diff --git a/.gitattributes b/.gitattributes index 232c6bc243207c3c952ee36a0d3e1e4dfa84181e..7209fd38324399a0f5f0a6ba67e34084b48015c3 100644 --- a/.gitattributes +++ b/.gitattributes @@ -516,3 +516,27 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text 4b284b28bc4seed3/evaluation/generation/examples.4b284b28bc4seed3_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text 4b284b42bc4seed3/evaluation/generation/examples.4b284b42bc4seed3_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text 4b284b84bc4v2seed1/evaluation/generation/examples.4b284b84bc4v2seed1_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2b222afd6861eb7441df5889fb538651b9752543 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.4137289209321652, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.03592840698985395}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.08052703538584219, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017032922927436723}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.34685731924417923, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004696819146262294}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.12202957876438714, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020897173297206215}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.0371963393448065, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001000406080573449}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.16920772861048264, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003352502998815072}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05709876588901533, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001338487535015282}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07642927515383495, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0015283993241970184}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.33488912829275347, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0045599664755635915}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.11638689693482958, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018866066835855856}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.07604904600865044, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015809038296551435}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.32815010771859937, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004354254520219142}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.11524865510935987, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001924801119419314}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.json new file mode 100644 index 0000000000000000000000000000000000000000..e7458bc1c9e5b9cb0a92e6c13d714526fe2ec721 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.44320235453851886, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.038654580038729125}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.0788292625128184, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001545865630724369}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.34898005560018197, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004794912547747137}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.12119128966268897, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020394652462786458}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03674083737130746, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009509963850229752}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.17151623711827377, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0034511631482392565}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.056707072109866384, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001298880402066703}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07498774748969433, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013853305220861518}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.33741306095617796, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004672233537657657}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.1158600041349514, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018669882568564582}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.07464447143195571, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001449910621324083}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.3300443408931697, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0044396729039993124}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.11473200282386622, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019120368338142416}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e0ea19f7c09d1215e5701f803fe14743a440b043 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.4318507139656118, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.020126652103215823}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07846937247932836, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015076119882704358}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.3512872090522125, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004843993030116799}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.1211597172909803, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002024707920166121}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03689332195406738, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000921539572592384}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.17407998451855428, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003436093615166077}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.057190355206892265, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0012758800698632082}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07486170965273004, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013700867024842227}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3400276434993588, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004727704994934382}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.11605588796630185, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018703477264729452}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.07425974001821288, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001410836040797904}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.33236868938870073, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004471409789333774}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.1146567492990496, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018940503662138908}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.json new file mode 100644 index 0000000000000000000000000000000000000000..041b098fbc12490cbcd93e1c7261f92b9ca32337 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.437820931259575, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.032980906480770865}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.0785926975391468, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015293603423737205}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.3493939393936786, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004787694752084967}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.12105811695552406, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002038435380001679}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03703345126698836, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009394498824059976}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.17399497492711738, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0034376201679732726}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05729780671036665, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0012917575350816215}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07468535679699133, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013893206714726519}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.33714313164357695, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004665286047497972}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.11550661899372622, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001880977056199583}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.07441958215060634, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014367820161710976}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.3308931008083881, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004444824580452303}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.11457534646291556, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019112644015919146}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.json new file mode 100644 index 0000000000000000000000000000000000000000..07b4ca6e7511ab1dc5adb4d7f54146822eeee305 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.44162298156671387, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.03391466255022238}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07809208129692338, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0014897473758506577}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.3509704340756107, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004753376988143335}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.12061836300623924, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0019968483074851587}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03681990692658017, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000915025627561909}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.17569168523985457, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003469639579874031}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05717656346160751, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001268286668919329}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07430240518062578, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001356662158276597}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.33848067082117866, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004630272763143682}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.11522040390086466, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018477157862829916}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.0737119127298611, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0013930977884493516}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.33180763273757674, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0044219813999489994}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.11384094914867832, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018639383740272559}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.json new file mode 100644 index 0000000000000000000000000000000000000000..87803bc41b5dbf044893cf0a26922447db1b81e2 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.43584026292753897, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.03585233394325135}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.0771055828854556, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001542950246478603}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.3485317236937699, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004899363014116322}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.11885306502412998, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020096665427829846}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03635257403197826, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009726184426252793}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.17491992097726822, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003638732362333741}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.056226522227932986, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0012937028286243123}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07302888437056451, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013873752417405871}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3349645978185685, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004754512380009764}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.11305367539046324, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018447783930060325}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.07261259826097624, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001427137555756464}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.3288098925316197, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004531291754719013}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.11195050334054779, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001866391249607523}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d6fe36a9c7cc115309e0cd0a661fc37d3a644d77 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.082701062500984, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0011114690924738965}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.12060845181501477, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.001294419304833145}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.09138645256779954, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001016337895874407}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.004221824477192578, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00022695165818508478}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.005013826064972669, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0002886749356995342}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.004231279339262943, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00021788523328651946}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.07584986609826198, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0009625240871993999}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.11285337234897329, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0012181187217990192}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.08450530803702978, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.000901554006313133}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.07385235192113547, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0009724143584799478}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.10890947711749421, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.001166359192980158}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.08182685699093503, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0008824530614132399}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.049986883599927444, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.007715281553787714}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..bc214987a2a3da551d5f43967053503b04f9587b --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.10817533987287839, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001557158831062884}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.17611373045605921, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0022577581661268067}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.1243815766776328, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0015555535464807611}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.011131441628753095, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0004968420013755639}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.01944327988697502, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0009397177797597168}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.012970684860542986, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.000559978352567754}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.08784703908570092, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0010678467138718758}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.14780695365208887, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0017330218043806387}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.10222393170091604, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001072599197742085}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.10103160064031973, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014463815800196036}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.16516729505216035, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0021165463983442577}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.11629483720068202, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0014424904565344696}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.6846935681911303, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.048520060976790166}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..aed1864c88ccceba88f2bb1e2f447d2f4b6da90c --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.11722745375161758, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0016710911856635707}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.19369245188326673, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024549618061264467}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.13555617621093394, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0016918864606359741}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.015714560769775038, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005800745400016176}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.028401953794142447, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0011788887815516438}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.018558312186827172, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0006667508176160621}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.09440630375692156, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0011423074011562776}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.16112301920239752, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019113881872497018}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.11035639324221315, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.00116330079987278}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.10875530149178837, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001540487913238783}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.18075066689057118, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002307538960280241}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.12597857991599187, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0015636832895239018}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.924456967620158, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.03559680289475058}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..e7480ecd6e25d5f1920b4394a969f84d81bf2dd8 