lm1-4b2-84b-c4-repetitions
/
4b284b17bc4
/evaluation
/generation
/slim.4b284b17bc4_GEM-wiki_lingua_en_tldr_en_4.json
{ | |
"results": [ | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_precision": 0.056788240211910736, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_precision_stderr": 0.0022506997974891542 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_recall": 0.08339625174295712, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_recall_stderr": 0.0029290040087097207 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_fmeasure": 0.05659885761358278, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_fmeasure_stderr": 0.001930223829324733 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_precision": 0.014380667558554284, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_precision_stderr": 0.000977357379524512 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_recall": 0.02101316087357165, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_recall_stderr": 0.0011619283931715888 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_fmeasure": 0.013810868807903593, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_fmeasure_stderr": 0.0006930003786904605 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_precision": 0.04257610439946902, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_precision_stderr": 0.0017464834049321358 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_recall": 0.06302882516092573, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_recall_stderr": 0.0022681193452949904 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_fmeasure": 0.042007409754473535, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_fmeasure_stderr": 0.0014258890197756744 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_precision": 0.05318358596123625, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_precision_stderr": 0.0021166691321526723 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_recall": 0.07838773551352705, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_recall_stderr": 0.002768443855799422 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_fmeasure": 0.05299986098950862, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_fmeasure_stderr": 0.0018068900698462816 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"bleu": 0.5461443377554994, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"bleu_stderr": 0.044799916123802616 | |
} | |
], | |
"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": 4, | |
"batch_size": 16, | |
"device": "cuda", | |
"use_cache": false, | |
"limit": 3000, | |
"bootstrap_iters": 10, | |
"seed": 1234 | |
} | |
} |