{ "results": [ { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "bleu": 3.1798181363636027, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "bleu_stderr": 0.11186670060245504 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge1_precision": 0.22243683019483318, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge1_precision_stderr": 0.0025163867913330275 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge1_recall": 0.2852722290772078, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge1_recall_stderr": 0.003171172872929976 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge1_fmeasure": 0.22609931277536174, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge1_fmeasure_stderr": 0.0022513761751812465 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge2_precision": 0.05973518770656727, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge2_precision_stderr": 0.001893687676123278 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge2_recall": 0.07895712586687036, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge2_recall_stderr": 0.0021825236706687757 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge2_fmeasure": 0.06124625613676503, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rouge2_fmeasure_stderr": 0.0017334783966114224 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeL_precision": 0.16887516659649215, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeL_precision_stderr": 0.002178357265241399 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeL_recall": 0.21318196705739953, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeL_recall_stderr": 0.002555636899506184 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeL_fmeasure": 0.16955218451285564, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeL_fmeasure_stderr": 0.0018846082416891987 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeLsum_precision": 0.1753893170918232, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeLsum_precision_stderr": 0.002217858281060236 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeLsum_recall": 0.22340887603027765, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeLsum_recall_stderr": 0.0027033960043687556 }, { "task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeLsum_fmeasure": 0.17665025797213654, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "rougeLsum_fmeasure_stderr": 0.0019283819849723594 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/176bt0/p31lossseq_global_step498,use_accelerate=True,tokenizer=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/176bt0/p31lossseq_global_step498,dtype=bfloat16", "num_fewshot": 0, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234 } }