Created
September 18, 2019 03:30
-
-
Save taylanbil/8ff73e6b8cb26e550c8d47be1a844f48 to your computer and use it in GitHub Desktop.
error while dumping graphs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| | WARNING: 240829 samples have invalid sizes and will be skipped, max_positions=(64, 64), first few sample ids=[1422704, 2718830, 2897878, 3673048, 2016896, 2200333, 3886976, 2097242, 3124502, 2871279] | |
| Epoch 1 begin 00:17:55 | |
| training/ 00:19:08, device xla:1, step 1, Rate=132.04, GlobalRate=132.04, loss=15.8125, nll_loss=15.8750 | |
| training/ 00:20:21, device xla:1, step 2, Rate=54.94, GlobalRate=6.89, loss=15.8125, nll_loss=15.8125 | |
| training/ 00:25:46, device xla:1, step 3, Rate=22.92, GlobalRate=2.56, loss=16.0000, nll_loss=16.0000 | |
| training/ 00:40:56, device xla:1, step 4, Rate=9.34, GlobalRate=0.98, loss=15.9375, nll_loss=15.9375 | |
| training/ 01:58:50, device xla:1, step 5, Rate=3.77, GlobalRate=0.26, loss=15.7500, nll_loss=15.8125 | |
| 2019-09-18 03:13:04.411218: E tensorflow/compiler/xla/xla_client/tf_logging.cc:11] Check failed: session_work.first->session()->Run( session_work.second.feed_inputs, session_work.second.outputs_handles, &outputs) == ::tensorflow::Status::OK() (Unavailable: From /job:tpu_worker/replica:0/task:0: | |
| Driver not open. | |
| [[{{node XRTAllocateFromTensor_9}}]] vs. OK) | |
| *** Begin stack trace *** | |
| tensorflow::CurrentStackTrace[abi:cxx11]() | |
| xla::XrtComputationClient::TransferToServer(absl::Span<xla::ComputationClient::TensorSource const>) | |
| torch_xla::TensorToXlaData(at::Tensor const&, torch_xla::Device const&) | |
| torch_xla::XLATensor::GetIrValueForTensor(at::Tensor const&, torch_xla::Device const&) | |
| torch_xla::XLATensor::GetIrValue() const | |
| torch_xla::XLATensor::div(torch_xla::XLATensor const&, torch_xla::XLATensor const&) | |
| torch_xla::AtenXlaType::div(at::Tensor const&, at::Tensor const&) | |
| c10::detail::wrap_kernel_functor_unboxed_<c10::detail::WrapKernelFunction_<at::Tensor (at::Tensor const&, at::Tensor const&), &torch_xla::AtenXlaType::div, at::Tensor, c10::guts::typelist::typelist<at::Tensor const&, at::Tensor const&> >, at::Tensor (at::Tensor const&, at::Tensor const&)>::call(c10::KernelCache*, at::Tensor const&, at::Tensor const&) | |
| torch::autograd::VariableType::div(at::Tensor const&, at::Tensor const&) | |
| PyCFunction_Call | |
| PyObject_Call | |
| PyNumber_TrueDivide | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyFunction_FastCallDict | |
| _PyObject_FastCallDict | |
| _PyObject_Call_Prepend | |
| PyObject_Call | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyFunction_FastCallDict | |
| _PyObject_FastCallDict | |
| _PyObject_Call_Prepend | |
| PyObject_Call | |
| clone | |
| *** End stack trace *** | |
| Exception in model function for device=xla:1: tensorflow/compiler/xla/xla_client/xrt_computation_client.cc:266 : Check failed: session_work.first->session()->Run( session_work.second.feed_inputs, session_work.second.outputs_handles, &outputs) == ::tensorflow::Status::OK() (Unavailable: From /job:tpu_worker/replica:0/task:0: | |
| Driver not open. | |
| [[{{node XRTAllocateFromTensor_9}}]] vs. OK) | |
| *** Begin stack trace *** | |
| tensorflow::CurrentStackTrace[abi:cxx11]() | |
| xla::XrtComputationClient::TransferToServer(absl::Span<xla::ComputationClient::TensorSource const>) | |
| torch_xla::TensorToXlaData(at::Tensor const&, torch_xla::Device const&) | |
| torch_xla::XLATensor::GetIrValueForTensor(at::Tensor const&, torch_xla::Device const&) | |
| torch_xla::XLATensor::GetIrValue() const | |
| torch_xla::XLATensor::div(torch_xla::XLATensor const&, torch_xla::XLATensor const&) | |
| torch_xla::AtenXlaType::div(at::Tensor const&, at::Tensor const&) | |
