lm1-2b8-55b-c4-repetitions / 2b855b14bc4 /evaluation /generation /slim.2b855b14bc4_gem_xsum_article_DOC_summary_1.json
Muennighoff's picture
Add eval
990f338
raw
history blame
4 kB
{
"results": [
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_precision": 0.1140166034883186,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_precision_stderr": 0.0017717045986566685
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_recall": 0.2805432315584404,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_recall_stderr": 0.004032930733728556
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_fmeasure": 0.15982873334149725,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_fmeasure_stderr": 0.0023425475142972094
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_precision": 0.019940357227904496,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_precision_stderr": 0.0008871654413527542
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_recall": 0.05092689357974137,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_recall_stderr": 0.002312862164867138
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_fmeasure": 0.028224641804303584,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_fmeasure_stderr": 0.0012456728390026997
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_precision": 0.091309067638146,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_precision_stderr": 0.001329012931152222
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_recall": 0.2262763383066154,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_recall_stderr": 0.003168321456722403
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_fmeasure": 0.12819849475633416,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_fmeasure_stderr": 0.0017636438268745173
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_precision": 0.09096322959488826,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_precision_stderr": 0.001426421358110679
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_recall": 0.22637426285655501,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_recall_stderr": 0.0034475762418152184
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_fmeasure": 0.12790721086358273,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_fmeasure_stderr": 0.0019153745973360782
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"bleu": 1.0412116160191136,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"bleu_stderr": 0.06275428072510103
}
],
"config": {
"model": "hf-causal",
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-c4-repetitions/2b855b14bc4/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
"task_args": "",
"num_fewshot": 1,
"batch_size": 16,
"device": "cuda",
"use_cache": false,
"limit": 3000,
"bootstrap_iters": 10,
"seed": 1234
}
}