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.11737973030479486, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0020068624954179474}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.190625289714194, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0029906981571119883}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.13144771127478205, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0019737365577617576}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.019855590629909, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0006805588907016732}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.035136977735741294, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0012979131621517655}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.022809767017555965, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0007411221039709219}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.09211895227457069, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001463335123058735}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.1532140325253042, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0023289864471671166}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.10364321400933231, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014077752246067334}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.10903674502952361, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0018618317785407703}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.17719145160862762, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002790477962341549}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.12201579783859283, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018234148242418614}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.3233423451404336, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05997841498906398}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8e69e45a5427f6cc768bba6036ac8ca296972072 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.04521455263428701, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001817051799470601}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.07167001920005753, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0026297817119641954}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.047822320448517586, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0017110762026540103}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.008537546793712486, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005451212697125958}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.015535161953539139, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0010082854476503452}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.009630515215905031, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0005703572936436381}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.03581845161408539, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001454348764904071}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.05736959242350815, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0020694778242817827}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.037591797438144656, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0012882375080276282}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.04226563254674496, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001724425679642684}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.0664662102163325, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0024427933119544}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.04440192076877557, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0015922060897516483}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.3613016066707259, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.036915701681708164}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..93c5a3cc8f954c2382a45af62f16d23e16136f25 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.007307470265602752, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0007897900183615145}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.011510813177556005, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0011552914746690388}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.00773346326426295, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0007772828239978309}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.001429085231861359, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00021883906441152553}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.002570423991576332, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00046790313160452587}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.0015852585648270666, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00022806743110909383}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.005352988837771441, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0005537181118288242}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.00878014362052647, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0008837201326346826}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.005728100957946406, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0005516850094907344}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.006777901778057594, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0007374290911612345}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.010579350524900687, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0010634321336190457}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.007108428092699879, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0007115175993630998}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 3.525168786175522e-07, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 5.612162101464965e-07}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.json new file mode 100644 index 0000000000000000000000000000000000000000..bc01454ce6d976d3b9580f049e1b4fc6e06a7c62 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 0.043151087658762945, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0032342340375698313}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.06495149327905961, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0006154921660754954}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.13370167404751163, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0010189486890049794}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.08500629167730897, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0006989135591713463}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.0035303832289245198, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0001527456230237433}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.007319549034551619, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00032488894186680385}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.0046873222992475675, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0002022412956316276}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.06359934650707177, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0005723430187186213}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.13157140403081988, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0009812226045655013}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.08337201239477712, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.000651472451774746}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.05504912687523559, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0005196674711591116}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.11355464831908403, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0008466893831039181}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.07193972974334535, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0005686183231544299}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d1ad29430d3265ac5d76498ef38c7d532ace623a --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 5.257466769424374, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.07357547724601604}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.23786938588769446, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002104681875527956}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.4121530298560502, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0030089320928001376}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.28148883433290234, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001923209524922163}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.09021145181730728, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0012485251931366231}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.16603227142774246, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002026618225842661}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.10965942344261605, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001266910542618815}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.193582677648821, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001580931677078503}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.34417212574068223, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0025977918681195948}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.23105487418644294, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014408012821073104}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.19491877857913123, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001917333394119044}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.3349539368345205, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0027000371649433153}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.22905909984905182, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0017314569916895598}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.json new file mode 100644 index 0000000000000000000000000000000000000000..d873d52dec5589edbf8146c973ebe5e7e402cc8d --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 6.5539390861720035, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.11033075795685604}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.2903404594422581, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0024584696959761548}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.4333135279478913, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002735582379776765}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.32505406392907477, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0019673064297673175}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.12271979460763294, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0015962080243060197}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.1876592718803383, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002021534025159006}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.13810992950827863, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001444581219830018}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.22365724489731642, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0018056307126048264}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.345401861303691, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0024446936487181117}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.2534760790754178, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014777484527935105}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.2395654073443738, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00223173839964408}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.35566140454139644, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0025565410886410314}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2673001651581832, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018598623220801944}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.json new file mode 100644 index 0000000000000000000000000000000000000000..0a87de342290e8da7407518d9ed7a0db873a22ba --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 7.802031385100445, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.12520230313336564}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.3338557482843276, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002551971432391476}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.438621126600984, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0026752980677359345}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.3574815420785405, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020170776348172677}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.14777645169229991, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001697278469314969}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.1968122332214139, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0020328947895924005}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.15830106057751542, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001543718964396758}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.24519327081461934, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0018824234987225013}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.33120052143267326, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002370647416558713}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.26474191187216406, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0015211355756810816}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.2764593808821877, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002325889733406939}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.36160015573781135, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00249846394269229}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.29524890844717644, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019147519696928641}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b43b3844839fb495525d339c4390734cd48d3dfb --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 8.382191502210562, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.14919541969359718}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.35487550391649403, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0025344302739034657}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.4361438966782426, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002544026410687206}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.37167375204035885, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001958486588378226}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.15717469519815827, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0017315413364928619}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.19553331645690575, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001973839383704276}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.1643064184413658, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0015388346414606316}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.2558302815927228, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0019085151038414955}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.3217813559039779, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002287943298156401}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.269902657132463, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001559683698964203}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.29398198190868147, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0022912359575795035}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.3619119446078494, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0024413151060046338}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.3079430786135033, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018787126708384577}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4ca7bd729577e2f65b6a64d489f430e25346610d --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 8.434096593422941, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.12374952402155545}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.3663947022200451, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0025940276035361334}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.4374444751473449, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002477034708943807}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.3784865425574256, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0019280406579030697}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.1621778484306982, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0017550698361701628}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.19557321714564072, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001918438736692879}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.1672452517241617, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0015293774465050592}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.2631916594457156, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0019344484995491348}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.32194602376614945, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0022606742323408495}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.27416374665856746, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0015606439952248043}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.30450332346607173, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002324281011297584}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.36375181614652935, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002343908164411574}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.3146193040515442, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018454927016279012}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.json new file mode 100644 index 0000000000000000000000000000000000000000..9898509b8fdb3e57169e73cbbfb377f3a5201790 