| c10::detail::wrap_kernel_functor_unboxed_<c10::detail::WrapKernelFunction_<at::Tensor (at::Tensor const&, at::Tensor const&), &torch_xla::AtenXlaType::div, at::Tensor, c10::guts::typelist::typelist<at::Tensor const&, at::Tensor const&> >, at::Tensor (at::Tensor const&, at::Tensor const&)>::call(c10::KernelCache*, at::Tensor const&, at::Tensor const&) | |
| torch::autograd::VariableType::div(at::Tensor const&, at::Tensor const&) | |
| PyCFunction_Call | |
| PyObject_Call | |
| PyNumber_TrueDivide | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyFunction_FastCallDict | |
| _PyObject_FastCallDict | |
| _PyObject_Call_Prepend | |
| PyObject_Call | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyFunction_FastCallDict | |
| _PyObject_FastCallDict | |
| _PyObject_Call_Prepend | |
| PyObject_Call | |
| clone | |
| *** End stack trace *** | |
| Traceback (most recent call last): | |
| File "/anaconda3/envs/pytorch-nightly/lib/python3.6/site-packages/torch_xla_py/data_parallel.py", line 229, in _module_runner | |
| result.result = loop_fn(module, loader, torch.device(device), context) | |
| File "tpu-examples/fairseq_train_tpu.py", line 289, in train_loop_fn | |
| log_output = trainer.train_step(samples) | |
| File "/home/taylanbil/tpu-examples/deps/fairseq/fairseq/trainer.py", line 328, in train_step | |
| logging_outputs, self.criterion | |
| File "/home/taylanbil/tpu-examples/deps/fairseq/fairseq/tasks/fairseq_task.py", line 258, in aggregate_logging_outputs | |
| return criterion.__class__.aggregate_logging_outputs(logging_outputs) | |
| File "/home/taylanbil/tpu-examples/deps/fairseq/fairseq/criterions/label_smoothed_cross_entropy.py", line 74, in aggregate_logging_outputs | |
| 'loss': sum(log.get('loss', 0) for log in logging_outputs) / sample_size / math.log(2) if sample_size > 0 else 0., | |
| RuntimeError: tensorflow/compiler/xla/xla_client/xrt_computation_client.cc:266 : Check failed: session_work.first->session()->Run( session_work.second.feed_inputs, session_work.second.outputs_handles, &outputs) == ::tensorflow::Status::OK() (Unavailable: From /job:tpu_worker/replica:0/task:0: | |
| Driver not open. | |
| [[{{node XRTAllocateFromTensor_9}}]] vs. OK) | |
| *** Begin stack trace *** | |
| tensorflow::CurrentStackTrace[abi:cxx11]() | |
| xla::XrtComputationClient::TransferToServer(absl::Span<xla::ComputationClient::TensorSource const>) | |
| torch_xla::TensorToXlaData(at::Tensor const&, torch_xla::Device const&) | |
| torch_xla::XLATensor::GetIrValueForTensor(at::Tensor const&, torch_xla::Device const&) | |
| torch_xla::XLATensor::GetIrValue() const | |
| torch_xla::XLATensor::div(torch_xla::XLATensor const&, torch_xla::XLATensor const&) | |
| torch_xla::AtenXlaType::div(at::Tensor const&, at::Tensor const&) | |
| c10::detail::wrap_kernel_functor_unboxed_<c10::detail::WrapKernelFunction_<at::Tensor (at::Tensor const&, at::Tensor const&), &torch_xla::AtenXlaType::div, at::Tensor, c10::guts::typelist::typelist<at::Tensor const&, at::Tensor const&> >, at::Tensor (at::Tensor const&, at::Tensor const&)>::call(c10::KernelCache*, at::Tensor const&, at::Tensor const&) | |
| torch::autograd::VariableType::div(at::Tensor const&, at::Tensor const&) | |
| PyCFunction_Call | |
| PyObject_Call | |
| PyNumber_TrueDivide | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyFunction_FastCallDict | |
| _PyObject_FastCallDict | |
| _PyObject_Call_Prepend | |
| PyObject_Call | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyEval_EvalFrameDefault | |
| _PyFunction_FastCallDict | |
| _PyObject_FastCallDict | |
| _PyObject_Call_Prepend | |
| PyObject_Call | |
| clone | |
| *** End stack trace *** |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment