We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
* 1 x E1003 23:51:14.134000 139750057968064 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 7 (pid: 776026) of binary: /home/mila/rocm/results/venv/torch/bin/python | [rank5]: Traceback (most recent call last): | [rank5]: File "/home/mila/milabench/benchmarks/rlhf/main.py", line 133, in <module> | [rank5]: main() | [rank5]: File "/home/mila/milabench/benchmarks/rlhf/main.py", line 124, in main | [rank5]: trainer.train() | [rank5]: File "/home/mila/rocm/results/venv/torch/lib/python3.10/site-packages/trl/trainer/ppov2_trainer.py", line 309, in train | [rank5]: query_responses, logitss = batch_generation( | [rank5]: File "/home/mila/rocm/results/venv/torch/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context | [rank5]: return func(*args, **kwargs) | [rank5]: File "/home/mila/rocm/results/venv/torch/lib/python3.10/site-packages/trl/trainer/utils.py", line 1176, in batch_generation | [rank5]: query_response, logits = generate( | [rank5]: File "/home/mila/rocm/results/venv/torch/lib/python3.10/site-packages/trl/trainer/utils.py", line 1151, in generate | [rank5]: output = lm_backbone.generate( | [rank5]: File "/home/mila/rocm/results/venv/torch/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context | [rank5]: return func(*args, **kwargs) | [rank5]: File "/home/mila/rocm/results/venv/torch/lib/python3.10/site-packages/transformers/generation/utils.py", line 2024, in generate | [rank5]: result = self._sample( | [rank5]: File "/home/mila/rocm/results/venv/torch/lib/python3.10/site-packages/transformers/generation/utils.py", line 3020, in _sample | [rank5]: next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1) | [rank5]: RuntimeError: probability tensor contains either `inf`, `nan` or element < 0
The text was updated successfully, but these errors were encountered:
No branches or pull requests
The text was updated successfully, but these errors were encountered: