ops_test_cpu PASSED in 9.6s //tensorflow/python/eager:lift_to_graph_test PASSED in 8.9s //tensorflow/python/eager:monitoring_test_cpu PASSED in 9.4s //tensorflow/python/eager:ops_test_cpu PASSED in 12.2s //tensorflow/python/eager:profiler_client_test PASSED in 7.0s //tensorflow/python/eager:profiler_test_cpu PASSED in 7.2s //tensorflow/python/eager:pywrap_tfe_test PASSED in 17.9s //tensorflow/python/eager:record_test PASSED in 9.0s //tensorflow/python/eager:remote_benchmarks_test_cpu PASSED in 8.2s //tensorflow/python/eager:run_eager_op_as_function_test_cpu PASSED in 7.7s //tensorflow/python/eager:run_eager_op_as_function_xla_test_cpu PASSED in 8.8s //tensorflow/python/eager:small_constants_optimizer_test_cpu PASSED in 175.8s //tensorflow/python/eager:tensor_test_cpu PASSED in 10.6s //tensorflow/python/eager:wrap_function_device_test_cpu PASSED in 10.6s //tensorflow/python/eager:wrap_function_test PASSED in 9.0s //tensorflow/python/eager/benchmarks:kpi_benchmark_test_cpu PASSED in 17.2s //tensorflow/python/eager/memory_tests:remote_memory_test_cpu PASSED in 8.5s //tensorflow/python/eager/polymorphic_function:argument_naming_test_cpu PASSED in 7.6s //tensorflow/python/eager/polymorphic_function:atomic_function_test_cpu PASSED in 9.8s //tensorflow/python/eager/polymorphic_function:collection_test_cpu PASSED in 12.6s //tensorflow/python/eager/polymorphic_function:compiler_ir_test_cpu PASSED in 8.2s //tensorflow/python/eager/polymorphic_function:compiler_ir_test_cpu_mlir_bridge_test PASSED in 9.6s //tensorflow/python/eager/polymorphic_function:function_spec_test PASSED in 6.8s //tensorflow/python/eager/polymorphic_function:polymorphic_function_xla_jit_test_cpu PASSED in 24.4s //tensorflow/python/eager/polymorphic_function:polymorphic_function_xla_jit_test_cpu_mlir_bridge_test PASSED in 24.5s //tensorflow/python/eager/polymorphic_function:polymorphic_function_xla_test_cpu PASSED in 9.7s //tensorflow/python/eager/polymorphic_function:quarantine_test PASSED in 24.6s //tensorflow/python/feature_column:sequence_feature_column_integration_test PASSED in 9.3s //tensorflow/python/feature_column:serialization_test PASSED in 12.0s //tensorflow/python/framework:auto_control_deps_test PASSED in 22.0s //tensorflow/python/framework:c_api_util_test PASSED in 9.7s //tensorflow/python/framework:common_shapes_test PASSED in 7.3s //tensorflow/python/framework:composite_tensor_test PASSED in 7.3s //tensorflow/python/framework:config_test_2gpu PASSED in 13.8s //tensorflow/python/framework:config_test_cpu PASSED in 13.3s //tensorflow/python/framework:constant_op_test PASSED in 9.4s //tensorflow/python/framework:device_spec_test PASSED in 7.9s //tensorflow/python/framework:device_test PASSED in 8.5s //tensorflow/python/framework:dtypes_test PASSED in 14.6s //tensorflow/python/framework:error_interpolation_test PASSED in 8.4s //tensorflow/python/framework:errors_test PASSED in 8.3s //tensorflow/python/framework:extension_type_field_test PASSED in 8.9s //tensorflow/python/framework:extension_type_test PASSED in 14.5s //tensorflow/python/framework:file_system_test PASSED in 7.1s //tensorflow/python/framework:function_def_to_graph_test PASSED in 8.8s //tensorflow/python/framework:graph_building_benchmark_cpu PASSED in 7.6s //tensorflow/python/framework:graph_util_test PASSED in 7.4s //tensorflow/python/framework:immutable_dict_test PASSED in 7.5s //tensorflow/python/framework:importer_test PASSED in 11.0s //tensorflow/python/framework:indexed_slices_test PASSED in 7.3s //tensorflow/python/framework:kernels_test PASSED in 8.9s //tensorflow/python/framework:meta_graph_test PASSED in 9.0s //tensorflow/python/framework:node_file_writer_test_cpu PASSED in 9.1s //tensorflow/python/framework:offset_counter_helper_test PASSED in 0.3s //tensorflow/python/framework:op_allowlist_namespace_test PASSED in 2.2s //tensorflow/python/framework:op_callbacks_test_cpu PASSED in 12.0s //tensorflow/python/framework:op_def_library_test PASSED in 7.5s //tensorflow/python/framework:op_def_util_test PASSED in 6.9s //tensorflow/python/framework:ops_enable_eager_test PASSED in 2.6s //tensorflow/python/framework:ops_test PASSED in 20.9s //tensorflow/python/framework:proto_test PASSED in 6.7s //tensorflow/python/framework:py_context_manager_test PASSED in 6.9s //tensorflow/python/framework:python_api_dispatcher_test PASSED in 8.0s //tensorflow/python/framework:python_api_info_test PASSED in 8.0s //tensorflow/python/framework:python_api_parameter_converter_test PASSED in 9.1s //tensorflow/python/framework:python_op_gen_annotation_test PASSED in 3.0s //tensorflow/python/framework:python_op_gen_annotator_test PASSED in 0.4s //tensorflow/python/framework:python_tensor_converter_test PASSED in 7.6s //tensorflow/python/framework:random_seed_test PASSED in 7.9s //tensorflow/python/framework:registry_test PASSED in 7.2s //tensorflow/python/framework:smart_cond_test PASSED in 8.4s //tensorflow/python/framework:sparse_tensor_test PASSED in 8.3s //tensorflow/python/framework:subscribe_test PASSED in 7.3s //tensorflow/python/framework:tensor_shape_test PASSED in 7.0s //tensorflow/python/framework:tensor_test PASSED in 7.7s //tensorflow/python/framework:tensor_util_test PASSED in 10.7s //tensorflow/python/framework:test_combinations_test PASSED in 8.8s //tensorflow/python/framework:test_util_test_cpu PASSED in 19.8s //tensorflow/python/framework:tf2_test PASSED in 8.7s //tensorflow/python/framework:traceable_stack_test PASSED in 10.5s //tensorflow/python/framework:type_spec_test PASSED in 8.6s //tensorflow/python/framework:versions_test PASSED in 8.3s //tensorflow/python/framework/experimental:graph_building_test_cpu PASSED in 7.0s //tensorflow/python/framework/experimental:unified_api_test_cpu PASSED in 13.5s //tensorflow/python/grappler:arithmetic_optimizer_test_cpu PASSED in 7.3s //tensorflow/python/grappler:auto_mixed_precision_test_cpu PASSED in 14.4s //tensorflow/python/grappler:constant_folding_test_cpu PASSED in 6.9s //tensorflow/python/grappler:cost_analyzer_test PASSED in 12.1s //tensorflow/python/grappler:datasets_test PASSED in 8.1s //tensorflow/python/grappler:item_test PASSED in 8.2s //tensorflow/python/grappler:memory_optimizer_test PASSED in 13.8s //tensorflow/python/grappler:model_analyzer_test PASSED in 10.4s //tensorflow/python/grappler:remapper_test_cpu PASSED in 11.2s //tensorflow/python/grappler:tf_optimizer_test PASSED in 10.2s //tensorflow/python/kernel_tests:benchmark_test_cpu PASSED in 9.4s //tensorflow/python/kernel_tests:check_ops_test_cpu PASSED in 16.3s //tensorflow/python/kernel_tests:collective_ops_multi_worker_test PASSED in 30.9s //tensorflow/python/kernel_tests:composite_tensor_ops_test PASSED in 9.4s //tensorflow/python/kernel_tests:critical_section_test_cpu PASSED in 22.2s //tensorflow/python/kernel_tests:garbage_collection_test PASSED in 10.2s //tensorflow/python/kernel_tests:gradient_correctness_test_cpu PASSED in 9.9s //tensorflow/python/kernel_tests:histogram_ops_test_cpu PASSED in 7.5s //tensorflow/python/kernel_tests:logging_ops_test_cpu PASSED in 8.8s //tensorflow/python/kernel_tests:numerics_test_cpu PASSED in 9.0s //tensorflow/python/kernel_tests:template_test PASSED in 10.9s //tensorflow/python/kernel_tests:trace_op_test_cpu PASSED in 9.4s //tensorflow/python/kernel_tests/array_ops:batch_gather_op_test_cpu PASSED in 11.2s //tensorflow/python/kernel_tests/array_ops:batch_scatter_ops_test PASSED in 8.5s //tensorflow/python/kernel_tests/array_ops:batchtospace_op_test_cpu PASSED in 19.8s //tensorflow/python/kernel_tests/array_ops:bcast_ops_test PASSED in 6.8s //tensorflow/python/kernel_tests/array_ops:bitcast_op_test_cpu PASSED in 6.9s //tensorflow/python/kernel_tests/array_ops:broadcast_to_ops_test_cpu PASSED in 38.2s //tensorflow/python/kernel_tests/array_ops:cast_op_test_cpu PASSED in 9.0s //tensorflow/python/kernel_tests/array_ops:constant_op_eager_test_cpu PASSED in 8.5s //tensorflow/python/kernel_tests/array_ops:constant_op_test_cpu PASSED in 12.1s //tensorflow/python/kernel_tests/array_ops:denormal_test_cpu PASSED in 8.6s //tensorflow/python/kernel_tests/array_ops:depthtospace_op_test_cpu PASSED in 12.8s //tensorflow/python/kernel_tests/array_ops:edit_distance_op_test PASSED in 11.7s //tensorflow/python/kernel_tests/array_ops:fingerprint_op_test PASSED in 8.0s //tensorflow/python/kernel_tests/array_ops:gather_nd_op_test_cpu PASSED in 12.5s //tensorflow/python/kernel_tests/array_ops:identity_n_op_py_test PASSED in 7.5s //tensorflow/python/kernel_tests/array_ops:identity_op_py_test PASSED in 7.0s //tensorflow/python/kernel_tests/array_ops:large_concat_op_test_cpu PASSED in 11.0s //tensorflow/python/kernel_tests/array_ops:manip_ops_test_cpu PASSED in 9.6s //tensorflow/python/kernel_tests/array_ops:one_hot_op_test_cpu PASSED in 11.1s //tensorflow/python/kernel_tests/array_ops:pad_op_test_cpu PASSED in 14.1s //tensorflow/python/kernel_tests/array_ops:reshape_op_test_cpu PASSED in 10.6s //tensorflow/python/kernel_tests/array_ops:reverse_sequence_op_test_cpu PASSED in 7.7s //tensorflow/python/kernel_tests/array_ops:scalar_test_cpu PASSED in 8.6s //tensorflow/python/kernel_tests/array_ops:shape_ops_test_cpu PASSED in 16.4s //tensorflow/python/kernel_tests/array_ops:slice_op_test_cpu PASSED in 9.0s //tensorflow/python/kernel_tests/array_ops:spacetobatch_op_test_cpu PASSED in 12.6s //tensorflow/python/kernel_tests/array_ops:spacetodepth_op_test_cpu PASSED in 8.5s //tensorflow/python/kernel_tests/array_ops:stack_op_test_cpu PASSED in 18.5s //tensorflow/python/kernel_tests/array_ops:unique_op_test_cpu PASSED in 7.4s //tensorflow/python/kernel_tests/array_ops:unstack_op_test_cpu PASSED in 9.4s //tensorflow/python/kernel_tests/array_ops:where_op_test_cpu PASSED in 19.8s //tensorflow/python/kernel_tests/control_flow:cond_v2_test_cpu PASSED in 65.7s //tensorflow/python/kernel_tests/control_flow:control_flow_util_test PASSED in 8.0s //tensorflow/python/kernel_tests/control_flow:control_flow_util_v2_test PASSED in 8.3s //tensorflow/python/kernel_tests/control_flow:py_func_test_cpu PASSED in 17.4s //tensorflow/python/kernel_tests/control_flow:scan_ops_test_cpu PASSED in 69.2s //tensorflow/python/kernel_tests/control_flow:while_v2_test_cpu PASSED in 61.3s //tensorflow/python/kernel_tests/custom_ops:ackermann_test PASSED in 7.3s //tensorflow/python/kernel_tests/custom_ops:duplicate_op_test PASSED in 7.3s //tensorflow/python/kernel_tests/custom_ops:invalid_op_test PASSED in 7.3s //tensorflow/python/kernel_tests/data_structures:conditional_accumulator_test PASSED in 8.4s //tensorflow/python/kernel_tests/data_structures:dynamic_partition_op_test_2gpu PASSED in 15.0s //tensorflow/python/kernel_tests/data_structures:dynamic_partition_op_test_cpu PASSED in 14.0s //tensorflow/python/kernel_tests/data_structures:dynamic_stitch_op_test_cpu PASSED in 9.9s //tensorflow/python/kernel_tests/data_structures:fifo_queue_test PASSED in 13.1s //tensorflow/python/kernel_tests/data_structures:list_ops_test_cpu PASSED in 21.1s //tensorflow/python/kernel_tests/data_structures:listdiff_op_test PASSED in 9.0s //tensorflow/python/kernel_tests/data_structures:lookup_ops_test PASSED in 21.2s //tensorflow/python/kernel_tests/data_structures:map_ops_test PASSED in 13.2s //tensorflow/python/kernel_tests/data_structures:padding_fifo_queue_test_cpu PASSED in 8.3s //tensorflow/python/kernel_tests/data_structures:priority_queue_test PASSED in 9.1s //tensorflow/python/kernel_tests/data_structures:stack_ops_test_cpu PASSED in 8.7s //tensorflow/python/kernel_tests/data_structures:stage_op_test_cpu PASSED in 11.3s //tensorflow/python/kernel_tests/distributions:bernoulli_test_cpu PASSED in 12.2s //tensorflow/python/kernel_tests/distributions:bijector_test_cpu PASSED in 10.6s //tensorflow/python/kernel_tests/distributions:categorical_test_cpu PASSED in 10.0s //tensorflow/python/kernel_tests/distributions:dirichlet_multinomial_test_cpu PASSED in 18.3s //tensorflow/python/kernel_tests/distributions:dirichlet_test_cpu PASSED in 14.5s //tensorflow/python/kernel_tests/distributions:exponential_test_cpu PASSED in 11.5s //tensorflow/python/kernel_tests/distributions:gamma_test_cpu PASSED in 65.7s //tensorflow/python/kernel_tests/distributions:identity_bijector_test_cpu PASSED in 8.0s //tensorflow/python/kernel_tests/distributions:kullback_leibler_test_cpu PASSED in 7.7s //tensorflow/python/kernel_tests/distributions:laplace_test_cpu PASSED in 28.6s //tensorflow/python/kernel_tests/distributions:multinomial_test_cpu PASSED in 8.0s //tensorflow/python/kernel_tests/distributions:normal_test_cpu PASSED in 31.7s //tensorflow/python/kernel_tests/distributions:special_math_test_cpu PASSED in 21.0s //tensorflow/python/kernel_tests/distributions:uniform_test_cpu PASSED in 11.9s //tensorflow/python/kernel_tests/image_ops:attention_ops_test PASSED in 7.1s //tensorflow/python/kernel_tests/image_ops:decode_bmp_op_test PASSED in 6.9s //tensorflow/python/kernel_tests/image_ops:decode_compressed_op_test PASSED in 10.4s //tensorflow/python/kernel_tests/image_ops:decode_image_op_test PASSED in 10.1s //tensorflow/python/kernel_tests/image_ops:decode_jpeg_op_test PASSED in 7.7s //tensorflow/python/kernel_tests/image_ops:decode_png_op_test PASSED in 9.5s //tensorflow/python/kernel_tests/image_ops:decode_raw_op_test PASSED in 9.2s //tensorflow/python/kernel_tests/image_ops:draw_bounding_box_op_test_cpu PASSED in 14.7s //tensorflow/python/kernel_tests/image_ops:extract_image_patches_op_test_cpu PASSED in 10.2s //tensorflow/python/kernel_tests/image_ops:extract_volume_patches_op_test_cpu PASSED in 9.4s //tensorflow/python/kernel_tests/io_ops:checkpoint_ops_test PASSED in 10.0s //tensorflow/python/kernel_tests/io_ops:decode_csv_op_test PASSED in 8.9s //tensorflow/python/kernel_tests/io_ops:io_ops_test PASSED in 11.0s //tensorflow/python/kernel_tests/io_ops:parse_single_example_op_test PASSED in 10.6s //tensorflow/python/kernel_tests/io_ops:parsing_ops_test PASSED in 30.5s //tensorflow/python/kernel_tests/io_ops:reader_ops_test PASSED in 17.9s //tensorflow/python/kernel_tests/io_ops:record_input_test PASSED in 33.6s //tensorflow/python/kernel_tests/io_ops:save_restore_ops_test PASSED in 7.1s //tensorflow/python/kernel_tests/linalg:determinant_op_test_cpu PASSED in 8.1s //tensorflow/python/kernel_tests/linalg:linear_operator_addition_test_cpu PASSED in 11.1s //tensorflow/python/kernel_tests/linalg:linear_operator_algebra_test_cpu PASSED in 7.5s //tensorflow/python/kernel_tests/linalg:linear_operator_test_cpu PASSED in 12.4s //tensorflow/python/kernel_tests/linalg:lu_op_test_cpu PASSED in 12.2s //tensorflow/python/kernel_tests/linalg:matrix_inverse_op_test_cpu PASSED in 7.7s //tensorflow/python/kernel_tests/linalg:matrix_logarithm_op_test PASSED in 52.2s //tensorflow/python/kernel_tests/linalg:matrix_solve_ls_op_test_cpu PASSED in 73.4s //tensorflow/python/kernel_tests/linalg:matrix_solve_op_test_cpu PASSED in 17.1s //tensorflow/python/kernel_tests/linalg:matrix_square_root_op_test_cpu PASSED in 6.7s //tensorflow/python/kernel_tests/linalg:slicing_test_cpu PASSED in 15.3s //tensorflow/python/kernel_tests/linalg/sparse:conjugate_gradient_test_cpu PASSED in 12.8s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_test_cpu PASSED in 7.1s //tensorflow/python/kernel_tests/math_ops:aggregate_ops_test_cpu PASSED in 9.2s //tensorflow/python/kernel_tests/math_ops:argmax_op_test_cpu PASSED in 11.3s //tensorflow/python/kernel_tests/math_ops:banded_triangular_solve_op_test_cpu PASSED in 9.5s //tensorflow/python/kernel_tests/math_ops:basic_gpu_test_cpu PASSED in 10.0s //tensorflow/python/kernel_tests/math_ops:bincount_op_test_cpu PASSED in 8.6s //tensorflow/python/kernel_tests/math_ops:bucketize_op_test_cpu PASSED in 9.0s //tensorflow/python/kernel_tests/math_ops:clip_ops_test PASSED in 8.1s //tensorflow/python/kernel_tests/math_ops:confusion_matrix_test PASSED in 12.6s //tensorflow/python/kernel_tests/math_ops:cross_grad_test_cpu PASSED in 7.9s //tensorflow/python/kernel_tests/math_ops:cumulative_logsumexp_test_cpu PASSED in 8.7s //tensorflow/python/kernel_tests/math_ops:in_topk_op_test_cpu PASSED in 8.4s //tensorflow/python/kernel_tests/math_ops:reduce_benchmark_test_cpu PASSED in 7.2s //tensorflow/python/kernel_tests/math_ops:segment_reduction_ops_d9m_test_cpu PASSED in 10.4s //tensorflow/python/kernel_tests/math_ops:sets_test PASSED in 27.9s //tensorflow/python/kernel_tests/math_ops:topk_op_test_cpu PASSED in 8.4s //tensorflow/python/kernel_tests/math_ops:zero_division_test_cpu PASSED in 7.1s //tensorflow/python/kernel_tests/nn_ops:betainc_op_test_cpu PASSED in 12.8s //tensorflow/python/kernel_tests/nn_ops:bias_op_test_cpu PASSED in 190.3s //tensorflow/python/kernel_tests/nn_ops:conv1d_test_cpu PASSED in 11.7s //tensorflow/python/kernel_tests/nn_ops:conv1d_transpose_test_cpu PASSED in 12.0s //tensorflow/python/kernel_tests/nn_ops:conv2d_transpose_test_cpu PASSED in 7.7s //tensorflow/python/kernel_tests/nn_ops:conv3d_backprop_filter_v2_grad_test_cpu PASSED in 11.0s //tensorflow/python/kernel_tests/nn_ops:conv3d_transpose_test_cpu PASSED in 9.8s //tensorflow/python/kernel_tests/nn_ops:ctc_decoder_ops_test PASSED in 9.0s //tensorflow/python/kernel_tests/nn_ops:ctc_loss_op_test_cpu PASSED in 95.1s //tensorflow/python/kernel_tests/nn_ops:cudnn_d9m_test_cpu PASSED in 7.7s //tensorflow/python/kernel_tests/nn_ops:cudnn_deterministic_ops_test_cpu PASSED in 6.9s //tensorflow/python/kernel_tests/nn_ops:losses_test PASSED in 29.6s //tensorflow/python/kernel_tests/nn_ops:lrn_op_test_cpu PASSED in 9.9s //tensorflow/python/kernel_tests/nn_ops:morphological_ops_test_cpu PASSED in 12.4s //tensorflow/python/kernel_tests/nn_ops:nth_element_op_test_cpu PASSED in 8.3s //tensorflow/python/kernel_tests/nn_ops:pool_test_cpu PASSED in 25.1s //tensorflow/python/kernel_tests/nn_ops:pooling_ops_3d_test_cpu PASSED in 18.9s //tensorflow/python/kernel_tests/nn_ops:relu_op_test_cpu PASSED in 12.7s //tensorflow/python/kernel_tests/nn_ops:softmax_op_test_cpu PASSED in 9.2s //tensorflow/python/kernel_tests/nn_ops:softplus_op_test_cpu PASSED in 8.9s //tensorflow/python/kernel_tests/nn_ops:softsign_op_test_cpu PASSED in 9.4s //tensorflow/python/kernel_tests/nn_ops:xent_op_d9m_test_cpu PASSED in 186.4s //tensorflow/python/kernel_tests/nn_ops:xent_op_test_cpu PASSED in 11.4s //tensorflow/python/kernel_tests/proto:descriptor_source_test PASSED in 7.6s //tensorflow/python/kernel_tests/proto:encode_proto_op_test PASSED in 9.6s //tensorflow/python/kernel_tests/quantization_ops:quantization_ops_test PASSED in 8.0s //tensorflow/python/kernel_tests/random:candidate_sampler_ops_test PASSED in 7.3s //tensorflow/python/kernel_tests/random:multinomial_op_test_cpu PASSED in 8.5s //tensorflow/python/kernel_tests/random:parameterized_truncated_normal_op_test_cpu PASSED in 12.3s //tensorflow/python/kernel_tests/random:random_crop_test_cpu PASSED in 8.4s //tensorflow/python/kernel_tests/random:random_grad_test_cpu PASSED in 10.5s //tensorflow/python/kernel_tests/random:random_ops_test_cpu PASSED in 16.1s //tensorflow/python/kernel_tests/random:random_poisson_test_cpu PASSED in 9.2s //tensorflow/python/kernel_tests/random:random_shuffle_queue_test PASSED in 9.1s //tensorflow/python/kernel_tests/random:stateful_random_ops_test_cpu PASSED in 23.0s //tensorflow/python/kernel_tests/signal:mel_ops_test_cpu PASSED in 14.2s //tensorflow/python/kernel_tests/signal:mfcc_ops_test_cpu PASSED in 8.0s //tensorflow/python/kernel_tests/signal:reconstruction_ops_test_cpu PASSED in 19.1s //tensorflow/python/kernel_tests/signal:shape_ops_test_cpu PASSED in 23.4s //tensorflow/python/kernel_tests/sparse_ops:sparse_add_op_test PASSED in 9.5s //tensorflow/python/kernel_tests/sparse_ops:sparse_concat_op_test PASSED in 9.1s //tensorflow/python/kernel_tests/sparse_ops:sparse_conditional_accumulator_test PASSED in 9.3s //tensorflow/python/kernel_tests/sparse_ops:sparse_cross_op_test PASSED in 12.6s //tensorflow/python/kernel_tests/sparse_ops:sparse_matmul_op_test_cpu PASSED in 42.6s //tensorflow/python/kernel_tests/sparse_ops:sparse_reorder_op_test PASSED in 8.5s //tensorflow/python/kernel_tests/sparse_ops:sparse_reshape_op_test PASSED in 13.1s //tensorflow/python/kernel_tests/sparse_ops:sparse_serialization_ops_test PASSED in 11.2s //tensorflow/python/kernel_tests/sparse_ops:sparse_slice_op_test PASSED in 10.8s //tensorflow/python/kernel_tests/sparse_ops:sparse_split_op_test_cpu PASSED in 10.1s //tensorflow/python/kernel_tests/sparse_ops:sparse_tensor_dense_matmul_grad_test_cpu PASSED in 21.5s //tensorflow/python/kernel_tests/sparse_ops:sparse_tensor_dense_matmul_op_d9m_test_cpu PASSED in 36.0s //tensorflow/python/kernel_tests/sparse_ops:sparse_tensor_dense_matmul_op_test_cpu PASSED in 33.5s //tensorflow/python/kernel_tests/sparse_ops:sparse_tensors_map_ops_test PASSED in 9.6s //tensorflow/python/kernel_tests/sparse_ops:sparse_to_dense_op_py_test_cpu PASSED in 8.8s //tensorflow/python/kernel_tests/sparse_ops:sparse_xent_op_d9m_test_cpu PASSED in 93.7s //tensorflow/python/kernel_tests/sparse_ops:sparse_xent_op_test_cpu PASSED in 8.6s //tensorflow/python/kernel_tests/sparse_ops:sparsemask_op_test PASSED in 8.4s //tensorflow/python/kernel_tests/strings_ops:as_string_op_test PASSED in 8.6s //tensorflow/python/kernel_tests/strings_ops:base64_ops_test PASSED in 11.7s //tensorflow/python/kernel_tests/strings_ops:reduce_join_op_test_cpu PASSED in 8.4s //tensorflow/python/kernel_tests/strings_ops:regex_full_match_op_test PASSED in 9.2s //tensorflow/python/kernel_tests/strings_ops:regex_replace_op_test PASSED in 8.5s //tensorflow/python/kernel_tests/strings_ops:string_bytes_split_op_test PASSED in 7.8s //tensorflow/python/kernel_tests/strings_ops:string_format_op_test PASSED in 8.8s //tensorflow/python/kernel_tests/strings_ops:string_join_op_test PASSED in 8.6s //tensorflow/python/kernel_tests/strings_ops:string_length_op_test PASSED in 10.0s //tensorflow/python/kernel_tests/strings_ops:string_lower_op_test PASSED in 8.0s //tensorflow/python/kernel_tests/strings_ops:string_split_op_test PASSED in 9.8s //tensorflow/python/kernel_tests/strings_ops:string_strip_op_test PASSED in 7.5s //tensorflow/python/kernel_tests/strings_ops:string_to_hash_bucket_op_test_cpu PASSED in 8.1s //tensorflow/python/kernel_tests/strings_ops:string_to_number_op_test_cpu PASSED in 11.1s //tensorflow/python/kernel_tests/strings_ops:string_upper_op_test PASSED in 8.0s //tensorflow/python/kernel_tests/strings_ops:substr_op_test PASSED in 9.6s //tensorflow/python/kernel_tests/strings_ops:unicode_decode_op_test PASSED in 16.2s //tensorflow/python/kernel_tests/strings_ops:unicode_encode_op_test PASSED in 7.3s //tensorflow/python/kernel_tests/strings_ops:unicode_script_op_test PASSED in 7.4s //tensorflow/python/kernel_tests/strings_ops:unicode_transcode_op_test PASSED in 8.9s //tensorflow/python/kernel_tests/strings_ops:unsorted_segment_join_op_test_cpu PASSED in 8.8s //tensorflow/python/kernel_tests/summary_ops:summary_ops_test_cpu PASSED in 15.5s //tensorflow/python/kernel_tests/summary_ops:summary_v1_audio_op_test_cpu PASSED in 8.5s //tensorflow/python/kernel_tests/summary_ops:summary_v1_image_op_test_cpu PASSED in 7.2s //tensorflow/python/kernel_tests/summary_ops:summary_v1_ops_test PASSED in 8.6s //tensorflow/python/kernel_tests/summary_ops:summary_v1_tensor_op_test PASSED in 8.5s //tensorflow/python/kernel_tests/v1_compat_tests:array_ops_test_cpu PASSED in 7.7s //tensorflow/python/kernel_tests/v1_compat_tests:dense_update_ops_test_cpu PASSED in 8.0s //tensorflow/python/kernel_tests/v1_compat_tests:identity_op_py_test PASSED in 6.7s //tensorflow/python/kernel_tests/v1_compat_tests:scatter_nd_ops_test_cpu PASSED in 7.9s //tensorflow/python/kernel_tests/v1_compat_tests:session_ops_test_cpu PASSED in 9.3s //tensorflow/python/kernel_tests/v1_compat_tests:stack_op_test_cpu PASSED in 7.7s //tensorflow/python/kernel_tests/variables:dense_update_ops_no_tsan_test_cpu PASSED in 10.2s //tensorflow/python/kernel_tests/variables:dense_update_ops_test_cpu PASSED in 7.6s //tensorflow/python/kernel_tests/variables:partitioned_variables_test PASSED in 10.5s //tensorflow/python/kernel_tests/variables:resource_variable_ops_test_cpu PASSED in 53.2s //tensorflow/python/kernel_tests/variables:variable_ops_test_cpu PASSED in 8.3s //tensorflow/python/kernel_tests/variables:variable_scope_test PASSED in 39.9s //tensorflow/python/kernel_tests/variables:variables_test PASSED in 13.2s //tensorflow/python/lib/core:custom_float_test PASSED in 8.3s //tensorflow/python/lib/io:file_io_test PASSED in 11.0s //tensorflow/python/lib/io:tf_record_test PASSED in 10.2s //tensorflow/python/module:module_test PASSED in 10.2s //tensorflow/python/ops/losses:util_test PASSED in 7.3s //tensorflow/python/ops/memory_tests:custom_gradient_memory_test_cpu PASSED in 11.5s //tensorflow/python/ops/numpy_ops:np_array_ops_test_cpu PASSED in 87.9s //tensorflow/python/ops/numpy_ops:np_arrays_test_cpu PASSED in 8.6s //tensorflow/python/ops/numpy_ops:np_dtypes_test_cpu PASSED in 7.9s //tensorflow/python/ops/numpy_ops:np_interop_test_cpu PASSED in 51.9s //tensorflow/python/ops/numpy_ops:np_logic_test_cpu PASSED in 10.5s //tensorflow/python/ops/numpy_ops:np_math_ops_test_cpu PASSED in 22.9s //tensorflow/python/ops/numpy_ops:np_random_test_cpu PASSED in 74.9s //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 18.2s //tensorflow/python/ops/numpy_ops/integration_test:public_symbol_test PASSED in 15.1s //tensorflow/python/ops/parallel_for:array_test_cpu PASSED in 50.1s //tensorflow/python/ops/parallel_for:gradients_test_cpu PASSED in 13.6s //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 8.2s //tensorflow/python/ops/ragged:ragged_batch_gather_op_test PASSED in 68.1s //tensorflow/python/ops/ragged:ragged_bitcast_op_test PASSED in 7.6s //tensorflow/python/ops/ragged:ragged_boolean_mask_op_test PASSED in 19.5s //tensorflow/python/ops/ragged:ragged_concat_op_test PASSED in 10.7s //tensorflow/python/ops/ragged:ragged_const_op_test PASSED in 8.7s //tensorflow/python/ops/ragged:ragged_constant_value_op_test PASSED in 7.1s //tensorflow/python/ops/ragged:ragged_cross_op_test PASSED in 29.1s //tensorflow/python/ops/ragged:ragged_dispatch_test PASSED in 122.3s //tensorflow/python/ops/ragged:ragged_dynamic_partition_op_test_cpu PASSED in 18.1s //tensorflow/python/ops/ragged:ragged_eager_test PASSED in 7.2s //tensorflow/python/ops/ragged:ragged_expand_dims_op_test PASSED in 8.2s //tensorflow/python/ops/ragged:ragged_factory_ops_test_cpu PASSED in 14.7s //tensorflow/python/ops/ragged:ragged_fill_empty_rows_op_test PASSED in 9.2s //tensorflow/python/ops/ragged:ragged_from_sparse_op_test PASSED in 8.1s //tensorflow/python/ops/ragged:ragged_from_tensor_op_test PASSED in 21.5s //tensorflow/python/ops/ragged:ragged_gather_nd_op_test PASSED in 10.6s //tensorflow/python/ops/ragged:ragged_map_flat_values_op_test PASSED in 7.9s //tensorflow/python/ops/ragged:ragged_map_fn_op_test PASSED in 13.2s //tensorflow/python/ops/ragged:ragged_math_ops_test PASSED in 15.1s //tensorflow/python/ops/ragged:ragged_matmul_op_test PASSED in 41.3s //tensorflow/python/ops/ragged:ragged_merge_dims_op_test PASSED in 32.3s //tensorflow/python/ops/ragged:ragged_one_hot_op_test PASSED in 12.7s //tensorflow/python/ops/ragged:ragged_operators_test PASSED in 19.9s //tensorflow/python/ops/ragged:ragged_placeholder_op_test PASSED in 9.1s //tensorflow/python/ops/ragged:ragged_print_op_test PASSED in 18.1s //tensorflow/python/ops/ragged:ragged_range_op_test PASSED in 8.7s //tensorflow/python/ops/ragged:ragged_rank_op_test PASSED in 11.9s //tensorflow/python/ops/ragged:ragged_reduce_op_test PASSED in 32.2s //tensorflow/python/ops/ragged:ragged_resize_image_op_test PASSED in 17.4s //tensorflow/python/ops/ragged:ragged_reverse_op_test PASSED in 7.8s //tensorflow/python/ops/ragged:ragged_row_lengths_op_test PASSED in 7.8s //tensorflow/python/ops/ragged:ragged_row_splits_to_segment_ids_op_test PASSED in 9.7s //tensorflow/python/ops/ragged:ragged_segment_ids_to_row_splits_op_test PASSED in 7.7s //tensorflow/python/ops/ragged:ragged_segment_op_test PASSED in 16.1s //tensorflow/python/ops/ragged:ragged_size_op_test PASSED in 7.0s //tensorflow/python/ops/ragged:ragged_split_op_test PASSED in 43.2s //tensorflow/python/ops/ragged:ragged_squeeze_op_test PASSED in 24.7s //tensorflow/python/ops/ragged:ragged_stack_op_test PASSED in 12.2s //tensorflow/python/ops/ragged:ragged_tensor_bounding_shape_op_test PASSED in 12.0s //tensorflow/python/ops/ragged:ragged_tensor_shape_test PASSED in 79.2s //tensorflow/python/ops/ragged:ragged_tile_op_test PASSED in 47.2s //tensorflow/python/ops/ragged:ragged_to_sparse_op_test PASSED in 12.9s //tensorflow/python/ops/ragged:ragged_to_tensor_op_test PASSED in 74.7s //tensorflow/python/ops/ragged:ragged_util_test PASSED in 31.9s //tensorflow/python/ops/ragged:ragged_where_op_test PASSED in 32.4s //tensorflow/python/ops/ragged:row_partition_test PASSED in 24.9s //tensorflow/python/ops/ragged:string_ngrams_op_test PASSED in 9.6s //tensorflow/python/ops/ragged:strings_reduce_join_op_test PASSED in 12.0s //tensorflow/python/ops/structured:structured_array_ops_test PASSED in 44.7s //tensorflow/python/ops/structured:structured_tensor_slice_test PASSED in 74.2s //tensorflow/python/ops/structured:structured_tensor_spec_test PASSED in 12.3s //tensorflow/python/ops/structured:structured_tensor_test PASSED in 53.8s //tensorflow/python/ops/v1_compat_tests:gradient_checker_test_cpu PASSED in 9.5s //tensorflow/python/platform:benchmark_test PASSED in 7.3s //tensorflow/python/platform:build_info_test PASSED in 10.0s //tensorflow/python/platform:resource_loader_test PASSED in 2.3s //tensorflow/python/profiler:pprof_profiler_test PASSED in 6.9s //tensorflow/python/profiler:profile_context_test_cpu PASSED in 39.1s //tensorflow/python/profiler:profiler_client_test_cpu PASSED in 8.4s //tensorflow/python/profiler:profiler_test_cpu PASSED in 20.3s //tensorflow/python/profiler:profiler_v2_test_cpu PASSED in 7.3s //tensorflow/python/profiler:profiler_wrapper_test PASSED in 7.0s //tensorflow/python/profiler:tfprof_logger_test PASSED in 7.4s //tensorflow/python/profiler/internal:flops_registry_test PASSED in 8.0s //tensorflow/python/profiler/internal:print_model_analysis_test PASSED in 7.4s //tensorflow/python/profiler/internal:run_metadata_test_cpu PASSED in 12.8s //tensorflow/python/saved_model:fingerprinting_test PASSED in 9.8s //tensorflow/python/saved_model:keras_injection_test PASSED in 17.5s //tensorflow/python/saved_model:load_v1_in_v2_test PASSED in 16.6s //tensorflow/python/saved_model:loader_test PASSED in 11.6s //tensorflow/python/saved_model:method_name_updater_test PASSED in 8.4s //tensorflow/python/saved_model:metrics_test PASSED in 10.8s //tensorflow/python/saved_model:nested_structure_coder_test PASSED in 8.3s //tensorflow/python/saved_model:pywrap_saved_model_fingerprinting_test PASSED in 8.4s //tensorflow/python/saved_model:pywrap_saved_model_metrics_test PASSED in 8.4s //tensorflow/python/saved_model:revived_types_test PASSED in 7.0s //tensorflow/python/saved_model:save_context_test PASSED in 11.7s //tensorflow/python/saved_model:save_test PASSED in 29.0s //tensorflow/python/saved_model:saved_model_test PASSED in 16.9s //tensorflow/python/saved_model:signature_def_utils_test PASSED in 9.7s //tensorflow/python/saved_model:simple_save_test PASSED in 8.6s //tensorflow/python/saved_model:tracing_utils_test PASSED in 8.3s //tensorflow/python/saved_model:utils_test PASSED in 8.1s //tensorflow/python/saved_model/model_utils:export_output_test PASSED in 19.2s //tensorflow/python/saved_model/model_utils:export_test PASSED in 10.6s //tensorflow/python/saved_model/model_utils:mode_keys_test PASSED in 6.9s //tensorflow/python/saved_model/registration:registration_saving_test PASSED in 13.9s //tensorflow/python/saved_model/registration:registration_test PASSED in 8.0s //tensorflow/python/saved_model/registration:tf_registration_test PASSED in 14.5s //tensorflow/python/summary:plugin_asset_test PASSED in 8.2s //tensorflow/python/summary:summary_iterator_test PASSED in 9.8s //tensorflow/python/summary:summary_test PASSED in 8.1s //tensorflow/python/summary:summary_v2_test PASSED in 7.4s //tensorflow/python/summary/writer:writer_test PASSED in 22.7s //tensorflow/python/tools:aot_compiled_test PASSED in 20.9s //tensorflow/python/tools:freeze_graph_test PASSED in 17.3s //tensorflow/python/tools:optimize_for_inference_test PASSED in 8.0s //tensorflow/python/tools:print_selective_registration_header_test PASSED in 15.5s //tensorflow/python/tools:saved_model_cli_test PASSED in 23.7s //tensorflow/python/tools:saved_model_utils_test PASSED in 11.5s //tensorflow/python/tools:strip_unused_test PASSED in 12.6s //tensorflow/python/tools/api/generator:create_python_api_test PASSED in 14.3s //tensorflow/python/tools/api/generator:output_init_files_test PASSED in 13.4s //tensorflow/python/tools/api/generator:tensorflow_doc_srcs_test PASSED in 14.5s //tensorflow/python/tpu:bfloat16_test PASSED in 9.6s //tensorflow/python/tpu:feature_column_test PASSED in 14.9s //tensorflow/python/tpu:topology_test PASSED in 6.7s //tensorflow/python/tpu:tpu_embedding_for_serving_test PASSED in 9.6s //tensorflow/python/tpu:tpu_embedding_v2_utils_test PASSED in 8.4s //tensorflow/python/tpu:tpu_infeed_test PASSED in 8.8s //tensorflow/python/tpu:tpu_sharding_test PASSED in 8.4s //tensorflow/python/tpu:tpu_test_wrapper_test PASSED in 6.8s //tensorflow/python/tpu/client:client_py_test PASSED in 8.2s //tensorflow/python/trackable:autotrackable_test PASSED in 8.8s //tensorflow/python/trackable:base_delegate_test PASSED in 8.3s //tensorflow/python/trackable:base_test PASSED in 10.6s //tensorflow/python/trackable:data_structures_test PASSED in 18.3s //tensorflow/python/trackable:python_state_test PASSED in 9.9s //tensorflow/python/trackable:resource_test PASSED in 18.9s //tensorflow/python/trackable:trackable_utils_test PASSED in 7.7s //tensorflow/python/training:adadelta_test_cpu PASSED in 17.1s //tensorflow/python/training:adagrad_da_test_cpu PASSED in 11.7s //tensorflow/python/training:adagrad_test_cpu PASSED in 18.6s //tensorflow/python/training:adam_test_cpu PASSED in 27.9s //tensorflow/python/training:basic_loops_test_cpu PASSED in 10.3s //tensorflow/python/training:basic_session_run_hooks_test PASSED in 19.9s //tensorflow/python/training:checkpoint_ops_test PASSED in 20.0s //tensorflow/python/training:coordinator_test_cpu PASSED in 16.3s //tensorflow/python/training:device_setter_test_cpu PASSED in 8.7s //tensorflow/python/training:ftrl_test_cpu PASSED in 13.5s //tensorflow/python/training:gradient_descent_test_cpu PASSED in 12.6s //tensorflow/python/training:input_test PASSED in 26.8s //tensorflow/python/training:momentum_test_cpu PASSED in 10.7s //tensorflow/python/training:monitored_session_test PASSED in 23.7s //tensorflow/python/training:moving_averages_test_cpu PASSED in 20.4s //tensorflow/python/training:optimizer_test_cpu PASSED in 11.8s //tensorflow/python/training:proximal_adagrad_test_cpu PASSED in 9.2s //tensorflow/python/training:proximal_gradient_descent_test_cpu PASSED in 9.5s //tensorflow/python/training:quantize_training_test_cpu PASSED in 8.2s //tensorflow/python/training:queue_runner_test_cpu PASSED in 8.6s //tensorflow/python/training:rmsprop_test_cpu PASSED in 32.3s //tensorflow/python/training:saver_large_partitioned_variable_test PASSED in 16.5s //tensorflow/python/training:saver_test_2gpu PASSED in 31.9s //tensorflow/python/training:saver_test_cpu PASSED in 44.5s //tensorflow/python/training:server_lib_multiple_containers_test PASSED in 9.0s //tensorflow/python/training:server_lib_same_variables_clear_container_test PASSED in 7.5s //tensorflow/python/training:server_lib_same_variables_clear_test PASSED in 8.4s //tensorflow/python/training:server_lib_same_variables_no_clear_test PASSED in 7.2s //tensorflow/python/training:server_lib_sparse_job_test PASSED in 7.6s //tensorflow/python/training:server_lib_test PASSED in 14.7s //tensorflow/python/training:session_manager_test_cpu PASSED in 75.5s //tensorflow/python/training:slot_creator_test_cpu PASSED in 11.9s //tensorflow/python/training:supervisor_test PASSED in 17.2s //tensorflow/python/training:training_ops_mlir_test_cpu PASSED in 10.0s //tensorflow/python/training:training_ops_test_cpu PASSED in 10.8s //tensorflow/python/training:training_util_test PASSED in 9.3s //tensorflow/python/training:warm_starting_util_test PASSED in 23.7s //tensorflow/python/training/experimental:loss_scale_optimizer_test PASSED in 16.6s //tensorflow/python/training/experimental:loss_scale_test PASSED in 27.1s //tensorflow/python/training/experimental:mixed_precision_test_cpu PASSED in 7.6s //tensorflow/python/training/saving:saveable_object_util_test PASSED in 8.5s //tensorflow/python/util:compat_test PASSED in 11.0s //tensorflow/python/util:decorator_utils_test PASSED in 7.8s //tensorflow/python/util:deprecation_test PASSED in 9.7s //tensorflow/python/util:dispatch_test PASSED in 8.7s //tensorflow/python/util:example_parser_configuration_test PASSED in 8.7s //tensorflow/python/util:fast_module_type_test PASSED in 8.0s //tensorflow/python/util:function_parameter_canonicalizer_test PASSED in 11.8s //tensorflow/python/util:function_utils_test PASSED in 7.6s //tensorflow/python/util:keyword_args_test PASSED in 7.6s //tensorflow/python/util:lazy_loader_test PASSED in 10.5s //tensorflow/python/util:lock_util_test PASSED in 9.2s //tensorflow/python/util:module_wrapper_test PASSED in 7.4s //tensorflow/python/util:nest_test PASSED in 14.2s //tensorflow/python/util:object_identity_test PASSED in 9.5s //tensorflow/python/util:pywrap_xla_ops_test PASSED in 1.8s //tensorflow/python/util:serialization_test PASSED in 6.8s //tensorflow/python/util:tf_contextlib_test PASSED in 8.0s //tensorflow/python/util:tf_decorator_test PASSED in 8.0s //tensorflow/python/util:tf_export_test PASSED in 7.2s //tensorflow/python/util:tf_inspect_test PASSED in 8.2s //tensorflow/python/util:tf_should_use_test PASSED in 8.3s //tensorflow/python/util:tf_stack_test PASSED in 7.5s //tensorflow/python/util:traceback_utils_test PASSED in 9.3s //tensorflow/python/util:type_annotations_test PASSED in 7.6s //tensorflow/python/util:variable_utils_test PASSED in 6.7s //tensorflow/python/util:vlog_test PASSED in 7.3s //tensorflow/tools/api/tests:module_test PASSED in 14.8s //tensorflow/tools/benchmark:benchmark_model_test PASSED in 2.2s //tensorflow/tools/common:public_api_test PASSED in 1.8s //tensorflow/tools/common:traverse_test PASSED in 2.5s //tensorflow/tools/compatibility:all_renames_v2_test PASSED in 9.1s //tensorflow/tools/compatibility:ast_edits_test PASSED in 6.4s //tensorflow/tools/compatibility:test_file_v1_0 PASSED in 13.2s //tensorflow/tools/compatibility:test_file_v2_0 PASSED in 14.1s //tensorflow/tools/compatibility:tf_upgrade_test PASSED in 6.7s //tensorflow/tools/compatibility:tf_upgrade_v2_safety_test PASSED in 8.9s //tensorflow/tools/docs:tf_doctest_test PASSED in 0.7s //tensorflow/tools/graph_transforms:file_utils_test PASSED in 1.3s //tensorflow/tools/graph_transforms:transform_graph_test PASSED in 3.7s //tensorflow/tools/graph_transforms:transform_utils_test PASSED in 1.9s //tensorflow/tools/graph_transforms:transforms_test PASSED in 4.8s //tensorflow/tools/proto_text:gen_proto_text_functions_lib_test PASSED in 0.1s //tensorflow/tools/tensorflow_builder/compat_checker:compat_checker_test PASSED in 0.9s //tensorflow/tsl/c:tsl_status_helper_test PASSED in 0.6s //tensorflow/tsl/c:tsl_status_test PASSED in 0.8s //tensorflow/tsl/concurrency:async_value_ref_test PASSED in 0.1s //tensorflow/tsl/concurrency:async_value_test PASSED in 0.1s //tensorflow/tsl/concurrency:concurrent_vector_test PASSED in 0.7s //tensorflow/tsl/cuda:cudnn_version_test PASSED in 0.2s //tensorflow/tsl/distributed_runtime/coordination:coordination_service_agent_test PASSED in 18.2s //tensorflow/tsl/distributed_runtime/coordination:coordination_service_error_util_test PASSED in 0.1s //tensorflow/tsl/distributed_runtime/coordination:coordination_service_recoverable_job_test PASSED in 0.6s //tensorflow/tsl/distributed_runtime/persistent_cache_repository:fake_cache_repository_test PASSED in 0.1s //tensorflow/tsl/distributed_runtime/preemption:preemption_notifier_test PASSED in 7.2s //tensorflow/tsl/distributed_runtime/preemption:preemption_sync_manager_test PASSED in 6.3s //tensorflow/tsl/distributed_runtime/rpc:grpc_channel_test PASSED in 0.8s //tensorflow/tsl/distributed_runtime/rpc:grpc_util_test PASSED in 0.4s //tensorflow/tsl/framework:cancellation_test PASSED in 1.6s //tensorflow/tsl/framework:device_id_utils_test PASSED in 4.4s //tensorflow/tsl/framework/convolution:spatial_convolutions_test PASSED in 0.3s //tensorflow/tsl/lib/gtl:tsl_lib_gtl_tests PASSED in 0.1s //tensorflow/tsl/lib/hash:crc32c_test PASSED in 0.6s //tensorflow/tsl/lib/histogram:histogram_test PASSED in 0.6s //tensorflow/tsl/lib/io:buffered_inputstream_test PASSED in 0.6s //tensorflow/tsl/lib/io:cache_test PASSED in 0.1s //tensorflow/tsl/lib/io:inputbuffer_test PASSED in 1.3s //tensorflow/tsl/lib/io:inputstream_interface_test PASSED in 0.6s //tensorflow/tsl/lib/io:random_inputstream_test PASSED in 