diff options
Diffstat (limited to 'logs/grpo_reflection_15498033.err')
| -rw-r--r-- | logs/grpo_reflection_15498033.err | 66 |
1 files changed, 66 insertions, 0 deletions
diff --git a/logs/grpo_reflection_15498033.err b/logs/grpo_reflection_15498033.err new file mode 100644 index 0000000..1434e29 --- /dev/null +++ b/logs/grpo_reflection_15498033.err @@ -0,0 +1,66 @@ +/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead. + warnings.warn( +[0;36m(APIServer pid=1914169)[0;0m The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored. +[0;36m(APIServer pid=1914169)[0;0m
Parse safetensors files: 0%| | 0/9 [00:00<?, ?it/s]
Parse safetensors files: 11%|█ | 1/9 [00:00<00:00, 8.22it/s]
Parse safetensors files: 100%|██████████| 9/9 [00:00<00:00, 49.13it/s] +/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead. + warnings.warn( +/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead. + warnings.warn( +/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead. + warnings.warn( +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 0% Completed | 0/9 [00:00<?, ?it/s] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 11% Completed | 1/9 [00:01<00:13, 1.67s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 22% Completed | 2/9 [00:03<00:11, 1.71s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 33% Completed | 3/9 [00:04<00:08, 1.48s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 44% Completed | 4/9 [00:06<00:07, 1.57s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 56% Completed | 5/9 [00:08<00:06, 1.63s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 67% Completed | 6/9 [00:09<00:04, 1.67s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 78% Completed | 7/9 [00:11<00:03, 1.65s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 89% Completed | 8/9 [00:12<00:01, 1.31s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 100% Completed | 9/9 [00:13<00:00, 1.43s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Loading safetensors checkpoint shards: 100% Completed | 9/9 [00:13<00:00, 1.52s/it] +[0;36m(Worker_TP0 pid=1914626)[0;0m +[0;36m(Worker_TP0 pid=1914626)[0;0m
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 0%| | 0/51 [00:00<?, ?it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 2%|▏ | 1/51 [00:00<00:19, 2.53it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 4%|▍ | 2/51 [00:00<00:15, 3.14it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 6%|▌ | 3/51 [00:00<00:13, 3.56it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 8%|▊ | 4/51 [00:01<00:12, 3.82it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 10%|▉ | 5/51 [00:01<00:11, 4.10it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 12%|█▏ | 6/51 [00:01<00:10, 4.27it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 14%|█▎ | 7/51 [00:01<00:10, 4.30it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 16%|█▌ | 8/51 [00:01<00:09, 4.44it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 18%|█▊ | 9/51 [00:02<00:08, 4.67it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 20%|█▉ | 10/51 [00:02<00:08, 4.80it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 22%|██▏ | 11/51 [00:02<00:08, 4.92it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 24%|██▎ | 12/51 [00:02<00:07, 5.03it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 25%|██▌ | 13/51 [00:02<00:07, 5.28it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 27%|██▋ | 14/51 [00:03<00:06, 5.43it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 29%|██▉ | 15/51 [00:03<00:06, 5.56it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 31%|███▏ | 16/51 [00:03<00:06, 5.69it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 33%|███▎ | 17/51 [00:03<00:05, 5.99it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 35%|███▌ | 18/51 [00:03<00:05, 6.10it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 37%|███▋ | 19/51 [00:03<00:05, 6.25it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 39%|███▉ | 20/51 [00:04<00:04, 6.35it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 41%|████ | 21/51 [00:04<00:04, 6.47it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 43%|████▎ | 22/51 [00:04<00:04, 6.53it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 45%|████▌ | 23/51 [00:04<00:04, 6.62it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 47%|████▋ | 24/51 [00:04<00:04, 6.69it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 49%|████▉ | 25/51 [00:04<00:03, 7.02it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 51%|█████ | 26/51 [00:04<00:03, 7.10it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 53%|█████▎ | 27/51 [00:05<00:03, 7.26it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 55%|█████▍ | 28/51 [00:05<00:03, 7.37it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 57%|█████▋ | 29/51 [00:05<00:02, 7.52it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 59%|█████▉ | 30/51 [00:05<00:02, 7.62it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 61%|██████ | 31/51 [00:05<00:02, 7.73it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 63%|██████▎ | 32/51 [00:05<00:02, 7.82it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 65%|██████▍ | 33/51 [00:05<00:02, 8.22it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 67%|██████▋ | 34/51 [00:05<00:02, 8.23it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 69%|██████▊ | 35/51 [00:06<00:01, 8.42it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 71%|███████ | 36/51 [00:06<00:01, 8.57it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 73%|███████▎ | 37/51 [00:06<00:01, 8.67it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 75%|███████▍ | 38/51 [00:06<00:01, 8.84it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 76%|███████▋ | 39/51 [00:06<00:01, 9.01it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 78%|███████▊ | 40/51 [00:06<00:01, 9.02it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 82%|████████▏ | 42/51 [00:06<00:00, 9.99it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 86%|████████▋ | 44/51 [00:06<00:00, 10.51it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 90%|█████████ | 46/51 [00:07<00:00, 10.89it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 94%|█████████▍| 48/51 [00:07<00:00, 11.13it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 98%|█████████▊| 50/51 [00:07<00:00, 11.33it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|██████████| 51/51 [00:07<00:00, 6.80it/s] +[0;36m(Worker_TP0 pid=1914626)[0;0m