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.08342489348341924, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0012842607244636889}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.18313462458030272, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0022833897865371204}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.11289013583650749, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0015241960402614591}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.006807640108939664, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0004546616697105076}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.014646684932925907, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0008582893632378247}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.00907913529407834, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0005360706812311225}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.07075720554200345, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0010438807547277764}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.1570230345629149, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001966731475785525}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.09604887262918436, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0012450372296769945}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.06903402748086229, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0010262159629070258}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.15315001526257727, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00192242995222989}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.09369805182267531, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0012217813043505867}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.2362860989119941, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06515733012952077}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.json new file mode 100644 index 0000000000000000000000000000000000000000..fc3bfbe9e01c58fc34930cc6bc2f994f87740fe0 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.0685738400230712, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0012614794489907162}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.16764066671392627, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0028556162454937625}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.09612718872859236, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0016940816359247253}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.00687822694283814, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005061346255521965}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.017217988643461746, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001286522520281308}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.009694349099296177, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0007117075020582719}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.06179089290304659, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001050543101974293}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.15154479594716758, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0024146601749356305}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.08667789904325363, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014098828990377955}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.058639097301684553, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0010116604269926539}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.14457668621942818, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0023919173520257917}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.08238177966767227, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0013689020999623559}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.37834186143792814, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.07579632209521951}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.json new file mode 100644 index 0000000000000000000000000000000000000000..1ffb2fb67a264eb98656cf94eb70b36271c79e50 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.07431434923410046, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015283612791276602}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.1827918011387138, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003586036642211407}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.10437600774672044, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00207952100569553}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.009246404787084099, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0006013153673346344}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.02349062031177244, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001548636822631295}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.013095799671134395, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0008489058427507967}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.06564873824136315, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012078804697379189}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.16191451646036112, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002884321850290769}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.09226827959916255, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016450494129720853}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.06260025314838306, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0012121969148993826}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.15522785504407458, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002921032689214908}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.08811439184894636, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001657196039152884}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.4849143382987017, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.04905432423972044}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.json new file mode 100644 index 0000000000000000000000000000000000000000..9558b25d27ff4db6277eb57d6bc2413d28a45718 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.07801541338302878, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018173640538940942}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.18154402515522824, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003824785983248113}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.10584203948827893, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022277495525711575}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.01034600818070244, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007057473078572547}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.024986150502265235, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001692210317983424}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.014219210333358922, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009311822269523914}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.0678536492661622, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0014739423841839488}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.1585838156145662, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0030943555602493257}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.09228122264940566, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001790178384835284}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.06570229340369058, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014813914622807897}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.1543154445584897, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0031794372645773186}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.08945125770061474, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018164527031048951}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.5746056304031278, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.03416800265114781}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.json new file mode 100644 index 0000000000000000000000000000000000000000..a7fcd33de42289c4a1e9242b0af5be84b9a63851 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.03064279607658244, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0022965807355317283}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.05195082603025642, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003220539005393162}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.03399511479025987, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020729464765277573}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.004284009012383848, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005485208167059648}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.008382344530163326, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001000201966734194}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.005260596389372223, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0006214146366789691}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.025526009580683906, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0018894407281977873}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.04350947253111104, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002619339324653331}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.028356576842958853, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016783975883159549}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.025412397431441656, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0019050756306301015}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.043137551559700685, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0026330951282367504}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.02809770605845126, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0016857742426147392}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.4651237596229011, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.11156128095981639}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.json b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.json new file mode 100644 index 0000000000000000000000000000000000000000..be992d29cea465e053c28c7fd65476af6567529f --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/agg.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.0021504887939511347, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0006247191105487891}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.001777814575528098, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0005039303650046605}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.001878489668702617, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0005292148091180053}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 5.717552887364208e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 5.7175528873642526e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 3.298588204248582e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 3.298588204248464e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 4.1835752834372257e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 4.183575283437121e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.0018915873488676697, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0005354926007169597}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.0016022233245543466, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00045106425429012806}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.0016730266584955929, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.00046229330330986443}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.0018136207185854307, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0005184093493039095}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.0015526690795628231, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0004429788793808031}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.0016122575588416806, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00045030733547815735}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 1.0502876017100983e-40, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 9.258629322298703e-36}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..914c8c96b8e4d3bc9f0dc5f04759d471744174b4 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9455cf30d6dac9b0255464925e866b630a7f79c17bb0e4a0c023172aa1262027 +size 4113873 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..810e47598ec68437c88529c89f52a40c83bde20f --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c983393809690c7c25f08a4caef553ae357c1fb6e8e7db09d025c6acd1b029 +size 5036769 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7b0a91dd882119bdf10e59c4e74b811380141801 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aab560c6c5651ae8cd3cdb101bdc6c5e4416a1c0f57da53565f8c3927a093cdc +size 5931023 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..46de792015361dd27104c321a452c438bd162ac0 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6beba663d78b725a8ae29eaddd053c57ca1c1efaa944861ce1052f8cb683414 +size 6843193 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b1d56381621371ad691075cec025cc3bb415e2ad --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b63d0ea02fa1bf697927726ed9963f37ca42e46e49c1805feed3237a97f2da95 +size 7745554 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9b7f6c380924297693fac8e9200141a8b69d8132 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a858a5c3f18bd7a5d9b61a014e7846bc504ac0c699d2dc7c0bfb74214a40b5 +size 8647738 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cac07b988baddbc6d682b7a2358dbad216f894cd --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9c1d38789465e68bb65fb0989942e06619b3ce043169aa9f7125efd36408c0 +size 7516544 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8f1375ab2128d33fc0a546f9e71a3f7c50cd4813 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0562d6b1e71c24cf301b42fc9b0f35b698192d4ab87c8f52b649996ce2f59bbe +size 13240933 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3a8889186e911f946e5dd404ae8a8935ac9e4b56 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc1f1600969516ac50d3b99579ea02cdb77bb1b245fc9ed5f1fe081db49fe4a +size 18843213 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bf4a83999260978e070fb232620fe238c21f86fb --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9691622401d9b8aeb0010d33949b20e262bed56c3c9b42b90bc184e9bda77c1 +size 24298344 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a8db194b0fd17a4451e71588e3068ba453eee1af --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4af1733f200bfa24f99f5e093f9fdfb716191e6387ad8bdde5cba2bbcd76b1a +size 29468077 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..545a0d4ad954eacc860902ac58446350154e808e --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49a98f0fbb47564ddf61f5b06d359ef4e6bd0bfa56ff54e1f5a2a946789230d4 +size 34799354 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..da6752976640a40bc917d3f263b67494d6de023e --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:139e641654606784359401881589ee31eff6bf0d9d339362c5d846509af96d49 +size 4483635 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3e503be1748f31ced3d5908480658d42e363cc40 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71d3ade76a38e8a3cbd0ebafabf4f12614ef379b90a9a9b5ce84b23709fb151 +size 5481215 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..76789cb934873845f4bd6c02827804acb1c476d9 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eaff2367e5d6f888ef701769e8bac4b1fe9c5e45bbd01e91d085056b4fb07f3 +size 6476444 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..16cfc991f4648f7cb5ffdf0fdd2c17df3d5c296b --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f973c5959cf6097ad25a8a6008e7a76b53474c56c56327678f8965fcf4093b3 +size 7469953 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6842e8e26e1cd3a21381b3973b5c05bafe0d0b39 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a838fe0a04cdd4e26801344a5aa0b5649707d8a043590ef4d2105bb807ecd43 +size 8505837 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6ee1fc4ac4daf85d8f7edbe2b4664562f2f548ce --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3313cbc080ab723ec5e75790c45f3d048b3e440a171dc3711e0fce5c744d25b +size 9576547 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..51ab4b4f3a7b218a4bdaa38ba7e914d043cd661e --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e128405ff06a2204216879540df95d6cb10692a62f0ab53034ce021deb291470 +size 2809896 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ea12c72cf4bbec677bdfbd8f55e0b44d4b94a91c --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee9a2c5db869af04703594f3620ba6c5155ff1b9d9b3072f71ab061d11ca94a +size 5080844 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e69c376c71d939ccca732622c20eb8427130704e --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcbef67a8c8fba272e4030631438fdadf6f891ef2e4ff007a58ffcf20f6aab62 +size 7357255 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f372c70d308c8f27ade9512ae6daf8386f61a551 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d88cd9646e566bb6a7aaedeaf8fb9f0f5174a3a9bde82ee1c374efd4cb66b69 +size 9628751 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9158d50e14c9d9c27670c0f38082f198412960f8 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83214bcba27f550af666f13f46849b7c7a56fc1c95d8fed10fd9ca7eb7807bec +size 11668753 diff --git a/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.jsonl b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b983797bfe1fa65edf00ceb100dab317f6d76bad --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/examples.