0.1s //tensorflow/tsl/lib/io:record_reader_writer_test PASSED in 0.5s //tensorflow/tsl/lib/io:recordio_test PASSED in 0.5s //tensorflow/tsl/lib/io:table_test PASSED in 3.9s //tensorflow/tsl/lib/io:zlib_buffers_test PASSED in 8.8s //tensorflow/tsl/lib/io/snappy:snappy_test PASSED in 1.3s //tensorflow/tsl/lib/math:math_util_test PASSED in 0.1s //tensorflow/tsl/lib/random:distribution_sampler_test PASSED in 0.6s //tensorflow/tsl/lib/random:philox_random_test PASSED in 0.7s //tensorflow/tsl/lib/random:random_distributions_test PASSED in 24.7s //tensorflow/tsl/lib/random:simple_philox_test PASSED in 0.1s //tensorflow/tsl/lib/random:weighted_picker_test PASSED in 11.1s //tensorflow/tsl/platform:ctstring_test PASSED in 0.2s //tensorflow/tsl/platform:denormal_test PASSED in 0.1s //tensorflow/tsl/platform:errors_test PASSED in 0.4s //tensorflow/tsl/platform:fingerprint_test PASSED in 0.6s //tensorflow/tsl/platform:float8_test PASSED in 2.2s //tensorflow/tsl/platform:hash_test PASSED in 0.2s //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 25.6s //tensorflow/tsl/platform:mutex_test PASSED in 0.2s //tensorflow/tsl/platform:net_test PASSED in 0.1s //tensorflow/tsl/platform:numbers_test PASSED in 0.5s //tensorflow/tsl/platform:path_test PASSED in 0.1s //tensorflow/tsl/platform:port_test PASSED in 8.2s //tensorflow/tsl/platform:random_test PASSED in 2.5s //tensorflow/tsl/platform:refcount_test PASSED in 0.4s //tensorflow/tsl/platform:retrying_file_system_test PASSED in 0.2s //tensorflow/tsl/platform:retrying_utils_test PASSED in 0.1s //tensorflow/tsl/platform:scanner_test PASSED in 0.3s //tensorflow/tsl/platform:setround_test PASSED in 1.0s //tensorflow/tsl/platform:stacktrace_handler_test PASSED in 3.0s //tensorflow/tsl/platform:stacktrace_test PASSED in 1.3s //tensorflow/tsl/platform:status_matchers_test PASSED in 0.2s //tensorflow/tsl/platform:status_test PASSED in 0.1s //tensorflow/tsl/platform:statusor_test PASSED in 2.8s //tensorflow/tsl/platform:str_util_test PASSED in 0.4s //tensorflow/tsl/platform:strcat_test PASSED in 0.4s //tensorflow/tsl/platform:stringpiece_test PASSED in 0.6s //tensorflow/tsl/platform:stringprintf_test PASSED in 0.9s //tensorflow/tsl/platform:subprocess_test PASSED in 1.7s //tensorflow/tsl/platform:tstring_test PASSED in 0.3s //tensorflow/tsl/platform:unbounded_work_queue_test PASSED in 0.2s //tensorflow/tsl/platform/cloud:compute_engine_metadata_client_test PASSED in 0.3s //tensorflow/tsl/platform/cloud:compute_engine_zone_provider_test PASSED in 0.2s //tensorflow/tsl/platform/cloud:curl_http_request_test PASSED in 7.6s //tensorflow/tsl/platform/cloud:expiring_lru_cache_test PASSED in 0.2s //tensorflow/tsl/platform/cloud:gcs_dns_cache_test PASSED in 0.3s //tensorflow/tsl/platform/cloud:gcs_file_system_test PASSED in 6.4s //tensorflow/tsl/platform/cloud:gcs_throttle_test PASSED in 0.1s //tensorflow/tsl/platform/cloud:google_auth_provider_test PASSED in 0.2s //tensorflow/tsl/platform/cloud:oauth_client_test PASSED in 0.7s //tensorflow/tsl/platform/cloud:ram_file_block_cache_test PASSED in 3.1s //tensorflow/tsl/platform/cloud:time_util_test PASSED in 0.2s //tensorflow/tsl/profiler/backends/cpu:traceme_recorder_test PASSED in 1.5s //tensorflow/tsl/profiler/convert:trace_container_test PASSED in 0.5s //tensorflow/tsl/profiler/convert:trace_events_to_json_test PASSED in 1.1s //tensorflow/tsl/profiler/convert:xla_op_utils_test PASSED in 0.3s //tensorflow/tsl/profiler/convert:xplane_to_trace_events_test PASSED in 0.3s //tensorflow/tsl/profiler/lib:profiler_factory_test PASSED in 0.4s //tensorflow/tsl/profiler/lib:profiler_lock_test PASSED in 0.2s //tensorflow/tsl/profiler/lib:scoped_annotation_test PASSED in 0.7s //tensorflow/tsl/profiler/lib:traceme_encode_test PASSED in 0.1s //tensorflow/tsl/profiler/rpc/client:profiler_client_test PASSED in 4.1s //tensorflow/tsl/profiler/rpc/client:remote_profiler_session_manager_test PASSED in 3.7s //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 0.1s //tensorflow/tsl/profiler/utils:preprocess_xplane_test PASSED in 0.7s //tensorflow/tsl/profiler/utils:tf_op_utils_test PASSED in 0.2s //tensorflow/tsl/profiler/utils:timespan_test PASSED in 0.2s //tensorflow/tsl/profiler/utils:tpu_xplane_utils_test PASSED in 0.6s //tensorflow/tsl/profiler/utils:xplane_builder_test PASSED in 0.7s //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 0.1s //tensorflow/compiler/tests:complex_div_test_cpu PASSED in 7.3s Stats over 2 runs: max = 7.3s, min = 6.7s, avg = 7.0s, dev = 0.3s //tensorflow/compiler/tests:complex_div_test_cpu_mlir_bridge_test PASSED in 8.6s Stats over 2 runs: max = 8.6s, min = 7.5s, avg = 8.1s, dev = 0.6s //tensorflow/compiler/xla/tests:conditional_test_cpu PASSED in 13.0s Stats over 2 runs: max = 13.0s, min = 12.3s, avg = 12.7s, dev = 0.3s //tensorflow/python:control_flow_ops_test_cpu PASSED in 35.0s Stats over 2 runs: max = 35.0s, min = 29.1s, avg = 32.0s, dev = 3.0s //tensorflow/python/data/experimental/kernel_tests/optimization:optimization_test PASSED in 19.4s Stats over 2 runs: max = 19.4s, min = 10.7s, avg = 15.1s, dev = 4.3s //tensorflow/python/data/experimental/kernel_tests/service:metadata_test PASSED in 17.1s Stats over 2 runs: max = 17.1s, min = 13.4s, avg = 15.3s, dev = 1.8s //tensorflow/python/data/kernel_tests:padded_batch_test PASSED in 34.6s Stats over 2 runs: max = 34.6s, min = 33.3s, avg = 34.0s, dev = 0.6s //tensorflow/python/data/kernel_tests:repeat_test PASSED in 40.2s Stats over 2 runs: max = 40.2s, min = 38.3s, avg = 39.3s, dev = 0.9s //tensorflow/python/data/kernel_tests:window_test PASSED in 42.1s Stats over 2 runs: max = 42.1s, min = 36.0s, avg = 39.0s, dev = 3.0s //tensorflow/python/kernel_tests/array_ops:scatter_nd_ops_test_cpu PASSED in 14.4s Stats over 2 runs: max = 14.4s, min = 13.7s, avg = 14.0s, dev = 0.3s //tensorflow/python/kernel_tests/control_flow:functional_ops_test_cpu PASSED in 16.8s Stats over 2 runs: max = 16.8s, min = 16.1s, avg = 16.4s, dev = 0.3s //tensorflow/python/kernel_tests/control_flow:map_fn_test_cpu PASSED in 12.0s Stats over 2 runs: max = 12.0s, min = 10.9s, avg = 11.4s, dev = 0.5s //tensorflow/python/kernel_tests/nn_ops:atrous_conv2d_test_cpu PASSED in 25.6s Stats over 2 runs: max = 25.6s, min = 15.9s, avg = 20.8s, dev = 4.8s //tensorflow/python/kernel_tests/nn_ops:bias_op_d9m_test_cpu PASSED in 104.4s Stats over 2 runs: max = 104.4s, min = 45.5s, avg = 75.0s, dev = 29.5s //tensorflow/python/kernel_tests/nn_ops:conv2d_backprop_filter_grad_test_cpu PASSED in 69.6s Stats over 2 runs: max = 69.6s, min = 9.9s, avg = 39.7s, dev = 29.8s //tensorflow/compiler/tests:spacetobatch_op_test_cpu PASSED in 9.6s Stats over 3 runs: max = 9.6s, min = 9.1s, avg = 9.2s, dev = 0.3s //tensorflow/compiler/tests:spacetobatch_op_test_cpu_mlir_bridge_test PASSED in 13.6s Stats over 3 runs: max = 13.6s, min = 11.4s, avg = 12.1s, dev = 1.0s //tensorflow/compiler/xla/tests:triangular_solve_test_cpu PASSED in 96.9s Stats over 3 runs: max = 96.9s, min = 76.3s, avg = 86.2s, dev = 8.4s //tensorflow/core/data/service:thread_safe_buffer_test PASSED in 0.9s Stats over 3 runs: max = 0.9s, min = 0.4s, avg = 0.6s, dev = 0.2s //tensorflow/python/data/experimental/kernel_tests/service:multi_process_cluster_test PASSED in 16.1s Stats over 3 runs: max = 16.1s, min = 11.7s, avg = 14.6s, dev = 2.0s //tensorflow/python/data/kernel_tests:unique_test PASSED in 15.7s Stats over 3 runs: max = 15.7s, min = 12.2s, avg = 13.7s, dev = 1.5s //tensorflow/python/kernel_tests/array_ops:gather_op_test_cpu PASSED in 50.3s Stats over 3 runs: max = 50.3s, min = 28.5s, avg = 36.2s, dev = 10.0s //tensorflow/python/kernel_tests/array_ops:weights_broadcast_test PASSED in 9.2s Stats over 3 runs: max = 9.2s, min = 8.7s, avg = 8.9s, dev = 0.2s //tensorflow/python/kernel_tests/distributions:util_test_cpu PASSED in 12.3s Stats over 3 runs: max = 12.3s, min = 10.7s, avg = 11.3s, dev = 0.7s //tensorflow/python/kernel_tests/linalg:matrix_triangular_solve_op_test_cpu PASSED in 574.6s Stats over 3 runs: max = 574.6s, min = 8.5s, avg = 197.3s, dev = 266.8s //tensorflow/python/kernel_tests/random:multinomial_op_big_test_cpu PASSED in 17.6s Stats over 3 runs: max = 17.6s, min = 10.9s, avg = 13.3s, dev = 3.0s //tensorflow/compiler/xla/tests:dynamic_ops_test_cpu PASSED in 16.8s Stats over 4 runs: max = 16.8s, min = 12.4s, avg = 15.6s, dev = 1.8s //tensorflow/core/kernels:example_parsing_ops_test PASSED in 0.7s Stats over 4 runs: max = 0.7s, min = 0.6s, avg = 0.6s, dev = 0.0s //tensorflow/python:nn_batchnorm_test_cpu PASSED in 18.1s Stats over 4 runs: max = 18.1s, min = 13.8s, avg = 15.4s, dev = 1.6s //tensorflow/python:nn_fused_batchnorm_d9m_test_cpu PASSED in 18.4s Stats over 4 runs: max = 18.4s, min = 15.8s, avg = 17.3s, dev = 1.1s //tensorflow/python/data/experimental/kernel_tests:auto_shard_dataset_test PASSED in 33.1s Stats over 4 runs: max = 33.1s, min = 15.8s, avg = 24.9s, dev = 6.5s //tensorflow/python/data/experimental/kernel_tests:map_and_batch_test PASSED in 34.1s Stats over 4 runs: max = 34.1s, min = 22.5s, avg = 26.3s, dev = 4.6s //tensorflow/python/data/experimental/kernel_tests:parse_example_dataset_test PASSED in 19.5s Stats over 4 runs: max = 19.5s, min = 10.3s, avg = 14.8s, dev = 4.5s //tensorflow/python/data/experimental/kernel_tests:rebatch_dataset_test PASSED in 20.1s Stats over 4 runs: max = 20.1s, min = 9.2s, avg = 13.0s, dev = 4.3s //tensorflow/python/data/experimental/kernel_tests:sql_dataset_test PASSED in 56.5s Stats over 4 runs: max = 56.5s, min = 45.0s, avg = 50.7s, dev = 4.9s //tensorflow/python/data/experimental/kernel_tests/service:cross_trainer_cache_ft_test PASSED in 11.5s Stats over 4 runs: max = 11.5s, min = 7.8s, avg = 9.5s, dev = 1.6s //tensorflow/python/data/experimental/kernel_tests/service:distributed_save_test PASSED in 46.5s Stats over 4 runs: max = 46.5s, min = 22.8s, avg = 35.5s, dev = 10.5s //tensorflow/python/data/kernel_tests:batch_test PASSED in 41.1s Stats over 4 runs: max = 41.1s, min = 30.3s, avg = 33.2s, dev = 4.6s //tensorflow/python/data/kernel_tests:fixed_length_record_dataset_test PASSED in 22.4s Stats over 4 runs: max = 22.4s, min = 11.2s, avg = 17.0s, dev = 5.2s //tensorflow/python/data/kernel_tests:from_generator_test PASSED in 34.9s Stats over 4 runs: max = 34.9s, min = 18.6s, avg = 25.4s, dev = 6.1s //tensorflow/python/data/kernel_tests:group_by_window_test PASSED in 27.7s Stats over 4 runs: max = 27.7s, min = 7.5s, avg = 16.4s, dev = 8.3s //tensorflow/python/data/kernel_tests:ragged_batch_test PASSED in 25.6s Stats over 4 runs: max = 25.6s, min = 21.8s, avg = 24.1s, dev = 1.4s //tensorflow/python/data/kernel_tests:skip_test PASSED in 34.4s Stats over 4 runs: max = 34.4s, min = 23.3s, avg = 28.9s, dev = 4.9s //tensorflow/python/data/kernel_tests:take_test PASSED in 37.2s Stats over 4 runs: max = 37.2s, min = 31.3s, avg = 33.5s, dev = 2.4s //tensorflow/python/data/kernel_tests:take_while_test PASSED in 26.7s Stats over 4 runs: max = 26.7s, min = 23.8s, avg = 25.3s, dev = 1.1s //tensorflow/python/data/kernel_tests:text_line_dataset_test PASSED in 18.9s Stats over 4 runs: max = 18.9s, min = 13.3s, avg = 15.8s, dev = 2.2s //tensorflow/python/data/kernel_tests:zip_test PASSED in 15.0s Stats over 4 runs: max = 15.0s, min = 12.1s, avg = 13.2s, dev = 1.2s //tensorflow/python/debug/lib:dumping_callback_test_cpu PASSED in 16.2s Stats over 4 runs: max = 16.2s, min = 15.3s, avg = 15.8s, dev = 0.3s //tensorflow/python/distribute:cross_device_ops_test_2gpu PASSED in 34.1s Stats over 4 runs: max = 34.1s, min = 25.5s, avg = 30.2s, dev = 3.6s //tensorflow/python/distribute:cross_device_ops_test_cpu PASSED in 32.5s Stats over 4 runs: max = 32.5s, min = 25.0s, avg = 27.7s, dev = 3.0s //tensorflow/python/framework:convert_to_constants_test PASSED in 25.5s Stats over 4 runs: max = 25.5s, min = 17.3s, avg = 20.8s, dev = 3.0s //tensorflow/python/kernel_tests:collective_ops_test_2gpu PASSED in 41.4s Stats over 4 runs: max = 41.4s, min = 39.5s, avg = 40.0s, dev = 0.8s //tensorflow/python/kernel_tests:collective_ops_test_cpu PASSED in 32.2s Stats over 4 runs: max = 32.2s, min = 31.0s, avg = 31.9s, dev = 0.5s //tensorflow/python/kernel_tests/array_ops:concat_op_test_cpu PASSED in 17.5s Stats over 4 runs: max = 17.5s, min = 15.8s, avg = 16.7s, dev = 0.7s //tensorflow/python/kernel_tests/array_ops:init_ops_test_cpu PASSED in 77.2s Stats over 4 runs: max = 77.2s, min = 27.4s, avg = 50.8s, dev = 19.8s //tensorflow/python/kernel_tests/array_ops:split_op_test_cpu PASSED in 35.1s Stats over 4 runs: max = 35.1s, min = 9.2s, avg = 18.6s, dev = 10.5s //tensorflow/python/kernel_tests/linalg:einsum_op_test_cpu PASSED in 85.7s Stats over 4 runs: max = 85.7s, min = 18.3s, avg = 46.9s, dev = 26.5s //tensorflow/python/kernel_tests/linalg:linear_operator_lower_triangular_test_cpu PASSED in 32.1s Stats over 4 runs: max = 32.1s, min = 27.6s, avg = 29.2s, dev = 1.7s //tensorflow/python/kernel_tests/nn_ops:conv_ops_test_cpu PASSED in 56.3s Stats over 4 runs: max = 56.3s, min = 39.3s, avg = 48.0s, dev = 6.0s //tensorflow/python/kernel_tests/random:random_gamma_test_cpu PASSED in 100.7s Stats over 4 runs: max = 100.7s, min = 8.4s, avg = 49.9s, dev = 42.0s //tensorflow/python/kernel_tests/signal:window_ops_test_cpu PASSED in 23.8s Stats over 4 runs: max = 23.8s, min = 19.2s, avg = 20.9s, dev = 1.7s //tensorflow/python/ops/ragged:ragged_gather_op_test PASSED in 90.2s Stats over 4 runs: max = 90.2s, min = 31.0s, avg = 58.1s, dev = 21.6s //tensorflow/python/ops/ragged:ragged_getitem_test PASSED in 61.3s Stats over 4 runs: max = 61.3s, min = 57.3s, avg = 58.8s, dev = 1.6s //tensorflow/compiler/tests:async_comp_test_cpu PASSED in 7.3s Stats over 5 runs: max = 7.3s, min = 6.4s, avg = 6.9s, dev = 0.3s //tensorflow/compiler/tests:conv3d_test_cpu PASSED in 11.3s Stats over 5 runs: max = 11.3s, min = 6.4s, avg = 8.7s, dev = 2.1s //tensorflow/compiler/tests:conv3d_test_cpu_mlir_bridge_test PASSED in 13.3s Stats over 5 runs: max = 13.3s, min = 7.5s, avg = 10.0s, dev = 2.6s //tensorflow/compiler/tests:depthwise_conv_op_test_cpu PASSED in 13.6s Stats over 5 runs: max = 13.6s, min = 8.3s, avg = 10.2s, dev = 2.2s //tensorflow/compiler/tests:depthwise_conv_op_test_cpu_mlir_bridge_test PASSED in 13.6s Stats over 5 runs: max = 13.6s, min = 8.3s, avg = 10.5s, dev = 2.0s //tensorflow/compiler/tests:fused_batchnorm_test_cpu PASSED in 9.6s Stats over 5 runs: max = 9.6s, min = 8.6s, avg = 9.1s, dev = 0.3s //tensorflow/compiler/tests:fused_batchnorm_test_cpu_mlir_bridge_test PASSED in 8.9s Stats over 5 runs: max = 8.9s, min = 7.7s, avg = 8.4s, dev = 0.4s //tensorflow/compiler/tests:image_ops_jit_compile_test_cpu PASSED in 8.3s Stats over 5 runs: max = 8.3s, min = 7.5s, avg = 7.9s, dev = 0.3s //tensorflow/compiler/tests:reduce_ops_test_cpu PASSED in 10.5s Stats over 5 runs: max = 10.5s, min = 9.5s, avg = 9.8s, dev = 0.4s //tensorflow/compiler/tests:reduce_ops_test_cpu_mlir_bridge_test PASSED in 12.7s Stats over 5 runs: max = 12.7s, min = 10.4s, avg = 11.6s, dev = 0.9s //tensorflow/compiler/tests:repeat_op_test_cpu PASSED in 10.3s Stats over 5 runs: max = 10.3s, min = 6.9s, avg = 8.0s, dev = 1.2s //tensorflow/compiler/tests:repeat_op_test_cpu_mlir_bridge_test PASSED in 7.3s Stats over 5 runs: max = 7.3s, min = 6.4s, avg = 6.7s, dev = 0.3s //tensorflow/compiler/tests:special_math_test_cpu PASSED in 113.3s Stats over 5 runs: max = 113.3s, min = 12.3s, avg = 47.3s, dev = 35.2s //tensorflow/compiler/tests:special_math_test_cpu_mlir_bridge_test PASSED in 104.0s Stats over 5 runs: max = 104.0s, min = 15.6s, avg = 46.8s, dev = 30.7s //tensorflow/compiler/xla/client/lib:self_adjoint_eig_test_cpu PASSED in 28.8s Stats over 5 runs: max = 28.8s, min = 13.6s, avg = 22.4s, dev = 6.5s //tensorflow/core/grappler/optimizers:constant_folding_test PASSED in 5.4s Stats over 5 runs: max = 5.4s, min = 3.3s, avg = 4.1s, dev = 0.9s //tensorflow/dtensor/python/tests:layout_propagation_test_cpu PASSED in 10.0s Stats over 5 runs: max = 10.0s, min = 9.6s, avg = 9.9s, dev = 0.2s //tensorflow/python/distribute:mirrored_strategy_test_2gpu PASSED in 12.6s Stats over 5 runs: max = 12.6s, min = 10.4s, avg = 11.4s, dev = 0.9s //tensorflow/python/distribute:mirrored_strategy_test_cpu PASSED in 10.8s Stats over 5 runs: max = 10.8s, min = 9.6s, avg = 10.2s, dev = 0.4s //tensorflow/python/distribute:moving_averages_test_2gpu PASSED in 21.1s Stats over 5 runs: max = 21.1s, min = 16.1s, avg = 18.8s, dev = 1.7s //tensorflow/python/distribute:moving_averages_test_cpu PASSED in 22.8s Stats over 5 runs: max = 22.8s, min = 14.8s, avg = 19.1s, dev = 3.1s //tensorflow/python/distribute:vars_test_2gpu PASSED in 23.9s Stats over 5 runs: max = 23.9s, min = 15.8s, avg = 19.0s, dev = 2.7s //tensorflow/python/distribute:vars_test_cpu PASSED in 22.1s Stats over 5 runs: max = 22.1s, min = 16.0s, avg = 18.3s, dev = 2.2s //tensorflow/python/eager:device_placement_test_cpu PASSED in 9.2s Stats over 5 runs: max = 9.2s, min = 8.0s, avg = 8.7s, dev = 0.4s //tensorflow/python/eager:forwardprop_test_cpu PASSED in 110.1s Stats over 5 runs: max = 110.1s, min = 15.2s, avg = 61.2s, dev = 30.8s //tensorflow/python/eager/polymorphic_function:gradients_test_cpu PASSED in 12.9s Stats over 5 runs: max = 12.9s, min = 6.3s, avg = 9.3s, dev = 2.5s //tensorflow/python/kernel_tests/linalg:cholesky_op_test_cpu PASSED in 78.3s Stats over 5 runs: max = 78.3s, min = 47.0s, avg = 60.6s, dev = 12.1s //tensorflow/python/kernel_tests/linalg:linear_operator_adjoint_test_cpu PASSED in 31.7s Stats over 5 runs: max = 31.7s, min = 27.5s, avg = 29.6s, dev = 1.6s //tensorflow/python/kernel_tests/linalg:linear_operator_composition_test_cpu PASSED in 47.7s Stats over 5 runs: max = 47.7s, min = 42.9s, avg = 45.7s, dev = 1.7s //tensorflow/python/kernel_tests/linalg:linear_operator_diag_test_cpu PASSED in 24.1s Stats over 5 runs: max = 24.1s, min = 20.6s, avg = 22.6s, dev = 1.2s //tensorflow/python/kernel_tests/linalg:linear_operator_full_matrix_test_cpu PASSED in 36.6s Stats over 5 runs: max = 36.6s, min = 30.5s, avg = 32.8s, dev = 2.4s //tensorflow/python/kernel_tests/linalg:linear_operator_householder_test_cpu PASSED in 29.0s Stats over 5 runs: max = 29.0s, min = 21.1s, avg = 25.7s, dev = 2.8s //tensorflow/python/kernel_tests/linalg:linear_operator_identity_test_cpu PASSED in 49.7s Stats over 5 runs: max = 49.7s, min = 37.7s, avg = 42.9s, dev = 4.6s //tensorflow/python/kernel_tests/linalg:linear_operator_inversion_test_cpu PASSED in 24.6s Stats over 5 runs: max = 24.6s, min = 22.0s, avg = 22.8s, dev = 0.9s //tensorflow/python/kernel_tests/linalg:linear_operator_permutation_test_cpu PASSED in 19.9s Stats over 5 runs: max = 19.9s, min = 18.2s, avg = 18.9s, dev = 0.6s //tensorflow/python/kernel_tests/linalg:linear_operator_toeplitz_test_cpu PASSED in 15.4s Stats over 5 runs: max = 15.4s, min = 12.7s, avg = 13.7s, dev = 1.0s //tensorflow/python/kernel_tests/linalg:linear_operator_tridiag_test_cpu PASSED in 66.2s Stats over 5 runs: max = 66.2s, min = 64.1s, avg = 65.2s, dev = 0.9s //tensorflow/python/kernel_tests/linalg:linear_operator_util_test_cpu PASSED in 7.6s Stats over 5 runs: max = 7.6s, min = 6.6s, avg = 7.1s, dev = 0.3s //tensorflow/python/kernel_tests/linalg:linear_operator_zeros_test_cpu PASSED in 18.0s Stats over 5 runs: max = 18.0s, min = 11.8s, avg = 14.5s, dev = 2.2s //tensorflow/python/kernel_tests/nn_ops:fractional_avg_pool_op_test PASSED in 15.4s Stats over 5 runs: max = 15.4s, min = 8.8s, avg = 10.6s, dev = 2.5s //tensorflow/python/kernel_tests/nn_ops:fractional_max_pool_op_test PASSED in 14.1s Stats over 5 runs: max = 14.1s, min = 8.0s, avg = 9.3s, dev = 2.4s //tensorflow/python/kernel_tests/sparse_ops:sparse_ops_test_cpu PASSED in 24.9s Stats over 5 runs: max = 24.9s, min = 7.3s, avg = 11.4s, dev = 6.7s //tensorflow/python/ops/parallel_for:math_test_cpu PASSED in 80.9s Stats over 5 runs: max = 80.9s, min = 30.1s, avg = 52.0s, dev = 18.8s //tensorflow/compiler/tests:scan_ops_test_cpu PASSED in 13.8s Stats over 6 runs: max = 13.8s, min = 10.0s, avg = 11.6s, dev = 1.2s //tensorflow/compiler/tests:scan_ops_test_cpu_mlir_bridge_test PASSED in 15.7s Stats over 6 runs: max = 15.7s, min = 10.3s, avg = 13.5s, dev = 1.6s //tensorflow/python:accumulate_n_benchmark_cpu PASSED in 9.1s Stats over 6 runs: max = 9.1s, min = 7.9s, avg = 8.4s, dev = 0.5s //tensorflow/python/data/experimental/kernel_tests:make_batched_features_dataset_test PASSED in 33.2s Stats over 6 runs: max = 33.2s, min = 7.1s, avg = 18.8s, dev = 11.7s //tensorflow/python/kernel_tests/array_ops:diag_op_test_cpu PASSED in 59.9s Stats over 6 runs: max = 59.9s, min = 10.7s, avg = 21.3s, dev = 