lm1-4b2-84b-oscar-repetitions
/
4b284b12boscar
/evaluation
/generation
/slim.4b284b12boscar_GEM-wiki_lingua_en_tldr_en_3.json
{ | |
"results": [ | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_precision": 0.2754936136179268, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_precision_stderr": 0.004157379347035767 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_recall": 0.20528413095627832, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_recall_stderr": 0.003149288824376793 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_fmeasure": 0.19838663921126778, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_fmeasure_stderr": 0.002621759128746396 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_precision": 0.08256853694746276, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_precision_stderr": 0.0024364087557486665 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_recall": 0.05727334409426975, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_recall_stderr": 0.0015675844642289158 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_fmeasure": 0.055968236855402816, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_fmeasure_stderr": 0.0014034751658766104 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_precision": 0.21625894747073696, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_precision_stderr": 0.0034653747339702624 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_recall": 0.15717871923447801, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_recall_stderr": 0.00246051792291125 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_fmeasure": 0.15243563853997083, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_fmeasure_stderr": 0.0020406692721428466 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_precision": 0.2591405389486435, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_precision_stderr": 0.003962509253114959 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_recall": 0.19231398442318168, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_recall_stderr": 0.0029662256128315167 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_fmeasure": 0.18589041350629654, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_fmeasure_stderr": 0.0024658633555113495 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"bleu": 2.8632324313744557, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"bleu_stderr": 0.09299178906804655 | |
} | |
], | |
"config": { | |
"model": "hf-causal", | |
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b12boscar/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 | |
} | |
} |