lm1-4b2-84b-c4seeds
/
4b284b12bc4seed2
/evaluation
/generation
/slim.4b284b12bc4seed2_GEM-wiki_lingua_en_tldr_en_0.json
{ | |
"results": [ | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_precision": 0.08041542381459962, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_precision_stderr": 0.0012034347430153701 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_recall": 0.12977261642720425, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_recall_stderr": 0.0016061415032672362 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_fmeasure": 0.09276892306618244, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_fmeasure_stderr": 0.0011960344018118775 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_precision": 0.00482101020032747, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_precision_stderr": 0.000288358623019921 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_recall": 0.007392323231333513, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_recall_stderr": 0.0004384293210501124 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_fmeasure": 0.005442298869452033, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_fmeasure_stderr": 0.00031336134550929984 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_precision": 0.06948188762406071, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_precision_stderr": 0.0009562354726599046 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_recall": 0.1148205615117217, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_recall_stderr": 0.0013763320189433634 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_fmeasure": 0.08081272257942029, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_fmeasure_stderr": 0.000958641259754323 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_precision": 0.07505126481568339, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_precision_stderr": 0.0011046552942777078 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_recall": 0.12191849988137807, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_recall_stderr": 0.001502332271175678 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_fmeasure": 0.08675704545208646, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_fmeasure_stderr": 0.0011000237175663734 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"bleu": 0.24392437655372481, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"bleu_stderr": 0.023857847767670762 | |
} | |
], | |
"config": { | |
"model": "hf-causal", | |
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscarseeds/4b284b12bc4seed2/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", | |
"task_args": "", | |
"num_fewshot": 0, | |
"batch_size": 16, | |
"device": "cuda", | |
"use_cache": false, | |
"limit": 3000, | |
"bootstrap_iters": 10, | |
"seed": 1234 | |
} | |
} |