{ "results": [ { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.22091940935835946, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.003036544780507811 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.28592540020450335, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.0028268458929152375 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.213319730404769, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.001947942927707738 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.0625668775391695, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.001863481800778566 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.07636442527094099, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.0016705370533154184 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.05619324678157442, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.0011378174233996204 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.16524622277086715, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.002504977446892061 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.21312172953880804, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.002230572391304009 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.15707830961714367, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.001424704542577375 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.2088533869488438, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.0029209986594073956 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.27031759901723496, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.00269091513844755 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.20133540483239756, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.0018432855451969799 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 3.0758182963274967, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "bleu_stderr": 0.07269865886048295 } ], "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": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234 } }