lm1-4b2-84b-oscar-repetitions / 4b284b28boscar /evaluation /generation /slim.4b284b28boscar_GEM-wiki_lingua_en_tldr_en_2.json
Muennighoff's picture
Add files
8170937
raw
history blame contribute delete
No virus
4.09 kB
{
"results": [
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge1_precision": 0.3042280180045783,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge1_precision_stderr": 0.0036548780493867858
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge1_recall": 0.2657722896569855,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge1_recall_stderr": 0.002856010555746096
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge1_fmeasure": 0.2423480992295036,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge1_fmeasure_stderr": 0.002213386982039197
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge2_precision": 0.09313769731615627,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge2_precision_stderr": 0.002310899996162063
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge2_recall": 0.07567489802793778,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge2_recall_stderr": 0.00165355417900699
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge2_fmeasure": 0.0696826972387138,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge2_fmeasure_stderr": 0.00138974451583577
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeL_precision": 0.23678748519073842,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeL_precision_stderr": 0.0030313841471723817
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeL_recall": 0.2052468833712137,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeL_recall_stderr": 0.002285031155511772
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeL_fmeasure": 0.18663522201860716,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeL_fmeasure_stderr": 0.001740118367633801
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeLsum_precision": 0.28748422717826916,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeLsum_precision_stderr": 0.0035473688052382567
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeLsum_recall": 0.24946630704943015,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeLsum_recall_stderr": 0.0026967966099014384
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeLsum_fmeasure": 0.22792203815398218,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeLsum_fmeasure_stderr": 0.0021140458556974436
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"bleu": 4.453155894580253,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"bleu_stderr": 0.07102095729922746
}
],
"config": {
"model": "hf-causal",
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b28boscar/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
"task_args": "",
"num_fewshot": 2,
"batch_size": 16,
"device": "cuda",
"use_cache": false,
"limit": 3000,
"bootstrap_iters": 10,
"seed": 1234
}
}