{ "results": [ { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.1310122719121047, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rouge1_precision_stderr": 0.001774463078853173 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.32197642898756434, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rouge1_recall_stderr": 0.004128514222989525 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.18395936513372504, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rouge1_fmeasure_stderr": 0.0023841684164883858 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.028592074721851848, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rouge2_precision_stderr": 0.0010146723977319822 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.07420088979991933, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rouge2_recall_stderr": 0.0027242327105131063 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.040730679478674064, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rouge2_fmeasure_stderr": 0.0014445249170945054 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.10506688444375611, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rougeL_precision_stderr": 0.0013615120559406814 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.2609222630071341, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rougeL_recall_stderr": 0.0034251450207401918 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.14791071749656537, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rougeL_fmeasure_stderr": 0.0018605423267814124 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.1039952495955331, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rougeLsum_precision_stderr": 0.00147131239785375 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.2579710996210495, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rougeLsum_recall_stderr": 0.0036391736637925577 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.1463682832676705, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "rougeLsum_fmeasure_stderr": 0.0020126152822738364 }, { "task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 1.5610996318449655, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "bleu_stderr": 0.061361742735683046 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b17bc4/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 } }