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6c9438ffb2eb9a5831feb66c337fdb240a745708b1f53ff8916992091f8fde +size 13897413 diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.json new file mode 100644 index 0000000000000000000000000000000000000000..f29dcf3228f6af355698e7c858724a562f138103 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.4137289209321652, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.03592840698985395 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.08052703538584219, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0017032922927436723 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.34685731924417923, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004696819146262294 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.12202957876438714, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0020897173297206215 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.0371963393448065, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.001000406080573449 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.16920772861048264, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.003352502998815072 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.05709876588901533, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001338487535015282 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.07642927515383495, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0015283993241970184 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.33488912829275347, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0045599664755635915 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.11638689693482958, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018866066835855856 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.07604904600865044, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0015809038296551435 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.32815010771859937, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004354254520219142 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.11524865510935987, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001924801119419314 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d5ce53a9aeb16928515993f71bc386c03252b2c5 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.44320235453851886, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.038654580038729125 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.0788292625128184, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001545865630724369 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.34898005560018197, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004794912547747137 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.12119128966268897, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0020394652462786458 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.03674083737130746, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0009509963850229752 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.17151623711827377, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0034511631482392565 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.056707072109866384, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001298880402066703 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.07498774748969433, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0013853305220861518 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.33741306095617796, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004672233537657657 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.1158600041349514, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018669882568564582 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.07464447143195571, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001449910621324083 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.3300443408931697, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0044396729039993124 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.11473200282386622, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019120368338142416 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.json new file mode 100644 index 0000000000000000000000000000000000000000..4ad9aa72a8a57d87f40740e07ddcead0978ca0ea --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.4318507139656118, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.020126652103215823 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.07846937247932836, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0015076119882704358 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.3512872090522125, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004843993030116799 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.1211597172909803, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002024707920166121 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.03689332195406738, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.000921539572592384 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.17407998451855428, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.003436093615166077 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.057190355206892265, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0012758800698632082 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.07486170965273004, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0013700867024842227 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.3400276434993588, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004727704994934382 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.11605588796630185, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018703477264729452 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.07425974001821288, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001410836040797904 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.33236868938870073, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004471409789333774 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.1146567492990496, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018940503662138908 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.json new file mode 100644 index 0000000000000000000000000000000000000000..9c67e5efe658e0f575919bf12493a024eba55256 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.437820931259575, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.032980906480770865 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.0785926975391468, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0015293603423737205 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.3493939393936786, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004787694752084967 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.12105811695552406, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002038435380001679 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.03703345126698836, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0009394498824059976 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.17399497492711738, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0034376201679732726 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.05729780671036665, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0012917575350816215 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.07468535679699133, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0013893206714726519 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.33714313164357695, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004665286047497972 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.11550661899372622, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.001880977056199583 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.07441958215060634, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0014367820161710976 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.3308931008083881, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004444824580452303 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.11457534646291556, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019112644015919146 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.json new file mode 100644 index 0000000000000000000000000000000000000000..86c8299b7988e7cb9065f37a44e7e1273aeb900f --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.44162298156671387, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.03391466255022238 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.07809208129692338, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0014897473758506577 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.3509704340756107, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004753376988143335 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.12061836300623924, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0019968483074851587 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.03681990692658017, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.000915025627561909 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.17569168523985457, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.003469639579874031 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.05717656346160751, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001268286668919329 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.07430240518062578, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001356662158276597 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.33848067082117866, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004630272763143682 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.11522040390086466, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018477157862829916 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.0737119127298611, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0013930977884493516 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.33180763273757674, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0044219813999489994 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.11384094914867832, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018639383740272559 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.json new file mode 100644 index 0000000000000000000000000000000000000000..da058177ab1268fdcdd55dbe0381f79903a4f39c --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-web_nlg_en_PALM_prompt_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.43584026292753897, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.03585233394325135 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.0771055828854556, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001542950246478603 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.3485317236937699, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004899363014116322 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.11885306502412998, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0020096665427829846 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.03635257403197826, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0009726184426252793 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.17491992097726822, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.003638732362333741 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.056226522227932986, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0012937028286243123 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.07302888437056451, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0013873752417405871 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.3349645978185685, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004754512380009764 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.11305367539046324, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018447783930060325 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.07261259826097624, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001427137555756464 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.3288098925316197, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004531291754719013 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.11195050334054779, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001866391249607523 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..9c0e9578300c0311d46f1f8cebc00ec14b467c70 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.082701062500984, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0011114690924738965 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.12060845181501477, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.001294419304833145 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.09138645256779954, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001016337895874407 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.004221824477192578, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00022695165818508478 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.005013826064972669, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0002886749356995342 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.004231279339262943, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00021788523328651946 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.07584986609826198, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0009625240871993999 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.11285337234897329, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0012181187217990192 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.08450530803702978, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.000901554006313133 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.07385235192113547, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0009724143584799478 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.10890947711749421, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.001166359192980158 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.08182685699093503, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0008824530614132399 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.049986883599927444, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.007715281553787714 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..1ab9dccc170b41671a14cf8f8f60c405231ef07c --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.10817533987287839, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001557158831062884 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.17611373045605921, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0022577581661268067 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.1243815766776328, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0015555535464807611 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.011131441628753095, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0004968420013755639 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.01944327988697502, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0009397177797597168 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.012970684860542986, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.000559978352567754 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.08784703908570092, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0010678467138718758 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.14780695365208887, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0017330218043806387 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.10222393170091604, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.001072599197742085 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.10103160064031973, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0014463815800196036 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.16516729505216035, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0021165463983442577 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.11629483720068202, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0014424904565344696 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.6846935681911303, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.048520060976790166 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..558a195b4dfba1836e77b803669074112a26ee0c --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.11722745375161758, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0016710911856635707 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.19369245188326673, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0024549618061264467 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.13555617621093394, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0016918864606359741 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.015714560769775038, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0005800745400016176 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.028401953794142447, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0011788887815516438 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.018558312186827172, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0006667508176160621 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.09440630375692156, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0011423074011562776 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.16112301920239752, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0019113881872497018 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.11035639324221315, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.00116330079987278 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.10875530149178837, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001540487913238783 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.18075066689057118, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.002307538960280241 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.12597857991599187, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0015636832895239018 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.924456967620158, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.03559680289475058 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..f8c39452ffb9f25a909dd1ada540a1da722ab71e --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.11737973030479486, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0020068624954179474 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.190625289714194, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0029906981571119883 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.13144771127478205, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0019737365577617576 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.019855590629909, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0006805588907016732 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.035136977735741294, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0012979131621517655 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.022809767017555965, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0007411221039709219 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.09211895227457069, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001463335123058735 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.1532140325253042, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0023289864471671166 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.10364321400933231, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0014077752246067334 