Capturing CUDA graphs (decode, FULL): 0%| | 0/35 [00:00<?, ?it/s]
Capturing CUDA graphs (decode, FULL): 3%|▎ | 1/35 [00:00<00:06, 4.97it/s]
Capturing CUDA graphs (decode, FULL): 6%|▌ | 2/35 [00:00<00:05, 5.80it/s]
Capturing CUDA graphs (decode, FULL): 9%|▊ | 3/35 [00:00<00:05, 6.25it/s]
Capturing CUDA graphs (decode, FULL): 11%|█▏ | 4/35 [00:00<00:04, 6.49it/s]
Capturing CUDA graphs (decode, FULL): 14%|█▍ | 5/35 [00:00<00:04, 6.70it/s]
Capturing CUDA graphs (decode, FULL): 17%|█▋ | 6/35 [00:00<00:04, 6.84it/s]
Capturing CUDA graphs (decode, FULL): 20%|██ | 7/35 [00:01<00:04, 6.97it/s]
Capturing CUDA graphs (decode, FULL): 23%|██▎ | 8/35 [00:01<00:03, 7.07it/s]
Capturing CUDA graphs (decode, FULL): 26%|██▌ | 9/35 [00:01<00:03, 7.46it/s]
Capturing CUDA graphs (decode, FULL): 29%|██▊ | 10/35 [00:01<00:03, 7.55it/s]
Capturing CUDA graphs (decode, FULL): 31%|███▏ | 11/35 [00:01<00:03, 7.73it/s]
Capturing CUDA graphs (decode, FULL): 34%|███▍ | 12/35 [00:01<00:02, 7.86it/s]
Capturing CUDA graphs (decode, FULL): 37%|███▋ | 13/35 [00:01<00:02, 8.05it/s]
Capturing CUDA graphs (decode, FULL): 40%|████ | 14/35 [00:01<00:02, 8.17it/s]
Capturing CUDA graphs (decode, FULL): 43%|████▎ | 15/35 [00:02<00:02, 8.31it/s]
Capturing CUDA graphs (decode, FULL): 46%|████▌ | 16/35 [00:02<00:02, 8.43it/s]
Capturing CUDA graphs (decode, FULL): 51%|█████▏ | 18/35 [00:02<00:01, 9.01it/s]
Capturing CUDA graphs (decode, FULL): 54%|█████▍ | 19/35 [00:02<00:01, 9.19it/s]
Capturing CUDA graphs (decode, FULL): 57%|█████▋ | 20/35 [00:02<00:01, 9.35it/s]
Capturing CUDA graphs (decode, FULL): 63%|██████▎ | 22/35 [00:02<00:01, 9.70it/s]
Capturing CUDA graphs (decode, FULL): 69%|██████▊ | 24/35 [00:02<00:01, 10.01it/s]
Capturing CUDA graphs (decode, FULL): 74%|███████▍ | 26/35 [00:03<00:00, 10.69it/s]
Capturing CUDA graphs (decode, FULL): 80%|████████ | 28/35 [00:03<00:00, 11.15it/s]
Capturing CUDA graphs (decode, FULL): 86%|████████▌ | 30/35 [00:03<00:00, 11.50it/s]
Capturing CUDA graphs (decode, FULL): 91%|█████████▏| 32/35 [00:03<00:00, 11.79it/s]
Capturing CUDA graphs (decode, FULL): 97%|█████████▋| 34/35 [00:03<00:00, 12.00it/s]
Capturing CUDA graphs (decode, FULL): 100%|██████████| 35/35 [00:03<00:00, 9.12it/s] +[0;36m(APIServer pid=1914169)[0;0m INFO: Started server process [1914169] +[0;36m(APIServer pid=1914169)[0;0m INFO: Waiting for application startup. +[0;36m(APIServer pid=1914169)[0;0m INFO: Application startup complete. +/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead. + warnings.warn( +/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/trl/import_utils.py:91: UserWarning: TRL currently only supports vLLM version `0.10.2`. You have version 0.13.0 installed. We recommend to install this version to avoid compatibility issues. + warnings.warn( +/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/trl/import_utils.py:91: UserWarning: TRL currently only supports vLLM version `0.10.2`. You have version 0.13.0 installed. We recommend to install this version to avoid compatibility issues. + warnings.warn( +Traceback (most recent call last): + File "/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/trl/import_utils.py", line 156, in _get_module + return importlib.import_module("." + module_name, self.__name__) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/u/yurenh2/miniforge3/envs/eval/lib/python3.11/importlib/__init__.py", line 126, in import_module + return _bootstrap._gcd_import(name[level:], package, level) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "<frozen importlib._bootstrap>", line 1204, in _gcd_import + File "<frozen importlib._bootstrap>", line 1176, in _find_and_load + File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked + File "<frozen importlib._bootstrap>", line 690, in _load_unlocked + File "<frozen importlib._bootstrap_external>", line 940, in exec_module + File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed + File "/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/trl/trainer/grpo_trainer.py", line 85, in <module> + from vllm.sampling_params import GuidedDecodingParams +ImportError: cannot import name 'GuidedDecodingParams' from 'vllm.sampling_params' (/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/vllm/sampling_params.py) + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/collaborativeagents/training/train_grpo.py", line 21, in <module> + from trl import GRPOConfig, GRPOTrainer + File "<frozen importlib._bootstrap>", line 1229, in _handle_fromlist + File "/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/trl/import_utils.py", line 147, in __getattr__ + value = getattr(module, name) + ^^^^^^^^^^^^^^^^^^^^^ + File "/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/trl/import_utils.py", line 146, in __getattr__ + module = self._get_module(self._class_to_module[name]) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/trl/import_utils.py", line 158, in _get_module + raise RuntimeError( +RuntimeError: Failed to import trl.trainer.grpo_trainer because of the following error (look up to see its traceback): +cannot import name 'GuidedDecodingParams' from 'vllm.sampling_params' (/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/vllm/sampling_params.py) |