17.4s //tensorflow/python/kernel_tests/math_ops:reduction_ops_test_cpu PASSED in 48.5s Stats over 6 runs: max = 48.5s, min = 21.9s, avg = 32.6s, dev = 8.4s //tensorflow/python/distribute/experimental/rpc:rpc_ops_test PASSED in 16.9s Stats over 7 runs: max = 16.9s, min = 12.1s, avg = 13.7s, dev = 2.0s //tensorflow/compiler/tests:matrix_diag_ops_test_cpu PASSED in 55.2s Stats over 8 runs: max = 55.2s, min = 6.1s, avg = 21.8s, dev = 16.6s //tensorflow/compiler/tests:matrix_diag_ops_test_cpu_mlir_bridge_test PASSED in 61.4s Stats over 8 runs: max = 61.4s, min = 7.1s, avg = 28.5s, dev = 20.4s //tensorflow/python/data/experimental/kernel_tests:csv_dataset_test PASSED in 25.5s Stats over 8 runs: max = 25.5s, min = 6.9s, avg = 14.4s, dev = 6.9s //tensorflow/python/data/experimental/kernel_tests:parallel_interleave_test PASSED in 30.6s Stats over 8 runs: max = 30.6s, min = 9.0s, avg = 18.7s, dev = 6.9s //tensorflow/python/data/experimental/kernel_tests/service:coordinated_read_ft_test PASSED in 44.7s Stats over 8 runs: max = 44.7s, min = 12.2s, avg = 27.6s, dev = 13.5s //tensorflow/python/data/experimental/kernel_tests/service:coordinated_read_test PASSED in 24.1s Stats over 8 runs: max = 24.1s, min = 7.7s, avg = 13.8s, dev = 6.7s //tensorflow/python/data/experimental/kernel_tests/service:cross_trainer_cache_test PASSED in 21.8s Stats over 8 runs: max = 21.8s, min = 7.0s, avg = 12.5s, dev = 5.8s //tensorflow/python/data/experimental/kernel_tests/service:fault_tolerance_test PASSED in 25.9s Stats over 8 runs: max = 25.9s, min = 4.4s, avg = 10.5s, dev = 6.5s //tensorflow/python/data/kernel_tests:filter_test PASSED in 21.1s Stats over 8 runs: max = 21.1s, min = 15.1s, avg = 17.5s, dev = 1.9s //tensorflow/python/data/kernel_tests:flat_map_test PASSED in 34.4s Stats over 8 runs: max = 34.4s, min = 17.5s, avg = 24.3s, dev = 5.7s //tensorflow/python/data/kernel_tests:shard_test PASSED in 21.2s Stats over 8 runs: max = 21.2s, min = 16.9s, avg = 20.0s, dev = 1.6s //tensorflow/python/data/kernel_tests:shuffle_test PASSED in 57.3s Stats over 8 runs: max = 57.3s, min = 30.0s, avg = 34.0s, dev = 8.8s //tensorflow/python/data/kernel_tests:tf_record_dataset_test PASSED in 30.9s Stats over 8 runs: max = 30.9s, min = 12.1s, avg = 19.5s, dev = 5.0s //tensorflow/python/distribute/failure_handling:failure_handler_test PASSED in 83.4s Stats over 8 runs: max = 83.4s, min = 31.8s, avg = 57.0s, dev = 15.9s //tensorflow/python/kernel_tests/linalg:linalg_ops_test_cpu PASSED in 45.5s Stats over 8 runs: max = 45.5s, min = 25.1s, avg = 35.8s, dev = 6.2s //tensorflow/python/kernel_tests/linalg:linear_operator_block_diag_test_cpu PASSED in 79.4s Stats over 8 runs: max = 79.4s, min = 58.7s, avg = 66.4s, dev = 6.6s //tensorflow/python/kernel_tests/linalg:linear_operator_block_lower_triangular_test_cpu PASSED in 57.7s Stats over 8 runs: max = 57.7s, min = 33.0s, avg = 46.5s, dev = 7.4s //tensorflow/python/kernel_tests/nn_ops:depthwise_conv_op_d9m_test_cpu PASSED in 96.2s Stats over 8 runs: max = 96.2s, min = 7.5s, avg = 22.6s, dev = 29.4s //tensorflow/python/kernel_tests/nn_ops:depthwise_conv_op_test_cpu PASSED in 6.9s Stats over 8 runs: max = 6.9s, min = 6.2s, avg = 6.5s, dev = 0.2s //tensorflow/python/kernel_tests/signal:fft_ops_test_cpu PASSED in 20.9s Stats over 8 runs: max = 20.9s, min = 8.4s, avg = 13.0s, dev = 4.8s //tensorflow/python/ops/ragged:dynamic_ragged_shape_test PASSED in 51.1s Stats over 8 runs: max = 51.1s, min = 35.3s, avg = 39.7s, dev = 5.3s //tensorflow/python/ops/ragged:ragged_tensor_test PASSED in 23.3s Stats over 8 runs: max = 23.3s, min = 10.9s, avg = 15.5s, dev = 3.6s //tensorflow/python/distribute/failure_handling:gce_failure_handler_test FLAKY, failed in 1 out of 9 in 116.4s Stats over 9 runs: max = 116.4s, min = 11.5s, avg = 49.7s, dev = 42.5s /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_7_of_8/test_attempts/attempt_1.log //tensorflow/compiler/tests:bincount_op_test_cpu PASSED in 7.1s Stats over 10 runs: max = 7.1s, min = 4.9s, avg = 6.0s, dev = 0.6s //tensorflow/compiler/tests:conv2d_test_cpu PASSED in 9.4s Stats over 10 runs: max = 9.4s, min = 5.4s, avg = 7.3s, dev = 1.2s //tensorflow/compiler/tests:conv2d_test_cpu_mlir_bridge_test PASSED in 7.9s Stats over 10 runs: max = 7.9s, min = 7.0s, avg = 7.4s, dev = 0.3s //tensorflow/compiler/tests:random_ops_test_cpu PASSED in 21.5s Stats over 10 runs: max = 21.5s, min = 13.1s, avg = 16.9s, dev = 2.3s //tensorflow/compiler/tests:random_ops_test_cpu_mlir_bridge_test PASSED in 20.6s Stats over 10 runs: max = 20.6s, min = 13.4s, avg = 16.7s, dev = 2.4s //tensorflow/compiler/tests:stateless_random_ops_test_cpu PASSED in 72.6s Stats over 10 runs: max = 72.6s, min = 38.4s, avg = 56.6s, dev = 11.6s //tensorflow/compiler/tests:stateless_random_ops_test_cpu_mlir_bridge_test PASSED in 62.5s Stats over 10 runs: max = 62.5s, min = 34.3s, avg = 49.7s, dev = 9.3s //tensorflow/compiler/xla/client/lib:svd_test_cpu PASSED in 72.4s Stats over 10 runs: max = 72.4s, min = 11.1s, avg = 28.6s, dev = 23.3s //tensorflow/compiler/xla/client/lib:tridiagonal_test_cpu PASSED in 12.7s Stats over 10 runs: max = 12.7s, min = 10.4s, avg = 11.4s, dev = 0.6s //tensorflow/compiler/xla/service/cpu:cpu_runtime_test PASSED in 16.9s Stats over 10 runs: max = 16.9s, min = 1.0s, avg = 10.3s, dev = 5.0s //tensorflow/python:special_math_ops_test_cpu PASSED in 60.5s Stats over 10 runs: max = 60.5s, min = 7.2s, avg = 16.2s, dev = 15.1s //tensorflow/python/data/kernel_tests:rejection_resample_test PASSED in 23.0s Stats over 10 runs: max = 23.0s, min = 9.9s, avg = 14.9s, dev = 4.4s //tensorflow/python/distribute:input_lib_test_2gpu PASSED in 29.8s Stats over 10 runs: max = 29.8s, min = 20.9s, avg = 25.6s, dev = 2.9s //tensorflow/python/distribute:input_lib_test_cpu PASSED in 32.9s Stats over 10 runs: max = 32.9s, min = 19.3s, avg = 23.6s, dev = 3.8s //tensorflow/python/distribute:input_lib_type_spec_test_2gpu PASSED in 17.3s Stats over 10 runs: max = 17.3s, min = 7.8s, avg = 12.1s, dev = 3.4s //tensorflow/python/distribute:input_lib_type_spec_test_cpu PASSED in 21.4s Stats over 10 runs: max = 21.4s, min = 9.7s, avg = 15.3s, dev = 4.4s //tensorflow/python/framework:config_vgpu_test_2gpu PASSED in 7.5s Stats over 10 runs: max = 7.5s, min = 5.6s, avg = 6.8s, dev = 0.7s //tensorflow/python/framework:config_vgpu_test_cpu PASSED in 7.0s Stats over 10 runs: max = 7.0s, min = 6.4s, avg = 6.7s, dev = 0.2s //tensorflow/python/framework:function_test_cpu PASSED in 54.8s Stats over 10 runs: max = 54.8s, min = 4.6s, avg = 11.3s, dev = 14.7s //tensorflow/python/grappler:cluster_test_cpu PASSED in 8.3s Stats over 10 runs: max = 8.3s, min = 7.2s, avg = 7.6s, dev = 0.4s //tensorflow/python/kernel_tests/array_ops:array_ops_test_cpu PASSED in 17.3s Stats over 10 runs: max = 17.3s, min = 7.8s, avg = 11.9s, dev = 3.0s //tensorflow/python/kernel_tests/array_ops:inplace_ops_test_cpu PASSED in 7.9s Stats over 10 runs: max = 7.9s, min = 3.2s, avg = 5.1s, dev = 1.8s //tensorflow/python/kernel_tests/data_structures:tensor_array_ops_test_cpu PASSED in 11.4s Stats over 10 runs: max = 11.4s, min = 6.9s, avg = 9.1s, dev = 1.5s //tensorflow/python/kernel_tests/linalg:linear_operator_low_rank_update_test_cpu PASSED in 63.1s Stats over 10 runs: max = 63.1s, min = 56.8s, avg = 58.9s, dev = 1.8s //tensorflow/python/kernel_tests/linalg:tridiagonal_matmul_op_test_cpu PASSED in 118.2s Stats over 10 runs: max = 118.2s, min = 4.9s, avg = 17.7s, dev = 33.5s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_ops_test_cpu PASSED in 40.1s Stats over 10 runs: max = 40.1s, min = 9.9s, avg = 24.0s, dev = 9.6s //tensorflow/python/kernel_tests/math_ops:segment_reduction_ops_test_cpu PASSED in 26.3s Stats over 10 runs: max = 26.3s, min = 7.2s, avg = 15.4s, dev = 7.3s //tensorflow/python/kernel_tests/nn_ops:pooling_ops_test_cpu PASSED in 29.2s Stats over 10 runs: max = 29.2s, min = 9.7s, avg = 14.9s, dev = 6.8s //tensorflow/python/kernel_tests/nn_ops:rnn_test_cpu PASSED in 12.4s Stats over 10 runs: max = 12.4s, min = 8.3s, avg = 10.1s, dev = 1.4s //tensorflow/python/kernel_tests/random:random_index_shuffle_test PASSED in 10.7s Stats over 10 runs: max = 10.7s, min = 8.2s, avg = 9.5s, dev = 0.9s //tensorflow/python/kernel_tests/random:stateless_random_ops_test_cpu PASSED in 153.1s Stats over 10 runs: max = 153.1s, min = 18.1s, avg = 81.0s, dev = 61.1s //tensorflow/python/ops/ragged:ragged_tensor_supported_values_test PASSED in 16.6s Stats over 10 runs: max = 16.6s, min = 14.6s, avg = 15.6s, dev = 0.7s //tensorflow/python/saved_model:load_test_cpu PASSED in 49.4s Stats over 10 runs: max = 49.4s, min = 27.1s, avg = 31.5s, dev = 6.3s //tensorflow/dtensor/python/tests:input_util_test FLAKY, failed in 2 out of 10 in 30.0s Stats over 10 runs: max = 30.0s, min = 16.9s, avg = 21.4s, dev = 4.0s /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 /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_2.log //tensorflow/compiler/tests:fft_test_cpu PASSED in 33.6s Stats over 12 runs: max = 33.6s, min = 19.8s, avg = 25.7s, dev = 5.4s //tensorflow/compiler/xla/service:triangular_solve_expander_test PASSED in 4.3s Stats over 12 runs: max = 4.3s, min = 2.2s, avg = 3.2s, dev = 0.7s //tensorflow/python/data/experimental/kernel_tests:group_by_reducer_test PASSED in 24.4s Stats over 12 runs: max = 24.4s, min = 4.2s, avg = 12.5s, dev = 6.0s //tensorflow/python/data/kernel_tests:choose_from_datasets_test PASSED in 12.0s Stats over 12 runs: max = 12.0s, min = 7.4s, avg = 9.2s, dev = 1.3s //tensorflow/python/data/kernel_tests:memory_cleanup_test_cpu PASSED in 12.0s Stats over 12 runs: max = 12.0s, min = 7.3s, avg = 9.5s, dev = 1.7s //tensorflow/python/distribute:multi_process_runner_test_2gpu PASSED in 225.5s Stats over 12 runs: max = 225.5s, min = 13.2s, avg = 51.0s, dev = 58.7s //tensorflow/python/distribute:multi_process_runner_test_cpu PASSED in 223.2s Stats over 12 runs: max = 223.2s, min = 12.0s, avg = 49.3s, dev = 58.3s //tensorflow/python/eager/polymorphic_function:polymorphic_function_test_cpu PASSED in 19.5s Stats over 15 runs: max = 19.5s, min = 13.0s, avg = 15.6s, dev = 1.7s //tensorflow/python/kernel_tests/linalg:linear_operator_circulant_test_cpu PASSED in 99.0s Stats over 15 runs: max = 99.0s, min = 75.4s, avg = 88.7s, dev = 7.3s //tensorflow/python/kernel_tests/nn_ops:rnn_cell_test_cpu