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.10903674502952361, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0018618317785407703 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.17719145160862762, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.002790477962341549 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.12201579783859283, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018234148242418614 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 1.3233423451404336, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.05997841498906398 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..afdf632ad09dda5670ce67b658872cd932b6e6e2 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.04521455263428701, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001817051799470601 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.07167001920005753, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0026297817119641954 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.047822320448517586, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0017110762026540103 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.008537546793712486, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0005451212697125958 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.015535161953539139, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0010082854476503452 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.009630515215905031, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0005703572936436381 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.03581845161408539, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001454348764904071 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.05736959242350815, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0020694778242817827 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.037591797438144656, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0012882375080276282 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.04226563254674496, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001724425679642684 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.0664662102163325, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0024427933119544 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.04440192076877557, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0015922060897516483 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.3613016066707259, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.036915701681708164 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..a5860cb91f859980aa5aec18cb9b36eca38a5e33 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_GEM-wiki_lingua_en_tldr_en_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.007307470265602752, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0007897900183615145 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.011510813177556005, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0011552914746690388 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.00773346326426295, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0007772828239978309 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.001429085231861359, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00021883906441152553 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.002570423991576332, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00046790313160452587 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.0015852585648270666, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00022806743110909383 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.005352988837771441, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0005537181118288242 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.00878014362052647, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0008837201326346826 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.005728100957946406, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0005516850094907344 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.006777901778057594, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0007374290911612345 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.010579350524900687, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0010634321336190457 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.007108428092699879, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0007115175993630998 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 3.525168786175522e-07, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 5.612162101464965e-07 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.json new file mode 100644 index 0000000000000000000000000000000000000000..12c110a003fb089cd35f710926af775fb41b28d3 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 0.043151087658762945, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.0032342340375698313 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.06495149327905961, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0006154921660754954 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.13370167404751163, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0010189486890049794 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.08500629167730897, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0006989135591713463 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.0035303832289245198, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0001527456230237433 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.007319549034551619, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.00032488894186680385 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.0046873222992475675, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0002022412956316276 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.06359934650707177, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0005723430187186213 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.13157140403081988, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0009812226045655013 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.08337201239477712, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.000651472451774746 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.05504912687523559, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0005196674711591116 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.11355464831908403, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0008466893831039181 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.07193972974334535, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0005686183231544299 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.json new file mode 100644 index 0000000000000000000000000000000000000000..35281da5fac8b0bc89c85256f74c92abc4f2fa44 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 5.257466769424374, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.07357547724601604 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.23786938588769446, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.002104681875527956 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.4121530298560502, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0030089320928001376 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.28148883433290234, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.001923209524922163 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.09021145181730728, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0012485251931366231 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.16603227142774246, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.002026618225842661 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.10965942344261605, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001266910542618815 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.193582677648821, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.001580931677078503 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.34417212574068223, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0025977918681195948 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.23105487418644294, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0014408012821073104 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.19491877857913123, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.001917333394119044 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.3349539368345205, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0027000371649433153 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.22905909984905182, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0017314569916895598 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e2d4c4b9bb2bbbfba70fb55a6100b8b41995d4ca --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 6.5539390861720035, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.11033075795685604 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.2903404594422581, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0024584696959761548 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.4333135279478913, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002735582379776765 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.32505406392907477, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0019673064297673175 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.12271979460763294, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0015962080243060197 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.1876592718803383, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.002021534025159006 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.13810992950827863, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001444581219830018 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.22365724489731642, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0018056307126048264 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.345401861303691, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0024446936487181117 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.2534760790754178, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0014777484527935105 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.2395654073443738, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.00223173839964408 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.35566140454139644, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0025565410886410314 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.2673001651581832, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018598623220801944 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.json new file mode 100644 index 0000000000000000000000000000000000000000..f98155460c32a26e5f9d1199033b376331ce9c08 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 7.802031385100445, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.12520230313336564 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.3338557482843276, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.002551971432391476 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.438621126600984, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0026752980677359345 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.3574815420785405, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020170776348172677 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.14777645169229991, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.001697278469314969 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.1968122332214139, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0020328947895924005 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.15830106057751542, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001543718964396758 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.24519327081461934, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0018824234987225013 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.33120052143267326, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.002370647416558713 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.26474191187216406, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0015211355756810816 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.2764593808821877, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002325889733406939 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.36160015573781135, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.00249846394269229 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.29524890844717644, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019147519696928641 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.json new file mode 100644 index 0000000000000000000000000000000000000000..845839e9201dc1b9cb4dcfcb51509ecb9a39d89c --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 8.382191502210562, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.14919541969359718 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.35487550391649403, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0025344302739034657 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.4361438966782426, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002544026410687206 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.37167375204035885, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.001958486588378226 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.15717469519815827, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0017315413364928619 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.19553331645690575, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001973839383704276 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.1643064184413658, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0015388346414606316 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.2558302815927228, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0019085151038414955 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.3217813559039779, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.002287943298156401 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.269902657132463, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.001559683698964203 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.29398198190868147, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0022912359575795035 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.3619119446078494, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0024413151060046338 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.3079430786135033, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018787126708384577 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.json new file mode 100644 index 0000000000000000000000000000000000000000..b67dbca6c13fae92e2c1c06e40f410ae39e2a322 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_e2e_nlg_cleaned_generate_text_restaurant_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 8.434096593422941, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.12374952402155545 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.3663947022200451, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0025940276035361334 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.4374444751473449, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002477034708943807 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.3784865425574256, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0019280406579030697 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.1621778484306982, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0017550698361701628 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.19557321714564072, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001918438736692879 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.1672452517241617, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0015293774465050592 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.2631916594457156, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0019344484995491348 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.32194602376614945, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0022606742323408495 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.27416374665856746, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0015606439952248043 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.30450332346607173, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002324281011297584 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.36375181614652935, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002343908164411574 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.3146193040515442, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018454927016279012 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e3faae32f37c97a8bc4f6590dc40f45d4f390043 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.08342489348341924, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0012842607244636889 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.18313462458030272, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0022833897865371204 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.11289013583650749, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0015241960402614591 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.006807640108939664, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0004546616697105076 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.014646684932925907, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0008582893632378247 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.00907913529407834, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0005360706812311225 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.07075720554200345, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0010438807547277764 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.1570230345629149, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.001966731475785525 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.09604887262918436, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0012450372296769945 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.06903402748086229, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0010262159629070258 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.15315001526257727, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.00192242995222989 