| { | |
| "results": { | |
| "winogrande": { | |
| "acc,none": 0.696921862667719, | |
| "acc_stderr,none": 0.012916727462634564, | |
| "alias": "winogrande" | |
| } | |
| }, | |
| "configs": { | |
| "winogrande": { | |
| "task": "winogrande", | |
| "dataset_path": "winogrande", | |
| "dataset_name": "winogrande_xl", | |
| "training_split": "train", | |
| "validation_split": "validation", | |
| "doc_to_text": "def doc_to_text(doc):\n answer_to_num = {\"1\": 0, \"2\": 1}\n return answer_to_num[doc[\"answer\"]]\n", | |
| "doc_to_target": "def doc_to_target(doc):\n idx = doc[\"sentence\"].index(\"_\") + 1\n return doc[\"sentence\"][idx:].strip()\n", | |
| "doc_to_choice": "def doc_to_choice(doc):\n idx = doc[\"sentence\"].index(\"_\")\n options = [doc[\"option1\"], doc[\"option2\"]]\n return [doc[\"sentence\"][:idx] + opt for opt in options]\n", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "acc", | |
| "aggregation": "mean", | |
| "higher_is_better": true | |
| } | |
| ], | |
| "output_type": "multiple_choice", | |
| "repeats": 1, | |
| "should_decontaminate": true, | |
| "doc_to_decontamination_query": "sentence", | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| } | |
| }, | |
| "versions": { | |
| "winogrande": 1.0 | |
| }, | |
| "n-shot": { | |
| "winogrande": 5 | |
| }, | |
| "config": { | |
| "model": "hf", | |
| "model_args": "pretrained=RWKV/rwkv-5-world-7b,dtype=float16,trust_remote_code=True", | |
| "batch_size": "auto", | |
| "batch_sizes": [ | |
| 64 | |
| ], | |
| "device": null, | |
| "use_cache": null, | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "gen_kwargs": null | |
| }, | |
| "git_hash": "1554066c" | |
| } |