bloomz
/
evaluation_bloomz
/evaluation_val
/mlsum_es
/slim.limited=3000.model=xp3capmixnewcodelonglossseq_global_step498.task=mlsum_es.templates=palm_prompt.fewshot=0.batchsize=4.seed=1234.timestamp=2022-09-11T02:20:44.json
{ | |
"results": [ | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"bleu": 4.155428402841844, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"bleu_stderr": 0.13385139476742874 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rouge1_precision": 0.24619254732411308, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge1_precision_stderr": 0.0024831470256754013 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rouge1_recall": 0.3117827742604337, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge1_recall_stderr": 0.003195536871718303 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rouge1_fmeasure": 0.25337122760428693, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge1_fmeasure_stderr": 0.002292834308471866 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rouge2_precision": 0.07273490542705281, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge2_precision_stderr": 0.0018966264658225132 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rouge2_recall": 0.09639944399072355, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge2_recall_stderr": 0.0023803811434546587 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rouge2_fmeasure": 0.0764102814843215, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge2_fmeasure_stderr": 0.0018719981450326982 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rougeL_precision": 0.18574476795133907, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeL_precision_stderr": 0.0021245793603333414 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rougeL_recall": 0.2339554472733289, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeL_recall_stderr": 0.0026473792404859554 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rougeL_fmeasure": 0.19022987411946263, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeL_fmeasure_stderr": 0.0019583024425978233 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rougeLsum_precision": 0.19337241472874026, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeLsum_precision_stderr": 0.002172473379459937 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rougeLsum_recall": 0.24449955120220104, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeLsum_recall_stderr": 0.0027610430609216626 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "palm_prompt", | |
"rougeLsum_fmeasure": 0.1982216464293535, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeLsum_fmeasure_stderr": 0.002000958689349937 | |
} | |
], | |
"config": { | |
"model": "hf-causal", | |
"model_args": "pretrained=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/176bt0/xp3capmixnewcodelonglossseq_global_step498,use_accelerate=True,tokenizer=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/176bt0/xp3capmixnewcodelonglossseq_global_step498,dtype=bfloat16", | |
"num_fewshot": 0, | |
"batch_size": 4, | |
"device": "cuda", | |
"use_cache": false, | |
"limit": 3000, | |
"bootstrap_iters": 10, | |
"seed": 1234 | |
} | |
} |