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.09369805182267531, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0012217813043505867 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.2362860989119941, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.06515733012952077 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.json new file mode 100644 index 0000000000000000000000000000000000000000..5b9c584025e83fa5ca84a9fe1ff00a857785c8fc --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.0685738400230712, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0012614794489907162 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.16764066671392627, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0028556162454937625 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.09612718872859236, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0016940816359247253 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.00687822694283814, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0005061346255521965 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.017217988643461746, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001286522520281308 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.009694349099296177, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0007117075020582719 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.06179089290304659, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.001050543101974293 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.15154479594716758, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0024146601749356305 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.08667789904325363, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0014098828990377955 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.058639097301684553, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0010116604269926539 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.14457668621942818, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0023919173520257917 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.08238177966767227, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0013689020999623559 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.37834186143792814, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.07579632209521951 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f55ba173134495c2e252c290d6457347bffc25fa --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.07431434923410046, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0015283612791276602 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.1827918011387138, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003586036642211407 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.10437600774672044, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.00207952100569553 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.009246404787084099, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0006013153673346344 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.02349062031177244, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001548636822631295 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.013095799671134395, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0008489058427507967 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.06564873824136315, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0012078804697379189 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.16191451646036112, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002884321850290769 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.09226827959916255, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016450494129720853 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.06260025314838306, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0012121969148993826 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.15522785504407458, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.002921032689214908 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.08811439184894636, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.001657196039152884 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.4849143382987017, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.04905432423972044 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.json new file mode 100644 index 0000000000000000000000000000000000000000..d845ca573d49ba6be0e1f96f98d245ad2743fad0 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.07801541338302878, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0018173640538940942 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.18154402515522824, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003824785983248113 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.10584203948827893, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0022277495525711575 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.01034600818070244, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0007057473078572547 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.024986150502265235, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001692210317983424 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.014219210333358922, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0009311822269523914 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.0678536492661622, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0014739423841839488 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.1585838156145662, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0030943555602493257 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.09228122264940566, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.001790178384835284 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.06570229340369058, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0014813914622807897 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.1543154445584897, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0031794372645773186 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.08945125770061474, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0018164527031048951 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.5746056304031278, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.03416800265114781 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.json new file mode 100644 index 0000000000000000000000000000000000000000..1b4179518e83f1b1f7727ade0ecd1b3ee13f6b9e --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.03064279607658244, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0022965807355317283 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.05195082603025642, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003220539005393162 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.03399511479025987, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0020729464765277573 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.004284009012383848, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0005485208167059648 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.008382344530163326, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001000201966734194 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.005260596389372223, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0006214146366789691 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.025526009580683906, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0018894407281977873 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.04350947253111104, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002619339324653331 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.028356576842958853, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016783975883159549 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.025412397431441656, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0019050756306301015 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.043137551559700685, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0026330951282367504 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.02809770605845126, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0016857742426147392 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.4651237596229011, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.11156128095981639 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.json b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.json new file mode 100644 index 0000000000000000000000000000000000000000..46a73b674f45c35fa125356f810e92162883390c --- /dev/null +++ b/4b284b12bc4seed1/evaluation/generation/slim.4b284b12bc4seed1_gem_xsum_article_DOC_summary_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.0021504887939511347, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0006247191105487891 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.001777814575528098, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0005039303650046605 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.001878489668702617, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0005292148091180053 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 5.717552887364208e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 5.7175528873642526e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 3.298588204248582e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 3.298588204248464e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 4.1835752834372257e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 4.183575283437121e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.0018915873488676697, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0005354926007169597 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.0016022233245543466, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.00045106425429012806 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.0016730266584955929, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.00046229330330986443 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.0018136207185854307, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0005184093493039095 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.0015526690795628231, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0004429788793808031 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.0016122575588416806, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.00045030733547815735 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 1.0502876017100983e-40, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 9.258629322298703e-36 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4seeds/4b284b12bc4seed1/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_0.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e79490b678ff52ad5bb5d7467f513c8a24b345d6 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_0.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.334, + "acc_stderr": 0.014922019523732967 + }, + "anli_r2": { + "acc": 0.325, + "acc_stderr": 0.014818724459095527 + }, + "anli_r3": { + "acc": 0.3441666666666667, + "acc_stderr": 0.013720551062295756 + }, + "cb": { + "acc": 0.4107142857142857, + "acc_stderr": 0.0663363415035954, + "f1": 0.1940928270042194 + }, + "copa": { + "acc": 0.79, + "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.46415056761601275, + "acc_stderr": 0.0049769393332400776, + "acc_norm": 0.6052579167496515, + "acc_norm_stderr": 0.0048779626449918555 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.0300523034631437 + }, + "winogrande": { + "acc": 0.5824782951854776, + "acc_stderr": 0.013859978264440251 + }, + "storycloze_2016": { + "acc": 0.7151256012827365, + "acc_stderr": 0.010437513986611718 + }, + "boolq": { + "acc": 0.591131498470948, + "acc_stderr": 0.008598573693259106 + }, + "arc_easy": { + "acc": 0.5660774410774411, + "acc_stderr": 0.010169795770462111, + "acc_norm": 0.5084175084175084, + "acc_norm_stderr": 0.010258329515226459 + }, + "arc_challenge": { + "acc": 0.26023890784982934, + "acc_stderr": 0.012821930225112568, + "acc_norm": 0.2790102389078498, + "acc_norm_stderr": 0.01310678488360133 + }, + "sciq": { + "acc": 0.829, + "acc_stderr": 0.011912216456264607, + "acc_norm": 0.751, + "acc_norm_stderr": 0.013681600278702301 + }, + "piqa": { + "acc": 0.7404787812840044, + "acc_stderr": 0.01022793988817392, + "acc_norm": 0.7431991294885746, + "acc_norm_stderr": 0.01019286480227804 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_0_lm-eval_global_step80108_2023-02-25-09-56-03_0shots_backup.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_0_lm-eval_global_step80108_2023-02-25-09-56-03_0shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..e79490b678ff52ad5bb5d7467f513c8a24b345d6 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_0_lm-eval_global_step80108_2023-02-25-09-56-03_0shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.334, + "acc_stderr": 0.014922019523732967 + }, + "anli_r2": { + "acc": 0.325, + "acc_stderr": 0.014818724459095527 + }, + "anli_r3": { + "acc": 0.3441666666666667, + "acc_stderr": 0.013720551062295756 + }, + "cb": { + "acc": 0.4107142857142857, + "acc_stderr": 0.0663363415035954, + "f1": 0.1940928270042194 + }, + "copa": { + "acc": 0.79, + "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.46415056761601275, + "acc_stderr": 0.0049769393332400776, + "acc_norm": 0.6052579167496515, + "acc_norm_stderr": 0.0048779626449918555 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.0300523034631437 + }, + "winogrande": { + "acc": 0.5824782951854776, + "acc_stderr": 0.013859978264440251 + }, + "storycloze_2016": { + "acc": 0.7151256012827365, + "acc_stderr": 0.010437513986611718 + }, + "boolq": { + "acc": 0.591131498470948, + "acc_stderr": 0.008598573693259106 + }, + "arc_easy": { + "acc": 0.5660774410774411, + "acc_stderr": 0.010169795770462111, + "acc_norm": 0.5084175084175084, + "acc_norm_stderr": 0.010258329515226459 + }, + "arc_challenge": { + "acc": 0.26023890784982934, + "acc_stderr": 0.012821930225112568, + "acc_norm": 0.2790102389078498, + "acc_norm_stderr": 0.01310678488360133 + }, + "sciq": { + "acc": 0.829, + "acc_stderr": 0.011912216456264607, + "acc_norm": 0.751, + "acc_norm_stderr": 0.013681600278702301 + }, + "piqa": { + "acc": 0.7404787812840044, + "acc_stderr": 0.01022793988817392, + "acc_norm": 0.7431991294885746, + "acc_norm_stderr": 0.01019286480227804 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_1.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_1.json new file mode 100644 index 0000000000000000000000000000000000000000..6bd0932431dc7c298c53127b475e844b3636a0dd --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_1.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.339, + "acc_stderr": 0.014976758771620342 + }, + "anli_r2": { + "acc": 0.323, + "acc_stderr": 0.014794927843348644 + }, + "anli_r3": { + "acc": 0.3441666666666667, + "acc_stderr": 0.013720551062295756 + }, + "cb": { + "acc": 0.5, + "acc_stderr": 0.06741998624632421, + "f1": 0.3261261261261261 + }, + "copa": { + "acc": 0.81, + "acc_stderr": 0.03942772444036623 + }, + "hellaswag": { + "acc": 0.4643497311292571, + "acc_stderr": 0.004977081808179424, + "acc_norm": 0.6074487153953396, + "acc_norm_stderr": 0.004873203269366301 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.030052303463143706 + }, + "winogrande": { + "acc": 0.5777426992896606, + "acc_stderr": 0.013881582030658549 + }, + "storycloze_2016": { + "acc": 0.7129877071084981, + "acc_stderr": 0.010460934115933261 + }, + "boolq": { + "acc": 0.5773700305810398, + "acc_stderr": 0.008639722698719023 + }, + "arc_easy": { + "acc": 0.6056397306397306, + "acc_stderr": 0.010028176038393004, + "acc_norm": 0.5606060606060606, + "acc_norm_stderr": 0.010184134315437663 + }, + "arc_challenge": { + "acc": 0.2721843003412969, + "acc_stderr": 0.013006600406423706, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.013438909184778764 + }, + "sciq": { + "acc": 0.847, + "acc_stderr": 0.01138950045966553, + "acc_norm": 0.792, + "acc_norm_stderr": 0.012841374572096928 + }, + "piqa": { + "acc": 0.7535364526659413, + "acc_stderr": 0.010054810789671824, + "acc_norm": 0.7595212187159956, + "acc_norm_stderr": 0.009971345364651068 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_1_lm-eval_global_step80108_2023-02-25-09-56-03_1shots_backup.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_1_lm-eval_global_step80108_2023-02-25-09-56-03_1shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..6bd0932431dc7c298c53127b475e844b3636a0dd --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_1_lm-eval_global_step80108_2023-02-25-09-56-03_1shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.339, + "acc_stderr": 0.014976758771620342 + }, + "anli_r2": { + "acc": 0.323, + "acc_stderr": 0.014794927843348644 + }, + "anli_r3": { + "acc": 0.3441666666666667, + "acc_stderr": 0.013720551062295756 + }, + "cb": { + "acc": 0.5, + "acc_stderr": 0.06741998624632421, + "f1": 0.3261261261261261 + }, + "copa": { + "acc": 0.81, + "acc_stderr": 0.03942772444036623 + }, + "hellaswag": { + "acc": 0.4643497311292571, + "acc_stderr": 0.004977081808179424, + "acc_norm": 0.6074487153953396, + "acc_norm_stderr": 0.004873203269366301 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.030052303463143706 + }, + "winogrande": { + "acc": 0.5777426992896606, + "acc_stderr": 0.013881582030658549 + }, + "storycloze_2016": { + "acc": 0.7129877071084981, + "acc_stderr": 0.010460934115933261 + }, + "boolq": { + "acc": 0.5773700305810398, + "acc_stderr": 0.008639722698719023 + }, + "arc_easy": { + "acc": 0.6056397306397306, + "acc_stderr": 0.010028176038393004, + "acc_norm": 0.5606060606060606, + "acc_norm_stderr": 0.010184134315437663 + }, + "arc_challenge": { + "acc": 0.2721843003412969, + "acc_stderr": 0.013006600406423706, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.013438909184778764 + }, + "sciq": { + "acc": 0.847, + "acc_stderr": 0.01138950045966553, + "acc_norm": 0.792, + "acc_norm_stderr": 0.012841374572096928 + }, + "piqa": { + "acc": 0.7535364526659413, + "acc_stderr": 0.010054810789671824, + "acc_norm": 0.7595212187159956, + "acc_norm_stderr": 0.009971345364651068 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_2.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_2.json new file mode 100644 index 0000000000000000000000000000000000000000..d34be2c98d249407f9ed9dc153e3169856dcc8bb --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_2.