{ "results": [ { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.21388175415191102, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.0037807201763198858 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.22109179833036308, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.00317048229219639 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.17690311487463797, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.0023173541475324253 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.06310561248802647, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.0021350241076741575 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.05983363177094545, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.0015915281660158853 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.04775424867054453, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.0011657814934947282 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.16656647324261953, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.0032154715784240336 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.16788106886771248, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.0024768275501905303 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.13377606619329538, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.0017521905460361976 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.2032660883469589, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.003645991164048245 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.20988404520976878, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.003033569663633178 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.16765421945999662, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.002202375233222233 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 3.2676357062273516, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "bleu_stderr": 0.12290136548273946 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b21bc4/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234 } }