{ "results": [ { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "bleu": 3.343300117413671, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "bleu_stderr": 0.09571770719260354 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rouge1_precision": 0.2520284100970267, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge1_precision_stderr": 0.002624579613126546 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rouge1_recall": 0.25801030343845277, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge1_recall_stderr": 0.0029853006756947876 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rouge1_fmeasure": 0.2288764030119338, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge1_fmeasure_stderr": 0.002161872693599132 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rouge2_precision": 0.0620405891134654, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge2_precision_stderr": 0.001792104074524257 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rouge2_recall": 0.07046107840903996, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge2_recall_stderr": 0.002067824846818046 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rouge2_fmeasure": 0.05865599311701669, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge2_fmeasure_stderr": 0.0015962367564830823 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rougeL_precision": 0.19551927910705028, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeL_precision_stderr": 0.002202337925100599 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rougeL_recall": 0.19887535262571626, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeL_recall_stderr": 0.002438033895761126 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rougeL_fmeasure": 0.176509767972313, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeL_fmeasure_stderr": 0.0017890354543847523 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rougeLsum_precision": 0.1998439483673831, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeLsum_precision_stderr": 0.0022520268262764018 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rougeLsum_recall": 0.20409646438222273, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeLsum_recall_stderr": 0.0025514751069907436 }, { "task_name": "mlsum_es", "prompt_name": "layman_summ_es", "rougeLsum_fmeasure": 0.18031629233459825, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeLsum_fmeasure_stderr": 0.0018146301526451975 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/350mt0/xp3capmixnewcodelonglossseqglobal_step1750,use_accelerate=True,tokenizer=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/350mt0/xp3capmixnewcodelonglossseqglobal_step1750,dtype=float16", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234 } }