diff --git "a/Order_Ablations/E115_2gpu100/launcher.log" "b/Order_Ablations/E115_2gpu100/launcher.log" new file mode 100644--- /dev/null +++ "b/Order_Ablations/E115_2gpu100/launcher.log" @@ -0,0 +1,291 @@ +>>>>> grad accum = 32 +/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. + import pynvml # type: ignore[import] +W0127 17:10:05.230000 185005 torch/distributed/run.py:803] +W0127 17:10:05.230000 185005 torch/distributed/run.py:803] ***************************************** +W0127 17:10:05.230000 185005 torch/distributed/run.py:803] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +W0127 17:10:05.230000 185005 torch/distributed/run.py:803] ***************************************** +/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. + import pynvml # type: ignore[import] +/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. + import pynvml # type: ignore[import] +Trainer._get_train_sampler replaced with custom implementation. +Trainer._get_train_sampler replaced with custom implementation. +[2026-01-27 17:10:12,014] [INFO] [real_accelerator.py:222:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2026-01-27 17:10:12,029] [INFO] [real_accelerator.py:222:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2026-01-27 17:10:13,285] [INFO] [comm.py:658:init_distributed] cdb=None +[2026-01-27 17:10:13,285] [INFO] [comm.py:658:init_distributed] cdb=None +[2026-01-27 17:10:13,285] [INFO] [comm.py:689:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +Warning: FlashAttention 3 is not available, falling back to PyTorch's scaled_dot_product_attention +Warning: FlashAttention 3 is not available, falling back to PyTorch's scaled_dot_product_attention +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. + Loading checkpoint shards: 0%| | 0/2 [00:00 + sys.exit(main()) + ^^^^^^ + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 357, in wrapper + return f(*args, **kwargs) + ^^^^^^^^^^^^^^^^^^ + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/run.py", line 936, in main + run(args) + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/run.py", line 927, in run + elastic_launch( + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/launcher/api.py", line 151, in __call__ + return launch_agent(self._config, self._entrypoint, list(args)) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/launcher/api.py", line 279, in launch_agent + result = agent.run() + ^^^^^^^^^^^ + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/metrics/api.py", line 138, in wrapper + result = f(*args, **kwargs) + ^^^^^^^^^^^^^^^^^^ + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/agent/server/api.py", line 724, in run + result = self._invoke_run(role) + ^^^^^^^^^^^^^^^^^^^^^^ + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/agent/server/api.py", line 888, in _invoke_run + time.sleep(monitor_interval) + File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/multiprocessing/api.py", line 85, in _terminate_process_handler + raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval) +torch.distributed.elastic.multiprocessing.api.SignalException: Process 185005 got signal: 15