evaluation_bloomz-7b1-p3/evaluation_val/agg.limited=3000.model=p31lossseqglobal_step1000.task=mlsum_es.templates=palm_prompt.fewshot=0.batchsize=16.seed=1234.timestamp=2022-09-09T23:48:40.json

{"results": [{"task_name": "mlsum_es", "prompt_name": "palm_prompt", "bleu": 3.341310161344892, "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": 0.12383760876849086}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge1_precision": 0.2238936517609025, "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": 0.002299862104308459}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge1_recall": 0.31290976115097796, "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": 0.003157461966656448}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge1_fmeasure": 0.23872886986952627, "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": 0.0021217578248352883}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge2_precision": 0.06209477646349353, "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": 0.001551591733457607}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge2_recall": 0.09261450488619867, "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": 0.002338770523626696}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rouge2_fmeasure": 0.06770985280514573, "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": 0.0016286057939871985}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeL_precision": 0.16744902972078152, "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": 0.001881884121187265}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeL_recall": 0.23426964040901505, "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": 0.0025983311247854634}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeL_fmeasure": 0.17833059997868725, "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": 0.0017648367718678965}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeLsum_precision": 0.1755707446810662, "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": 0.0019188012583382194}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeLsum_recall": 0.24827775226125046, "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": 0.0027727938693488186}, {"task_name": "mlsum_es", "prompt_name": "palm_prompt", "rougeLsum_fmeasure": 0.1876134227034203, "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": 0.0018064283175187946}], "config": {"model": "hf-causal", "model_args": "pretrained=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000,use_accelerate=True,tokenizer=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000,dtype=float16", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}