The following values were not passed to `accelerate launch` and had defaults used instead: `--num_processes` was set to a value of `8` More than one GPU was found, enabling multi-GPU training. If this was unintended please pass in `--num_processes=1`. `--num_machines` was set to a value of `1` `--mixed_precision` was set to a value of `'no'` `--dynamo_backend` was set to a value of `'no'` To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`. 2025-02-21:14:10:46,362 INFO [__main__.py:279] Verbosity set to INFO 2025-02-21:14:10:46,362 INFO [__main__.py:279] Verbosity set to INFO 2025-02-21:14:10:46,362 INFO [__main__.py:279] Verbosity set to INFO 2025-02-21:14:10:46,362 INFO [__main__.py:279] Verbosity set to INFO 2025-02-21:14:10:46,362 INFO [__main__.py:279] Verbosity set to INFO 2025-02-21:14:10:46,362 INFO [__main__.py:279] Verbosity set to INFO 2025-02-21:14:10:46,362 INFO [__main__.py:279] Verbosity set to INFO 2025-02-21:14:10:46,362 INFO [__main__.py:279] Verbosity set to INFO 2025-02-21:14:11:03,010 INFO [__main__.py:376] Selected Tasks: ['gsm8k_cot_zeroshot'] 2025-02-21:14:11:03,010 INFO [__main__.py:376] Selected Tasks: ['gsm8k_cot_zeroshot'] 2025-02-21:14:11:03,010 INFO [__main__.py:376] Selected Tasks: ['gsm8k_cot_zeroshot'] 2025-02-21:14:11:03,010 INFO [__main__.py:376] Selected Tasks: ['gsm8k_cot_zeroshot'] 2025-02-21:14:11:03,010 INFO [__main__.py:376] Selected Tasks: ['gsm8k_cot_zeroshot'] 2025-02-21:14:11:03,010 INFO [__main__.py:376] Selected Tasks: ['gsm8k_cot_zeroshot'] 2025-02-21:14:11:03,010 INFO [__main__.py:376] Selected Tasks: ['gsm8k_cot_zeroshot'] 2025-02-21:14:11:03,010 INFO [__main__.py:376] Selected Tasks: ['gsm8k_cot_zeroshot'] 2025-02-21:14:11:03,023 INFO [evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2025-02-21:14:11:03,023 INFO [evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2025-02-21:14:11:03,023 INFO [evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2025-02-21:14:11:03,023 INFO [evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2025-02-21:14:11:03,023 INFO [evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2025-02-21:14:11:03,023 INFO [evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2025-02-21:14:11:03,023 WARNING [evaluator.py:175] generation_kwargs specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2025-02-21:14:11:03,023 INFO [evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2025-02-21:14:11:03,023 INFO [evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2025-02-21:14:11:03,023 WARNING [evaluator.py:175] generation_kwargs specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2025-02-21:14:11:03,023 WARNING [evaluator.py:175] generation_kwargs specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2025-02-21:14:11:03,023 WARNING [evaluator.py:175] generation_kwargs specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2025-02-21:14:11:03,023 WARNING [evaluator.py:175] generation_kwargs specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2025-02-21:14:11:03,023 WARNING [evaluator.py:175] generation_kwargs specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2025-02-21:14:11:03,023 INFO [evaluator.py:201] Initializing hf-auto model, with arguments: {'pretrained': '/nlp_group/huangwei12/r1_research/open-r1/data/Qwen-2.5-7B-Simple-RL', 'trust_remote_code': True, 'dtype': 'bfloat16'} 2025-02-21:14:11:03,023 WARNING [evaluator.py:175] generation_kwargs specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2025-02-21:14:11:03,023 INFO [evaluator.py:201] Initializing hf-auto model, with arguments: {'pretrained': '/nlp_group/huangwei12/r1_research/open-r1/data/Qwen-2.5-7B-Simple-RL', 'trust_remote_code': True, 'dtype': 'bfloat16'} 2025-02-21:14:11:03,023 INFO [evaluator.py:201] Initializing hf-auto model, with arguments: {'pretrained': '/nlp_group/huangwei12/r1_research/open-r1/data/Qwen-2.5-7B-Simple-RL', 'trust_remote_code': True, 'dtype': 'bfloat16'} 2025-02-21:14:11:03,023 INFO [evaluator.py:201] Initializing hf-auto model, with arguments: {'pretrained': '/nlp_group/huangwei12/r1_research/open-r1/data/Qwen-2.5-7B-Simple-RL', 'trust_remote_code': True, 'dtype': 'bfloat16'} 2025-02-21:14:11:03,023 WARNING [evaluator.py:175] generation_kwargs specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2025-02-21:14:11:03,023 INFO [evaluator.py:201] Initializing hf-auto model, with arguments: {'pretrained': '/nlp_group/huangwei12/r1_research/open-r1/data/Qwen-2.5-7B-Simple-RL', 'trust_remote_code': True, 'dtype': 'bfloat16'} 2025-02-21:14:11:03,023 INFO [evaluator.py:201] Initializing hf-auto model, with arguments: {'pretrained': '/nlp_group/huangwei12/r1_research/open-r1/data/Qwen-2.5-7B-Simple-RL', 'trust_remote_code': True, 'dtype': 'bfloat16'} 2025-02-21:14:11:03,023 INFO [evaluator.py:201] Initializing hf-auto model, with arguments: {'pretrained': '/nlp_group/huangwei12/r1_research/open-r1/data/Qwen-2.5-7B-Simple-RL', 'trust_remote_code': True, 'dtype': 'bfloat16'} 2025-02-21:14:11:03,023 INFO [evaluator.py:201] Initializing hf-auto model, with arguments: {'pretrained': '/nlp_group/huangwei12/r1_research/open-r1/data/Qwen-2.5-7B-Simple-RL', 'trust_remote_code': True, 'dtype': 'bfloat16'} 2025-02-21:14:11:06,773 INFO [huggingface.py:482] Using model type 'default' 2025-02-21:14:11:06,775 INFO [huggingface.py:482] Using model type 'default' 2025-02-21:14:11:06,819 INFO [huggingface.py:482] Using model type 'default' 2025-02-21:14:11:07,030 INFO [huggingface.py:482] Using model type 'default' 2025-02-21:14:11:07,037 INFO [huggingface.py:482] Using model type 'default' 2025-02-21:14:11:07,060 INFO [huggingface.py:482] Using model type 'default' 2025-02-21:14:11:07,080 INFO [huggingface.py:482] Using model type 'default' 2025-02-21:14:11:07,081 INFO [huggingface.py:482] Using model type 'default' 2025-02-21:14:11:07,246 INFO [huggingface.py:366] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:4'} 2025-02-21:14:11:07,249 INFO [huggingface.py:366] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:6'} 2025-02-21:14:11:07,338 INFO [huggingface.py:366] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:0'} 2025-02-21:14:11:07,442 INFO [huggingface.py:366] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:3'} 2025-02-21:14:11:07,447 INFO [huggingface.py:366] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:1'} 2025-02-21:14:11:07,458 INFO [huggingface.py:366] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:5'} 2025-02-21:14:11:07,479 INFO [huggingface.py:366] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:2'} 2025-02-21:14:11:07,490 INFO [huggingface.py:366] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:7'} Loading checkpoint shards: 0%| | 0/4 [00:00