evaluation_val/mlsum_es/agg.limited=3000.model=350mt0_xp3capmixnewcodelonglossseqglobal_step1750.task=mlsum_es.templates=summarise_this_in_es_few_sentences.fewshot=0.batchsize=16.seed=1234.timestamp=2022-10-08T13:34:03.json

{"results": [{"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "bleu": 2.2882710041529153, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.13207303223436284}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge1_precision": 0.22651610428388194, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0025544747897463032}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge1_recall": 0.27912823578913315, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0030975001090301035}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge1_fmeasure": 0.2189869273902612, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002121244091390277}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge2_precision": 0.055842105602095085, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0015575440347090582}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge2_recall": 0.07587543663337117, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0021035214347602566}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rouge2_fmeasure": 0.055896502176123325, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001443062190482965}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeL_precision": 0.1739623288648582, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002091198749309696}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeL_recall": 0.21461276288961498, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0025095083723608315}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeL_fmeasure": 0.16731035227157529, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001707299917111998}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeLsum_precision": 0.1782157403124354, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0021381828458997194}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeLsum_recall": 0.22125747931306458, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002679305378482259}, {"task_name": "mlsum_es", "prompt_name": "summarise_this_in_es_few_sentences", "rougeLsum_fmeasure": 0.17158408384663376, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "5e644239-d989-4531-b2ff-44b0e4310df6", "prompt_jinja": "{{text}}\n===\nGiven the above document, write few sentences in Spanish to summarize: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001743083120213333}], "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}}