{ "results": { "hellaswag": { "acc,none": 0.6504680342561243, "acc_stderr,none": 0.004758476684324035, "acc_norm,none": 0.8483369846644094, "acc_norm_stderr,none": 0.0035796087435066605, "alias": "hellaswag" } }, "configs": { "hellaswag": { "task": "hellaswag", "group": [ "multiple_choice" ], "dataset_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/eval/hellaswag", "training_split": "train", "validation_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n out_doc = {\n \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n \"gold\": int(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "{{query}}", "doc_to_target": "{{label}}", "doc_to_choice": "choices", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 10, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true }, { "metric": "acc_norm", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } } }, "versions": { "hellaswag": 1.0 }, "n-shot": { "hellaswag": 10 }, "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 }