lm1-4b2-84b-c4-repetitions / 4b284b21bc4 /evaluation /generation /slim.4b284b21bc4_gem_xsum_article_DOC_summary_4.json
Muennighoff's picture
Add files
a1243c9
{
"results": [
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_precision": 0.04293551268263482,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_precision_stderr": 0.0025300915700631186
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_recall": 0.08251909123638941,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_recall_stderr": 0.0047552295627311435
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_fmeasure": 0.052109895215743926,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_fmeasure_stderr": 0.0029325961974541494
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_precision": 0.008902116582691397,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_precision_stderr": 0.0007882814434287245
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_recall": 0.020355209333257882,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_recall_stderr": 0.0018399757489791825
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_fmeasure": 0.01203821663060757,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_fmeasure_stderr": 0.001058756941479336
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_precision": 0.03291018535700006,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_precision_stderr": 0.001988611171780747
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_recall": 0.06245660895956642,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_recall_stderr": 0.0036021201516783473
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_fmeasure": 0.039428572953528446,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_fmeasure_stderr": 0.002210624192813922
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_precision": 0.03518063964656488,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_precision_stderr": 0.0021155739741956746
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_recall": 0.0671088243853192,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_recall_stderr": 0.003920638757312349
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_fmeasure": 0.0423468971865807,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_fmeasure_stderr": 0.002398760878941016
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"bleu": 0.912241430159217,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"bleu_stderr": 0.1508779538575514
}
],
"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": 4,
"batch_size": 16,
"device": "cuda",
"use_cache": false,
"limit": 3000,
"bootstrap_iters": 10,
"seed": 1234
}
}