lm1-4b2-84b-c4-repetitions / 4b284b21bc4 /evaluation /generation /slim.4b284b21bc4_gem_xsum_article_DOC_summary_1.json
Muennighoff's picture
Add files
a1243c9
raw
history blame
4 kB
{
"results": [
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_precision": 0.1344416388362992,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_precision_stderr": 0.0019127327308320389
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_recall": 0.33053933219336484,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_recall_stderr": 0.00435936977132835
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_fmeasure": 0.18885391905418497,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_fmeasure_stderr": 0.0025584792794476653
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_precision": 0.02919021495874484,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_precision_stderr": 0.001083579043412117
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_recall": 0.07395642387380598,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_recall_stderr": 0.0027833547930418757
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_fmeasure": 0.041352212313184845,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_fmeasure_stderr": 0.0015256985849036882
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_precision": 0.10283551822207533,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_precision_stderr": 0.0014281321188522025
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_recall": 0.25511273674645885,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_recall_stderr": 0.0034307162021354593
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_fmeasure": 0.1447818747001178,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_fmeasure_stderr": 0.001931305342910804
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_precision": 0.10637101855903888,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_precision_stderr": 0.0015675521812090556
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_recall": 0.26365396988763345,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_recall_stderr": 0.003725007857599503
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_fmeasure": 0.14973596762001254,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_fmeasure_stderr": 0.002121716066142779
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"bleu": 1.6712614198546765,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"bleu_stderr": 0.08029090892350033
}
],
"config": {
"model": "hf-causal",
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b21bc4/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
}
}