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

{"results": [{"task_name": "mlsum_es", "prompt_name": "palm_prompt", "bleu": 3.619325486335941, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.179919419902639}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge1_precision": 0.24780663444349338, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002507147956018597}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge1_recall": 0.27545135338282833, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003003125501891925}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge1_fmeasure": 0.23676009275524143, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021301319931734007}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge2_precision": 0.0640710564358735, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0017900238806753247}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge2_recall": 0.07767444430106467, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0021965535248787645}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge2_fmeasure": 0.06294952611868992, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016498514297430393}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeL_precision": 0.1901311887539964, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002107469317872449}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeL_recall": 0.2111905723569327, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002518349475307121}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeL_fmeasure": 0.18117329279306474, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017908424050208493}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeLsum_precision": 0.19470439311305227, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002151332052117866}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeLsum_recall": 0.21735203759781344, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0026235912805025272}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeLsum_fmeasure": 0.18538806816923076, "fixed_answer_choice_list": null, "dataset_path": "GEM/mlsum", "dataset_name": "es", "subset": "", "prompt_id": "e3c60771-5e99-49b1-b477-c2b69f645d59", "prompt_jinja": "I will first show a news article and then provide a summary of it in Spanish:\nArticle: {{text}}\n ===\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018064286752298999}], "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}}