PASSED in 46.1s Stats over 15 runs: max = 46.1s, min = 8.1s, avg = 14.4s, dev = 9.4s //tensorflow/compiler/tests:ftrl_test_cpu PASSED in 8.3s Stats over 16 runs: max = 8.3s, min = 3.8s, avg = 5.8s, dev = 1.2s //tensorflow/compiler/tests:ternary_ops_test_cpu PASSED in 11.3s Stats over 16 runs: max = 11.3s, min = 5.3s, avg = 7.7s, dev = 1.5s //tensorflow/compiler/tests:ternary_ops_test_cpu_mlir_bridge_test PASSED in 11.1s Stats over 16 runs: max = 11.1s, min = 3.2s, avg = 7.2s, dev = 2.2s //tensorflow/python:image_ops_test_cpu PASSED in 21.0s Stats over 16 runs: max = 21.0s, min = 8.9s, avg = 15.4s, dev = 3.1s //tensorflow/python/data/experimental/kernel_tests/service:dynamic_sharding_test PASSED in 13.1s Stats over 16 runs: max = 13.1s, min = 3.7s, avg = 8.1s, dev = 3.0s //tensorflow/python/data/experimental/kernel_tests/service:worker_tags_test PASSED in 36.9s Stats over 16 runs: max = 36.9s, min = 7.9s, avg = 18.3s, dev = 8.1s //tensorflow/python/data/kernel_tests:snapshot_test PASSED in 22.7s Stats over 16 runs: max = 22.7s, min = 7.2s, avg = 14.3s, dev = 4.1s //tensorflow/python/kernel_tests/control_flow:control_flow_ops_py_test_cpu PASSED in 31.6s Stats over 16 runs: max = 31.6s, min = 9.3s, avg = 12.3s, dev = 5.2s //tensorflow/python/kernel_tests/linalg:matrix_exponential_op_test PASSED in 9.6s Stats over 16 runs: max = 9.6s, min = 4.5s, avg = 6.7s, dev = 1.6s //tensorflow/python/kernel_tests/signal:dct_ops_test_cpu PASSED in 11.8s Stats over 16 runs: max = 11.8s, min = 8.5s, avg = 9.9s, dev = 0.8s //tensorflow/python/ops/parallel_for:control_flow_ops_test_cpu PASSED in 71.0s Stats over 16 runs: max = 71.0s, min = 17.4s, avg = 26.6s, dev = 12.3s //tensorflow/python/data/experimental/kernel_tests/service:distributed_save_ft_test PASSED in 14.3s Stats over 17 runs: max = 14.3s, min = 6.3s, avg = 9.5s, dev = 2.6s //tensorflow/python/data/kernel_tests:map_test PASSED in 48.0s Stats over 19 runs: max = 48.0s, min = 11.7s, avg = 19.0s, dev = 7.7s //tensorflow/compiler/tests:pooling_ops_3d_test_cpu PASSED in 6.7s Stats over 20 runs: max = 6.7s, min = 3.4s, avg = 4.7s, dev = 1.2s //tensorflow/compiler/tests:pooling_ops_3d_test_cpu_mlir_bridge_test PASSED in 7.5s Stats over 20 runs: max = 7.5s, min = 3.9s, avg = 5.8s, dev = 1.2s //tensorflow/compiler/tests:pooling_ops_test_cpu PASSED in 12.1s Stats over 20 runs: max = 12.1s, min = 3.1s, avg = 5.9s, dev = 2.5s //tensorflow/compiler/tests:pooling_ops_test_cpu_mlir_bridge_test PASSED in 12.5s Stats over 20 runs: max = 12.5s, min = 5.2s, avg = 6.8s, dev = 1.5s //tensorflow/compiler/xla/tests:convolution_dimension_numbers_test_cpu PASSED in 13.7s Stats over 20 runs: max = 13.7s, min = 10.0s, avg = 11.7s, dev = 0.7s //tensorflow/compiler/xla/tests:dot_operation_single_threaded_runtime_test_cpu PASSED in 23.9s Stats over 20 runs: max = 23.9s, min = 16.1s, avg = 19.6s, dev = 1.7s //tensorflow/compiler/xla/tests:dot_operation_test_cpu PASSED in 35.9s Stats over 20 runs: max = 35.9s, min = 15.0s, avg = 20.3s, dev = 4.9s //tensorflow/compiler/xla/tests:prng_test_cpu PASSED in 13.6s Stats over 20 runs: max = 13.6s, min = 8.4s, avg = 11.8s, dev = 1.4s //tensorflow/compiler/xla/tests:reduce_window_test_cpu PASSED in 51.0s Stats over 20 runs: max = 51.0s, min = 10.2s, avg = 24.8s, dev = 13.4s //tensorflow/python/autograph/tests:loop_control_flow_test PASSED in 24.7s Stats over 20 runs: max = 24.7s, min = 17.9s, avg = 21.2s, dev = 2.1s //tensorflow/python/kernel_tests:metrics_test PASSED in 51.1s Stats over 20 runs: max = 51.1s, min = 6.5s, avg = 21.1s, dev = 11.9s //tensorflow/python/kernel_tests/array_ops:matrix_band_part_op_test_cpu PASSED in 8.7s Stats over 20 runs: max = 8.7s, min = 3.1s, avg = 5.5s, dev = 1.6s //tensorflow/python/kernel_tests/data_structures:barrier_ops_test PASSED in 13.9s Stats over 20 runs: max = 13.9s, min = 4.0s, avg = 7.5s, dev = 2.1s //tensorflow/python/kernel_tests/linalg:eig_op_test PASSED in 53.1s Stats over 20 runs: max = 53.1s, min = 6.6s, avg = 17.5s, dev = 15.4s //tensorflow/python/kernel_tests/linalg:linalg_grad_test_cpu PASSED in 89.3s Stats over 20 runs: max = 89.3s, min = 23.9s, avg = 44.6s, dev = 17.8s //tensorflow/python/kernel_tests/linalg:norm_op_test_cpu PASSED in 7.8s Stats over 20 runs: max = 7.8s, min = 3.5s, avg = 4.8s, dev = 1.3s //tensorflow/python/kernel_tests/linalg:normalize_op_test_cpu PASSED in 24.6s Stats over 20 runs: max = 24.6s, min = 8.3s, avg = 14.7s, dev = 5.1s //tensorflow/python/kernel_tests/linalg:qr_op_test_cpu PASSED in 159.6s Stats over 20 runs: max = 159.6s, min = 31.5s, avg = 88.3s, dev = 41.8s //tensorflow/python/kernel_tests/linalg:self_adjoint_eig_op_test_cpu PASSED in 31.7s Stats over 20 runs: max = 31.7s, min = 8.5s, avg = 14.7s, dev = 6.6s //tensorflow/python/kernel_tests/math_ops:batch_matmul_op_test_cpu PASSED in 22.9s Stats over 20 runs: max = 22.9s, min = 7.4s, avg = 14.1s, dev = 5.8s //tensorflow/python/kernel_tests/math_ops:matmul_op_test_cpu PASSED in 15.7s Stats over 20 runs: max = 15.7s, min = 10.8s, avg = 13.1s, dev = 1.3s //tensorflow/python/kernel_tests/math_ops:tensordot_op_test_cpu PASSED in 79.1s Stats over 20 runs: max = 79.1s, min = 7.0s, avg = 34.3s, dev = 23.8s //tensorflow/python/kernel_tests/nn_ops:embedding_ops_test_cpu PASSED in 16.1s Stats over 20 runs: max = 16.1s, min = 8.6s, avg = 11.1s, dev = 1.9s //tensorflow/python/data/experimental/kernel_tests/service:local_workers_test PASSED in 20.6s Stats over 24 runs: max = 20.6s, min = 8.0s, avg = 14.3s, dev = 3.3s //tensorflow/python/data/kernel_tests:interleave_test PASSED in 20.6s Stats over 24 runs: max = 20.6s, min = 7.6s, avg = 13.0s, dev = 3.8s //tensorflow/python/data/kernel_tests:sample_from_datasets_test PASSED in 17.4s Stats over 24 runs: max = 17.4s, min = 3.4s, avg = 9.0s, dev = 3.8s //tensorflow/compiler/xla/tests:array_elementwise_ops_test_cpu PASSED in 14.9s Stats over 25 runs: max = 14.9s, min = 11.8s, avg = 12.9s, dev = 0.9s //tensorflow/compiler/xla/tests:select_and_scatter_test_cpu PASSED in 42.4s Stats over 25 runs: max = 42.4s, min = 10.0s, avg = 14.5s, dev = 7.7s //tensorflow/compiler/xla/tests:convolution_variants_test_cpu PASSED in 13.9s Stats over 30 runs: max = 13.9s, min = 10.9s, avg = 12.4s, dev = 0.9s //tensorflow/compiler/xla/tests:iota_test_cpu PASSED in 21.5s Stats over 30 runs: max = 21.5s, min = 16.0s, avg = 18.8s, dev = 1.4s //tensorflow/compiler/xla/tests:params_test_cpu PASSED in 17.9s Stats over 30 runs: max = 17.9s, min = 9.8s, avg = 12.9s, dev = 2.3s //tensorflow/compiler/xla/tests:reshape_test_cpu PASSED in 14.6s Stats over 30 runs: max = 14.6s, min = 9.2s, avg = 11.6s, dev = 1.2s //tensorflow/python/kernel_tests/nn_ops:conv_ops_3d_test_cpu PASSED in 14.7s Stats over 30 runs: max = 14.7s, min = 2.8s, avg = 6.8s, dev = 2.4s //tensorflow/compiler/xla/tests:reduce_test_cpu PASSED in 17.6s Stats over 31 runs: max = 17.6s, min = 12.0s, avg = 14.7s, dev = 1.8s //tensorflow/compiler/xla/tests:scalar_computations_test_cpu PASSED in 15.0s Stats over 32 runs: max = 15.0s, min = 11.2s, avg = 12.9s, dev = 0.9s //tensorflow/python/data/experimental/kernel_tests/service:auto_shard_test PASSED in 20.3s Stats over 32 runs: max = 20.3s, min = 3.7s, avg = 13.0s, dev = 4.1s //tensorflow/python/data/experimental/kernel_tests/service:data_service_ops_test PASSED in 31.2s Stats over 32 runs: max = 31.2s, min = 5.6s, avg = 11.8s, dev = 5.7s //tensorflow/compiler/xla/tests:batch_normalization_test_cpu PASSED in 18.4s Stats over 40 runs: max = 18.4s, min = 15.3s, avg = 16.6s, dev = 0.8s //tensorflow/compiler/xla/tests:bfloat16_test_cpu PASSED in 17.4s Stats over 40 runs: max = 17.4s, min = 11.5s, avg = 13.9s, dev = 1.5s //tensorflow/compiler/xla/tests:conv_depthwise_backprop_filter_test_cpu PASSED in 16.2s Stats over 40 runs: max = 16.2s, min = 13.8s, avg = 15.0s, dev = 0.6s //tensorflow/compiler/xla/tests:slice_test_cpu PASSED in 18.5s Stats over 40 runs: max = 18.5s, min = 11.1s, avg = 14.1s, dev = 1.7s //tensorflow/core/kernels:stochastic_cast_op_test PASSED in 1.8s Stats over 48 runs: max = 1.8s, min = 0.4s, avg = 0.7s, dev = 0.3s //tensorflow/compiler/mlir/quantization/tensorflow/python:quantize_model_test PASSED in 39.5s Stats over 50 runs: max = 39.5s, min = 19.5s, avg = 27.1s, dev = 5.5s //tensorflow/compiler/tests:sort_ops_test_cpu PASSED in 50.7s Stats over 50 runs: max = 50.7s, min = 3.0s, avg = 13.8s, dev = 9.4s //tensorflow/compiler/tests:sort_ops_test_cpu_mlir_bridge_test PASSED in 52.2s Stats over 50 runs: max = 52.2s, min = 3.7s, avg = 13.9s, dev = 10.4s //tensorflow/compiler/tests:unary_ops_test_cpu PASSED in 20.4s Stats over 50 runs: max = 20.4s, min = 6.8s, avg = 8.2s, dev = 2.8s //tensorflow/compiler/tests:unary_ops_test_cpu_mlir_bridge_test PASSED in 41.4s Stats over 50 runs: max = 41.4s, min = 3.1s, avg = 7.1s, dev = 6.8s //tensorflow/compiler/xla/tests:conv_depthwise_test_cpu PASSED in 19.3s Stats over 50 runs: max = 19.3s, min = 10.3s, avg = 14.5s, dev = 2.0s //tensorflow/compiler/xla/tests:convolution_test_1d_no_vmodule_cpu PASSED in 21.7s Stats over 50 runs: max = 21.7s, min = 14.0s, avg = 18.3s, dev = 1.6s //tensorflow/compiler/xla/tests:convolution_test_cpu PASSED in 22.5s Stats over 50 runs: max = 22.5s, min = 14.3s, avg = 18.7s, dev = 2.1s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_dense_mat_mul_grad_test_cpu PASSED in 21.8s Stats over 50 runs: max = 21.8s, min = 5.8s, avg = 12.1s, dev = 4.1s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_grad_test_cpu PASSED in 8.8s Stats over 50 runs: max = 8.8s, min = 2.9s, avg = 5.0s, dev = 1.3s //tensorflow/python/kernel_tests/linalg/sparse:csr_sparse_matrix_sparse_mat_mul_grad_test_cpu PASSED in 8.1s Stats over 50 runs: max = 8.1s, min = 3.2s, avg = 4.9s, dev = 1.1s //tensorflow/python/kernel_tests/math_ops:cwise_ops_binary_test_cpu PASSED in 29.0s Stats over 50 runs: max = 29.0s, min = 7.7s, avg = 15.2s, dev = 5.2s //tensorflow/python/kernel_tests/math_ops:cwise_ops_test_cpu PASSED in 11.5s Stats over 50 runs: max = 11.5s, min = 2.9s, avg = 4.4s, dev = 1.4s //tensorflow/python/kernel_tests/math_ops:cwise_ops_unary_test_cpu PASSED in 15.8s Stats over 50 runs: max = 15.8s, min = 2.8s, avg = 6.4s, dev = 3.1s Executed 3755 out of 3755 tests: 3755 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.