lm1-4b2-84b-c4-repetitions
/
4b284b28bc4
/evaluation
/generation
/slim.4b284b28bc4_GEM-wiki_lingua_en_tldr_en_3.json
{ | |
"results": [ | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_precision": 0.22344987630747953, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_precision_stderr": 0.0038946320752308397 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_recall": 0.228687908011972, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_recall_stderr": 0.0033634865916312945 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge1_fmeasure": 0.1819863863181494, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge1_fmeasure_stderr": 0.0024282963824572346 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_precision": 0.06821362116644611, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_precision_stderr": 0.0023091245896002433 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_recall": 0.06243742554002245, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_recall_stderr": 0.001665626169617889 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rouge2_fmeasure": 0.05005886014366939, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rouge2_fmeasure_stderr": 0.0012507484027525577 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_precision": 0.17380086539073145, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_precision_stderr": 0.003294779021368952 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_recall": 0.1728818390227638, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_recall_stderr": 0.0026287282834976822 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeL_fmeasure": 0.13680266609806765, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeL_fmeasure_stderr": 0.001821525871477116 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_precision": 0.21200019749157653, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_precision_stderr": 0.003735810714751958 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_recall": 0.21587781354640423, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_recall_stderr": 0.003186682013692883 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"rougeLsum_fmeasure": 0.17195845477450572, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"rougeLsum_fmeasure_stderr": 0.0023005495305984053 | |
}, | |
{ | |
"task_name": "GEM/wiki_lingua_en", | |
"prompt_name": "tldr_en", | |
"bleu": 3.5006949715383118, | |
"dataset_path": "GEM/wiki_lingua", | |
"dataset_name": "en", | |
"subset": null, | |
"bleu_stderr": 0.08071997944617754 | |
} | |
], | |
"config": { | |
"model": "hf-causal", | |
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b28bc4/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 | |
} | |
} |