{ "results": { "boolq": { "acc": 0.7382262996941896, "acc_stderr": 0.007688653730439849 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.2126984126984127 }, "copa": { "acc": 0.84, "acc_stderr": 0.036845294917747115 }, "multirc": { "acc": 0.008394543546694649, "acc_stderr": 0.002956987733350658 }, "record": { "f1": 0.900992857142857, "f1_stderr": 0.0029401923751195343, "em": 0.893, "em_stderr": 0.0030912870467751773 }, "wic": { "acc": 0.4843260188087774, "acc_stderr": 0.01980098495534785 }, "wsc": { "acc": 0.6346153846153846, "acc_stderr": 0.0474473339327792 } }, "versions": { "boolq": 1, "cb": 1, "copa": 0, "multirc": 1, "record": 0, "wic": 0, "wsc": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }