bloomz
/
evaluation_bloomz
/evaluation_val
/mlsum_es
/slim.limited=3000.model=xp3capmixnewcodelonglossseq_global_step498.task=mlsum_es.templates=layman_summ_es.fewshot=0.batchsize=4.seed=1234.timestamp=2022-09-11T02:20:44.json
{ | |
"results": [ | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"bleu": 3.606126125049115, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"bleu_stderr": 0.1777428611437274 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rouge1_precision": 0.24897524860913609, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge1_precision_stderr": 0.002769352726963559 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rouge1_recall": 0.24862486574088613, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge1_recall_stderr": 0.0030999097459434703 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rouge1_fmeasure": 0.22369539928629967, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge1_fmeasure_stderr": 0.002355115682657273 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rouge2_precision": 0.06634301490578277, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge2_precision_stderr": 0.002048301218559081 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rouge2_recall": 0.06986753000720762, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge2_recall_stderr": 0.002064436828187958 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rouge2_fmeasure": 0.06070627110770783, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rouge2_fmeasure_stderr": 0.001726497816324924 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rougeL_precision": 0.1940954836427296, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeL_precision_stderr": 0.002431855538295837 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rougeL_recall": 0.18959437921291328, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeL_recall_stderr": 0.0025078934952384247 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rougeL_fmeasure": 0.1716590640884715, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeL_fmeasure_stderr": 0.001979894431520568 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rougeLsum_precision": 0.19939821083949505, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeLsum_precision_stderr": 0.0024800156414648273 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rougeLsum_recall": 0.19543176650107444, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeLsum_recall_stderr": 0.0025892786548937794 | |
}, | |
{ | |
"task_name": "mlsum_es", | |
"prompt_name": "layman_summ_es", | |
"rougeLsum_fmeasure": 0.17657777023351298, | |
"dataset_path": "GEM/mlsum", | |
"dataset_name": "es", | |
"subset": "", | |
"rougeLsum_fmeasure_stderr": 0.002018383139682419 | |
} | |
], | |
"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 | |
} | |
} |