| { | |
| "results": { | |
| "gsm8k": { | |
| "exact_match,get-answer": 0.7414708112206216, | |
| "exact_match_stderr,get-answer": 0.012059911372516116, | |
| "alias": "gsm8k" | |
| } | |
| }, | |
| "configs": { | |
| "gsm8k": { | |
| "task": "gsm8k", | |
| "group": [ | |
| "math_word_problems" | |
| ], | |
| "dataset_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/eval/gsm8k", | |
| "dataset_name": "main", | |
| "training_split": "train", | |
| "test_split": "test", | |
| "fewshot_split": "train", | |
| "doc_to_text": "Question: {{question}}\nAnswer:", | |
| "doc_to_target": "{{answer}}", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": false, | |
| "regexes_to_ignore": [ | |
| ",", | |
| "\\$", | |
| "(?s).*#### " | |
| ] | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "\n\n", | |
| "Question:" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "get-answer", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "#### (\\-?[0-9\\.\\,]+)" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 2.0 | |
| } | |
| } | |
| }, | |
| "versions": { | |
| "gsm8k": 2.0 | |
| }, | |
| "n-shot": { | |
| "gsm8k": 5 | |
| }, | |
| "config": { | |
| "model": "vllm", | |
| "model_args": "pretrained=/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Oasis,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.9,data_parallel_size=1,max_model_len=4096", | |
| "batch_size": "auto:128", | |
| "batch_sizes": [], | |
| "device": "cuda", | |
| "use_cache": "/lustre07/scratch/gagan30/arocr/cache/", | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "gen_kwargs": null | |
| }, | |
| "git_hash": null | |
| } |