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.326, + "acc_stderr": 0.014830507204541037 + }, + "anli_r2": { + "acc": 0.337, + "acc_stderr": 0.014955087918653607 + }, + "anli_r3": { + "acc": 0.33416666666666667, + "acc_stderr": 0.013622434813136774 + }, + "cb": { + "acc": 0.42857142857142855, + "acc_stderr": 0.06672848092813058, + "f1": 0.26622479977906655 + }, + "copa": { + "acc": 0.81, + "acc_stderr": 0.039427724440366234 + }, + "hellaswag": { + "acc": 0.4629555865365465, + "acc_stderr": 0.004976067726432562, + "acc_norm": 0.609838677554272, + "acc_norm_stderr": 0.004867893927258165 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.0300523034631437 + }, + "winogrande": { + "acc": 0.5824782951854776, + "acc_stderr": 0.013859978264440246 + }, + "storycloze_2016": { + "acc": 0.7145911277391769, + "acc_stderr": 0.010443395884062115 + }, + "boolq": { + "acc": 0.5752293577981651, + "acc_stderr": 0.008645503833361106 + }, + "arc_easy": { + "acc": 0.5993265993265994, + "acc_stderr": 0.010055304474255573, + "acc_norm": 0.5694444444444444, + "acc_norm_stderr": 0.010160345396860082 + }, + "arc_challenge": { + "acc": 0.28071672354948807, + "acc_stderr": 0.013131238126975576, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.013438909184778766 + }, + "sciq": { + "acc": 0.844, + "acc_stderr": 0.011480235006122363, + "acc_norm": 0.794, + "acc_norm_stderr": 0.012795613612786548 + }, + "piqa": { + "acc": 0.7437431991294886, + "acc_stderr": 0.01018578783156506, + "acc_norm": 0.7524483133841132, + "acc_norm_stderr": 0.010069703966857116 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_2_lm-eval_global_step80108_2023-02-25-09-56-03_2shots_backup.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_2_lm-eval_global_step80108_2023-02-25-09-56-03_2shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..d34be2c98d249407f9ed9dc153e3169856dcc8bb --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_2_lm-eval_global_step80108_2023-02-25-09-56-03_2shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.326, + "acc_stderr": 0.014830507204541037 + }, + "anli_r2": { + "acc": 0.337, + "acc_stderr": 0.014955087918653607 + }, + "anli_r3": { + "acc": 0.33416666666666667, + "acc_stderr": 0.013622434813136774 + }, + "cb": { + "acc": 0.42857142857142855, + "acc_stderr": 0.06672848092813058, + "f1": 0.26622479977906655 + }, + "copa": { + "acc": 0.81, + "acc_stderr": 0.039427724440366234 + }, + "hellaswag": { + "acc": 0.4629555865365465, + "acc_stderr": 0.004976067726432562, + "acc_norm": 0.609838677554272, + "acc_norm_stderr": 0.004867893927258165 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.0300523034631437 + }, + "winogrande": { + "acc": 0.5824782951854776, + "acc_stderr": 0.013859978264440246 + }, + "storycloze_2016": { + "acc": 0.7145911277391769, + "acc_stderr": 0.010443395884062115 + }, + "boolq": { + "acc": 0.5752293577981651, + "acc_stderr": 0.008645503833361106 + }, + "arc_easy": { + "acc": 0.5993265993265994, + "acc_stderr": 0.010055304474255573, + "acc_norm": 0.5694444444444444, + "acc_norm_stderr": 0.010160345396860082 + }, + "arc_challenge": { + "acc": 0.28071672354948807, + "acc_stderr": 0.013131238126975576, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.013438909184778766 + }, + "sciq": { + "acc": 0.844, + "acc_stderr": 0.011480235006122363, + "acc_norm": 0.794, + "acc_norm_stderr": 0.012795613612786548 + }, + "piqa": { + "acc": 0.7437431991294886, + "acc_stderr": 0.01018578783156506, + "acc_norm": 0.7524483133841132, + "acc_norm_stderr": 0.010069703966857116 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_3.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_3.json new file mode 100644 index 0000000000000000000000000000000000000000..abc46a1af4298091c160131ae3bec321fcd80c2d --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_3.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.316, + "acc_stderr": 0.014709193056057127 + }, + "anli_r2": { + "acc": 0.337, + "acc_stderr": 0.014955087918653609 + }, + "anli_r3": { + "acc": 0.355, + "acc_stderr": 0.0138192490040473 + }, + "cb": { + "acc": 0.44642857142857145, + "acc_stderr": 0.06703189227942398, + "f1": 0.25805555555555554 + }, + "copa": { + "acc": 0.79, + "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4627564230233021, + "acc_stderr": 0.004975919665116542, + "acc_norm": 0.6117307309300936, + "acc_norm_stderr": 0.004863603638367434 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.0300523034631437 + }, + "winogrande": { + "acc": 0.5824782951854776, + "acc_stderr": 0.013859978264440251 + }, + "storycloze_2016": { + "acc": 0.711918760021379, + "acc_stderr": 0.010472537019822576 + }, + "boolq": { + "acc": 0.5831804281345566, + "acc_stderr": 0.008623192108843677 + }, + "arc_easy": { + "acc": 0.5896464646464646, + "acc_stderr": 0.010093531255765457, + "acc_norm": 0.571969696969697, + "acc_norm_stderr": 0.01015294331642626 + }, + "arc_challenge": { + "acc": 0.27559726962457337, + "acc_stderr": 0.013057169655761841, + "acc_norm": 0.30204778156996587, + "acc_norm_stderr": 0.013417519144716413 + }, + "sciq": { + "acc": 0.834, + "acc_stderr": 0.011772110370812184, + "acc_norm": 0.793, + "acc_norm_stderr": 0.012818553557843986 + }, + "piqa": { + "acc": 0.7480957562568009, + "acc_stderr": 0.010128421335088683, + "acc_norm": 0.7595212187159956, + "acc_norm_stderr": 0.009971345364651066 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_3_lm-eval_global_step80108_2023-02-25-09-54-24_3shots_backup.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_3_lm-eval_global_step80108_2023-02-25-09-54-24_3shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..abc46a1af4298091c160131ae3bec321fcd80c2d --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_3_lm-eval_global_step80108_2023-02-25-09-54-24_3shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.316, + "acc_stderr": 0.014709193056057127 + }, + "anli_r2": { + "acc": 0.337, + "acc_stderr": 0.014955087918653609 + }, + "anli_r3": { + "acc": 0.355, + "acc_stderr": 0.0138192490040473 + }, + "cb": { + "acc": 0.44642857142857145, + "acc_stderr": 0.06703189227942398, + "f1": 0.25805555555555554 + }, + "copa": { + "acc": 0.79, + "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4627564230233021, + "acc_stderr": 0.004975919665116542, + "acc_norm": 0.6117307309300936, + "acc_norm_stderr": 0.004863603638367434 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.0300523034631437 + }, + "winogrande": { + "acc": 0.5824782951854776, + "acc_stderr": 0.013859978264440251 + }, + "storycloze_2016": { + "acc": 0.711918760021379, + "acc_stderr": 0.010472537019822576 + }, + "boolq": { + "acc": 0.5831804281345566, + "acc_stderr": 0.008623192108843677 + }, + "arc_easy": { + "acc": 0.5896464646464646, + "acc_stderr": 0.010093531255765457, + "acc_norm": 0.571969696969697, + "acc_norm_stderr": 0.01015294331642626 + }, + "arc_challenge": { + "acc": 0.27559726962457337, + "acc_stderr": 0.013057169655761841, + "acc_norm": 0.30204778156996587, + "acc_norm_stderr": 0.013417519144716413 + }, + "sciq": { + "acc": 0.834, + "acc_stderr": 0.011772110370812184, + "acc_norm": 0.793, + "acc_norm_stderr": 0.012818553557843986 + }, + "piqa": { + "acc": 0.7480957562568009, + "acc_stderr": 0.010128421335088683, + "acc_norm": 0.7595212187159956, + "acc_norm_stderr": 0.009971345364651066 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_4.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_4.json new file mode 100644 index 0000000000000000000000000000000000000000..f2ae67f02b17af580c2c82aa51754a8399e7cbe8 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_4.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.323, + "acc_stderr": 0.014794927843348633 + }, + "anli_r2": { + "acc": 0.317, + "acc_stderr": 0.014721675438880236 + }, + "anli_r3": { + "acc": 0.3625, + "acc_stderr": 0.013883037874225516 + }, + "cb": { + "acc": 0.35714285714285715, + "acc_stderr": 0.06460957383809221, + "f1": 0.19573820395738203 + }, + "copa": { + "acc": 0.79, + "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4592710615415256, + "acc_stderr": 0.004973199296339971, + "acc_norm": 0.6106353316072496, + "acc_norm_stderr": 0.00486609688094144 + }, + "rte": { + "acc": 0.5126353790613718, + "acc_stderr": 0.030086851767188564 + }, + "winogrande": { + "acc": 0.585635359116022, + "acc_stderr": 0.013844846232268565 + }, + "storycloze_2016": { + "acc": 0.7194013896312133, + "acc_stderr": 0.01038980964728882 + }, + "boolq": { + "acc": 0.5755351681957187, + "acc_stderr": 0.008644688121685498 + }, + "arc_easy": { + "acc": 0.5942760942760943, + "acc_stderr": 0.010075755540128873, + "acc_norm": 0.5757575757575758, + "acc_norm_stderr": 0.010141333654958552 + }, + "arc_challenge": { + "acc": 0.2790102389078498, + "acc_stderr": 0.013106784883601333, + "acc_norm": 0.30802047781569963, + "acc_norm_stderr": 0.013491429517292038 + }, + "sciq": { + "acc": 0.835, + "acc_stderr": 0.01174363286691616, + "acc_norm": 0.788, + "acc_norm_stderr": 0.01293148186493805 + }, + "piqa": { + "acc": 0.7540805223068553, + "acc_stderr": 0.010047331865625194, + "acc_norm": 0.7589771490750816, + "acc_norm_stderr": 0.009979042717267314 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_4_lm-eval_global_step80108_2023-02-25-09-56-03_4shots_backup.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_4_lm-eval_global_step80108_2023-02-25-09-56-03_4shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..f2ae67f02b17af580c2c82aa51754a8399e7cbe8 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_4_lm-eval_global_step80108_2023-02-25-09-56-03_4shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.323, + "acc_stderr": 0.014794927843348633 + }, + "anli_r2": { + "acc": 0.317, + "acc_stderr": 0.014721675438880236 + }, + "anli_r3": { + "acc": 0.3625, + "acc_stderr": 0.013883037874225516 + }, + "cb": { + "acc": 0.35714285714285715, + "acc_stderr": 0.06460957383809221, + "f1": 0.19573820395738203 + }, + "copa": { + "acc": 0.79, + "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4592710615415256, + "acc_stderr": 0.004973199296339971, + "acc_norm": 0.6106353316072496, + "acc_norm_stderr": 0.00486609688094144 + }, + "rte": { + "acc": 0.5126353790613718, + "acc_stderr": 0.030086851767188564 + }, + "winogrande": { + "acc": 0.585635359116022, + "acc_stderr": 0.013844846232268565 + }, + "storycloze_2016": { + "acc": 0.7194013896312133, + "acc_stderr": 0.01038980964728882 + }, + "boolq": { + "acc": 0.5755351681957187, + "acc_stderr": 0.008644688121685498 + }, + "arc_easy": { + "acc": 0.5942760942760943, + "acc_stderr": 0.010075755540128873, + "acc_norm": 0.5757575757575758, + "acc_norm_stderr": 0.010141333654958552 + }, + "arc_challenge": { + "acc": 0.2790102389078498, + "acc_stderr": 0.013106784883601333, + "acc_norm": 0.30802047781569963, + "acc_norm_stderr": 0.013491429517292038 + }, + "sciq": { + "acc": 0.835, + "acc_stderr": 0.01174363286691616, + "acc_norm": 0.788, + "acc_norm_stderr": 0.01293148186493805 + }, + "piqa": { + "acc": 0.7540805223068553, + "acc_stderr": 0.010047331865625194, + "acc_norm": 0.7589771490750816, + "acc_norm_stderr": 0.009979042717267314 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_5.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_5.json new file mode 100644 index 0000000000000000000000000000000000000000..ce35a8185f0c6cfc04c1d314afa35af83c1e48f8 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_5.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.324, + "acc_stderr": 0.014806864733738857 + }, + "anli_r2": { + "acc": 0.338, + "acc_stderr": 0.014965960710224498 + }, + "anli_r3": { + "acc": 0.3525, + "acc_stderr": 0.013797164918918362 + }, + "cb": { + "acc": 0.42857142857142855, + "acc_stderr": 0.06672848092813057, + "f1": 0.25882352941176473 + }, + "copa": { + "acc": 0.81, + "acc_stderr": 0.03942772444036623 + }, + "hellaswag": { + "acc": 0.45907189802828124, + "acc_stderr": 0.004973036453863711, + "acc_norm": 0.6099382593108943, + "acc_norm_stderr": 0.004867670042866713 + }, + "rte": { + "acc": 0.5234657039711191, + "acc_stderr": 0.030063300411902652 + }, + "winogrande": { + "acc": 0.5777426992896606, + "acc_stderr": 0.013881582030658552 + }, + "storycloze_2016": { + "acc": 0.7151256012827365, + "acc_stderr": 0.010437513986611718 + }, + "boolq": { + "acc": 0.5730886850152905, + "acc_stderr": 0.008651119069643816 + }, + "arc_easy": { + "acc": 0.6043771043771043, + "acc_stderr": 0.010033741393430983, + "acc_norm": 0.5749158249158249, + "acc_norm_stderr": 0.010143966195717845 + }, + "arc_challenge": { + "acc": 0.2841296928327645, + "acc_stderr": 0.013179442447653887, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.01343890918477876 + }, + "sciq": { + "acc": 0.836, + "acc_stderr": 0.011715000693181331, + "acc_norm": 0.791, + "acc_norm_stderr": 0.012864077288499337 + }, + "piqa": { + "acc": 0.7480957562568009, + "acc_stderr": 0.010128421335088683, + "acc_norm": 0.7573449401523396, + "acc_norm_stderr": 0.01000200256970869 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_5_lm-eval_global_step80108_2023-02-25-09-56-03_5shots_backup.json b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_5_lm-eval_global_step80108_2023-02-25-09-56-03_5shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..ce35a8185f0c6cfc04c1d314afa35af83c1e48f8 --- /dev/null +++ b/4b284b12bc4seed1/evaluation/rankeval/4b284b12bc4seed1_5_lm-eval_global_step80108_2023-02-25-09-56-03_5shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.324, + "acc_stderr": 0.014806864733738857 + }, + "anli_r2": { + "acc": 0.338, + "acc_stderr": 0.014965960710224498 + }, + "anli_r3": { + "acc": 0.3525, + "acc_stderr": 0.013797164918918362 + }, + "cb": { + "acc": 0.42857142857142855, + "acc_stderr": 0.06672848092813057, + "f1": 0.25882352941176473 + }, + "copa": { + "acc": 0.81, + "acc_stderr": 0.03942772444036623 + }, + "hellaswag": { + "acc": 0.45907189802828124, + "acc_stderr": 0.004973036453863711, + "acc_norm": 0.6099382593108943, + "acc_norm_stderr": 0.004867670042866713 + }, + "rte": { + "acc": 0.5234657039711191, + "acc_stderr": 0.030063300411902652 + }, + "winogrande": { + "acc": 0.5777426992896606, + "acc_stderr": 0.013881582030658552 + }, + "storycloze_2016": { + "acc": 0.7151256012827365, + "acc_stderr": 0.010437513986611718 + }, + "boolq": { + "acc": 0.5730886850152905, + "acc_stderr": 0.008651119069643816 + }, + "arc_easy": { + "acc": 0.6043771043771043, + "acc_stderr": 0.010033741393430983, + "acc_norm": 0.5749158249158249, + "acc_norm_stderr": 0.010143966195717845 + }, + "arc_challenge": { + "acc": 0.2841296928327645, + "acc_stderr": 0.013179442447653887, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.01343890918477876 + }, + "sciq": { + "acc": 0.836, + "acc_stderr": 0.011715000693181331, + "acc_norm": 0.791, + "acc_norm_stderr": 0.012864077288499337 + }, + "piqa": { + "acc": 0.7480957562568009, + "acc_stderr": 0.010128421335088683, + "acc_norm": 0.7573449401523396, + "acc_norm_stderr": 0.01000200256970869 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa83ab96e5ab8ac33f36f84756c9edb3cf2f957c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8c2d8abeb438fb57214a8a4fe5b712146c4dd9c61199c591393efbaffbc0212 +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..07051b134856339e8bf75fdebc3391aba882aa1c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bebed6c0b69ec81d0a39b5efcb6b3e193d29591435a6a7d8c87e63e3406267a7 +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..66348218cae1e8047e4c7116bfe14b1461bb1334 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c7ab22650e014d33b5a240b04ba0694bcf718d6741dea3ee7b77819065602e +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f727c3b1426a5971cd81f6a9c975e6716025bd23 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a176ea7713a06e26cd285e69b578a9625d63a8bb174c3df5bec9f2b11eb151d +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1196f8f88a5591e3e8cdaa49b6d7e9bb968ff9b6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca34989ed5cf87850de37617926882d56b4605e8befb7611f4a882b3a044051a +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d753c11af4fe605fd939c5ab017c547a4c0d75e8 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7d00d1732158c5a9c6254132bdc6dd91d8d9aa471e350e971de8cfd1653c53 +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1da6fafa79bd743c48d0307f77e34453bdbfc713 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f72f346eceb5a1052d382ae6e6206bdb947dc48fdaf124b55f5fcc32859956b +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb586e55b2a0845c1beca155e9e1fc1d40f50c16 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c28e8c46356f1b5345a71aaa847e4ec24ec52f1066c7bb9270c85bbefcbf04 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f74b276988ec5db94e66ef3a7a0b658e71b2114 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551b4be40ba4d649b1ff9167fd41cab94cb50bc1f9349628e51e57a11236df50 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7892b39d87d985c8f7f1a534399894cb120ad92b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197a34c25365dd7172e8ef29710e1be860543ba714837a364135332ce5a390b6 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..14a33cb6dc5e15873cb65a768480deb60f967ce5 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7670d1a1793084c9114b32f9256194fe8f808642994ec8016064ddc7c86bf2 +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..add3b6086b8f2040aab541e6bdc2e6d5a08f54ea --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85058efcf11107ec2414dd3f33a8442b8614713c5d161d48b1372413d129748 +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f40382ec2af465fd62efdbe1098d1e23a367b27c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9321a7a95fbd06a28e4b8ad6773678959b3036c3e7c386a13981b33fdfeb676b +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35bf909e143f9690c4067f97bb9c031e25abd7d0 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0ef37d0848bdae81150437205d255d983b681d7b90e22b6109bd9cc3517bf80 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..75914584d8d6ffc39e2f056c3d07198e08af1fdd --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d01372cb4aa5774e2252df554d75ad353b0a7d4867a711c1e10a45a21f59ba4 +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2af7cca8351ceab51ce726fc6d2d4c86791683a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ea797ea1fc3f000a41a21b26f0bc7f6bdf3fc6adac809b0e249090d7db1e50 +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc9434df07727f0d999eede540feed51a94f11a4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2bf9f78ddf8436e3c239171c6b58aed47101f76cb543bfb0da540c002a8819a +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3a2ec0ef71e6a0a698d1252decd075a217aaa0a6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2324b8ce41e82cf119579206fea808e25ad13499ed8efc17d8249ad55164440 +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87314584d2c181bec4c0ee37a175565c9bde3f7b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ce4485a972bfb2b5505c0a3308372a722434218806b8f7f6ca9afeafc43bb4 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8035d58be94b60ef560464df788ce643df4a7a6e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91e2b9c99a04bbd7b31876cb709e70a328911c41b56598a68426e54b5e9c8de1 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8527a7f0257f44604cd9cc2a419ab385e1c70f05 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e44a9f01bf21250110b2da767e21de8cd5404847a1e96c752d0b2d5950bd587 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b57e48f27bdf7736ffae2d226a21a1c30577105 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5e2e7657c96524f5d24c1022edbcdef31572b33d0e72337042e5ec5918384f +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..518ef4af14ce2b82b0b8a21bca4453b678e4abf1 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9948c23981f549af857cb3fcb8f4cae2aa69ca03540aaa6fb932adfbfc55087 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b181f569388d94aac2bb7c0d8ba8d211f3efc77 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fbfdedd87972c5005d9263c53b6781f8f1e83bd37d426b31001d05a0e4ce7d +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..51e7824653773d647bc17a067512f7dc1c4fe4b7 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfb9c7e124b3fca87ab38f52a87277aa75062516639b56775e2866b5ac23399 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f1d85eb81ece4af61640f0fa07626e3efe35016f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf997f58f81b543839a5378405763416a3f979812b547fa65b34f974812774f9 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7dd3f41077c8dd8dee134fb5b786dd90cd76c8d0 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f64dd2edc23f1d4beab74f15c27ccde1d70476642d2d4c750506d50482b5017a +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ba52c2db627444cdb04fcaad9c3b1d324e0f3b1 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3881f1cb31c838a90efdadd9c79ae1de27d99a6785698e0058da35270dd4c5b1 +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..517a29318f6cece5534786bc2a3b43dd6b933d40 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96c1207d822a014fca22af80ac912dcbba2c275d2223f5c201bc3a61e7e9b7b7 +size 199058605 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..33daa44798c02679c799a98609ef7bfc79197684 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80e625f301516da03c2d501d9512f55444af685ce1e08022c4d4d9b5a7c923fa +size 199058605 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..30eab1391b6b4f070a87ce65029d15f19686fc6f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4286cb8e1f6f903d746f6d54bb4bd7c3dcf15984b1a9314aa1758989e3fe4f47 +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76f58ec2fe873751567e822f6a3c38bc446cfe49 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:761cd973d8697c1843bd2cd3c61d66598a4d2203bdafaf80aa0e27e977b31aab +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d403c225aa8b1d92b780141c15d06c298d7bff4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f21f5a137fcfcf3af32b88dfdaebe248b788a3a8615f40b5795b2ba7fab870d +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0392c79a4ee9a6f61f497107c1867bc7d9bf6208 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fb884e07e891f96bed751e8e0d56d507956d17a5e783c9b3ce6b5675705d0fa +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..910915c5b113e579c30bf350dbca717faa2d58d8 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76bd29bd2365074cc404e7582294b8dc2e9f3f184c27c914b925ed0cf3efa168 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ffc4270b2025f599ff35f01e72b47720323c0246 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e01b042edb2effac82b36c22e033e880e0bf7a9a323517b9dc432a0e4cf28d +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8afe860d4a304c42d3175dc4c136f3f17125bbe --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f9ee34cd344ea64d22149a8305146440ff99159fec53be53fc1df47edfb9406 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d67202dbeb1ad8d341de6dabbb1cc566837a70c7 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb8b8bcb26d45fa61baec42929d797e7d3efb8d6908a92533da71a5e55fade0 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8b08d5f9b845e7409d48a39e4b92f5ca7928e38 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8b32b916696767d47b7731d400ad32669de7f294d29fe50549cfd7b9454872c +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98c4fd74eec8ea53aa80260c19143f2fc3daebca --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2abd727b8ccf0747dbc5b519871edf667861278efb6187eec4d9cbf351d2db +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be91940c1dd35f391a96bd4d908bd970343fb74f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b1d8f29c8ce33997f0b1fd39d92d5e32c94542d1ab000917c64f314e5192c7b +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7bdd4bb0b386ec4908472ab0a7e9e189247d2ce --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f06653a58fe7f87365b0e0623555ecdce43c11047a2464795599253db3b6956 +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e90d12575d5e72bbe6b338b970264ee6e3bd5a37 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c8a99d80c577a725d06b63db76da1450fe6d9fa8d41ff8a59dd1fc891170ef +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd45465e9a53d3508f26583596fe98dcc13d569b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd381eb1f0d1c5a4c3459eb5812870562d9a2ce83435c513d103b48ceeb10cd +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..515f624285c15eaebddf582d412d8fbb2d75f33b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8912851b2b8fba6152351c16b4c80cbe0fd0d5cc0a81b8fb538bd10b7ad1a7bf +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d10a5697a0d75c1005bf2a05782ec3d261ae31f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e755715aaa2ee2e3ee1b40c7b64b21453b7062958aceb7dff84e84229a5b7a +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5382ade9805a9011db9e97ad7c1f2ec5c82cfc6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b69d57f988e6c09e6853d40df3a9e237a20aa8baba1844708be8ac8c6aff5a +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..73626ef94f57eb0345cbd614dce2981ef5e05c28 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:838c766d48058e3f594e882f8b99199215c575a6193849f0f350930ac8d980cb +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93fba0e7c660ac4075d1c48dc713ebeb74662092 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c864daa600288f1cbe6180fd9f42efb48280b847acf8daf2ba0695f4494d330c +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..56ad7880084f86b966f23750d0065ffc351ec44e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1c487ad742717f90bb107cf0da809021aaa0afd7ff4a6c16df84f99fbc1697d +size 199058797 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..711dca15c48b969d773e2264c85df9053cabaa46 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1fdc6780e83da67cd02a030a62beba2d6bc374f570b6116cb1a31e056255597 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c230e8f69c173cdc33cfbbeaa12eb74141b6c9a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f784a795ef9c5cc018f683fd2d25086063c44bf55e177887a58fe836c0f867 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..92df18e1caf3e9729595a59e0c37db07e9a2bd71 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bad86c202023fee31d4c9a1c3ff222cb6d851f800129a4517167535c9eddb24 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ce14770d0e17029b10b3877d0fcc37369a6e5ed --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e42cb8876782cfba7e9dde0ebdf42c4eae005dcf1c0ea48766627d9d99cdce3 +size 199058733 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcd05dabc62b9dc688d302e7de5be7654d8cd228 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f35df84b1bb8fcc3c3935abe66f8dbbc639fac193097b0e76bb0336071284766 +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b2eddeedd5ce6d8e6e566688f4fa3f8dcf58446 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c95c626ec89c53e65296c1a3bae5d1d6ee22773de313b273fe0888421ed3b40 +size 199058669 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e27f8fbe0e58544e2a1a777116b8eb31dad245ba --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df23319315432a596cc2c1631870c055d192da94eb6bf6fdcdbdba5cbce78d5 +size 199058925 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da864b46f19d7da7c269bc264351a1c225456448 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e9a0899fc4f5b4d7b450ae6d9be9a12eebbc5a0b3918c79b8a89e8e127171e +size 199058925 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf1a243be945b2076077c419b691346d71c21c22 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a4c9c475671ee31b10fb07a11ebb326d830e17bfa2901f908b1f0efaebbb37a +size 199058605 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a4f8111e595a870d60b4da61991c4b198084f9c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f39021b8cca71536bcb1317931d18c106ff2c8492b67db810fa8b5cba757ef7 +size 199058605 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb63e439f3ff46c8f4f71462a53dd152b366920e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7cc9798767a58bc41f08d1574bb5aff0206efc48d04cb964ba698465c0cf19 +size 199058605 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9b126859a03009710691fe91ab5a988614d841c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7509abe6060a2f31975f42630debe688a004c36f097523f9880ce484699c0ab0 +size 199058605 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d508c3714144fe5bdb583c0cd0de719f2bdd01f0 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d56aa644faed4116783c16a2c843c5dd971ca9ab0d6be4c3ba177e3d60cd8a +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e0f4620d485ece78d2c5a85a11185dd377031d5 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7171d1574cf88f4abafb9908191c30c59c0e5a6848e2b7f29916822b25d820 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..590d3eb94c966f26d3b6dcff261165ffee298555 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36de8c2860f84c3d93fa5107dacb967ee55ce82c1a8c14c5c22364634b5d73a3 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae24f37f846d3b329ca1e3536556bd4d7c54d1ee --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb78479e071b144e668d72006dc8c32c4ecacd2d07fbbed2500ce94812a343d +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..92606d877053ef63769c2ffdc961ea00c206dc16 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e4a2bb824a13c96523a54b32e5582aca794bb9bf56a5fe89b28a34067476f8a +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ac49f66742b84c9610cadd5ae4809d32f1db33e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17f0762c691d40c2692ac9f46d23c139ac58be934698cecd9f42fed8133816aa +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..70416c56719854ac7313cd6a94e6d1e855066cf5 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3983528165845ab6af0be707e3268d1ea1dceffaf510a51f0b505d161d7c4b83 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..02599d2a3c2ebc343d4bdc9b7b7b5e3ad1d7bc71 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb09265432d57815d699478a4c12ff426692f40917dd61e9d9360639469bad1c +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a16be031eea0cb665fff0ac2ad7fd3d6bd5a8b31 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ddfb9412e4901ec47034fbb4014cbded92fb99f6afb3693ab73693a0386cea +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..94776a00847139c5b0d06a6fb94687dad7103403 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d759e55dab803da1108b8d8744e079d7dd30942c09e43dde50a434541eb867d +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9d0042225143251fa4a498e2c1c5a613e71f4ef --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc22d0cd1354ae31151316397d2d724d7812e5f2664c3f1038a45ba30a399b1b +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b672d2524bf483f77d6f4f3e410679333c8dcc6f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3503aa2f7ace1bf5df5c9f0238a310653ca73651039a0e5c72cb0258372c49a5 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..95e8b4ed46de2826bbc0246f35bf642641eff45a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4204f1fb69178d5503e9e5ec8cc55647c421299db7b126cc421e6bb5a1bb6164 +size 199058978 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c40681d9b3d87a98e9ecef13ebf3bd09c690d96a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26fefd1fc536b7017e6c78a8b2edaa2c84cca5ef1ee2b512e95257dac9736ee +size 199058978 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36bf388a069614de93725c11bad9f9357c72ad84 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b7cf4fcef9e7fa1dd3602aaca747f2738b80be37cbbd957cade77a57246cf0 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60e6e9d43922401733e01a812051983215574dea --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd8b1800c6ad38442633c91100d46e57af5a1313b7e5675d5caa4e17a9ff0c4 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c61fcb2874842c4e20ff55b1b7ec542fe427396 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcd2290662315b8167ca25a4338efd11a481f787fc72f7bad4d8979138d8e005 +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb76fc9cf0b7ce2904784990f2b1b0b6ff09aaa7 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd45d37079d408ae2ff9e62c09d81f169ecba1a3d979b42ebd2c41e825652b6a +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7dd593b6ddbef25b53ec3d065026d5304ed5d25 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd31fc8a747c59474bac5f41aa8054b554ec7c902ed7efbab760cc26cd06a8f4 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3da1aa88017b040e29d16dabb3d7e3dfaf0f70ec --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a6ba9d42f2c76d027b7fe3130504bc1d62ea9b9ce2abdf36f721ee67ec9340 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c9bdb1b63b6e2c9156737356b3dff40c4a57be48 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373e79cf80ba47a5963bc16cecdb4f7d3330090d2d5e198901b9d0f6b9308aa0 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8afbdc01ef6bb574697423621b64d06d7999989 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3287423055438d39ba489eea26bbef9351622967805a26b13f887a5f9c67ee6 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aacefbe0843203ff4d8c0f1bacae012ba3e2d0e3 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf2b974b045640149ef8bb02ee3ef73b9a5acee7d886bb440db3b4d26d68d38 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bea364c7686c1c550ba29b098f0ed37709fb71be --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f63ec69083943304e7002a4b1644c0cec432f7a419477074569a9999453cf7a7 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..52b8d8dcc34e548c25852dd402be5d130eed147b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:327abafe980e167746e7e0a0e14f56e2c5dd9ab3c3bef2533c5ccbdf1e3c4596 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d2ae7618ffadf75f81fb82e3c6c71862c4bb684 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6b3aa5de05d18c29ed9ab34a8d463da0e70c9f803831cb3cdef20acedda224 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..977952bc9da5567310952566e3f31206f72e73eb --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511045abc3d8d56d77f8db5ab8079f3a5f2e17bdbc97d06488f44ebfc83a8533 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cb3291729b448537a70999b7954d7837f3f9672 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7dfbeee9b32b001b3aa308c1805d5a980f35287e524f0694316aa070b823436 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fdb592ad77ce0430894b63eb413eb8f2b6971a2 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1085329fbb5c16ee0a46f9eabe76f925b41d64b1ecf003292a7aa8a83ef2504 +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3785c163d74a70c82a0a125be8293c2c3b8f50b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b43f96316e8c934261094adc6757f4b395acb94c82c339da4a6553307f2827f +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2c29d760f7263d9640c2b80c4b81d3bed3dee0b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1576119e3f7672d73f66ecb2930f31f3aa196593ea514a8eca9c0f5b123d069 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..01dd31893047f366fa543eda32d710e4c9b6ba9b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88bc189ae9924d4a6c5ebb422c8dea8a7acf71d3c0bf59aee38be436d00af4ac +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76344350e82490ce3870437769b866a92c03d7a3 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3663affe8f14001b87f0334eb4dd4a5c243c338a073db7c51a8cbe5a232828a +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a391757878389ebda17c0618562981e1409a564c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66881b7f0e0fba823ff1628a665c00a26b717324b5cd38b2d9b695fc2d5fa3c3 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b2b85751dacabfd54bb46180d428af518b7df86e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53c7b3221058d3076f6534ae6af5e4f8fbabd479862067dc3ae061937f91462 +size 199058594 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60c2526af1d4b24d3b5605ffcdf95af903c92f7e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb8a3aac014de555229a228b5c654f7e7b3224a7424517204ed5b8c440c1dda0 +size 199058594 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..13b4b0db0d27a1f593235b99deb2cd40d71fc306 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4e8dfde57897bb50b9f77e760dd0070cc32072b77943a796d073919bb1fd2d5 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..947a90f7c7e8962f294740d0a784eb85b1dbcce7 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b5515fc6cf846315353254f7bb7ab5e84777b2606192e6f82fa20a691788c6 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ddfd568a43f23ff49cf34d499cdbfcad5c5f73e5 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13eaf15462a3ec01182025b14a497ba7dab4676ff92685dabae2ad659926734d +size 199058711 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d795dfb73d0b4f0b91ce132fd11a80030876a9c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d81442a2549c617bd0d2cc538cfe21d768861bf5fe63e689892a805b195432c7 +size 199058711 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9cc8fc29a9a8b02277bb25794d52d637902be120 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a07cc0671727b8910cdc61eac11dc9e629f4cb875883e4658e76a42b4f65a95 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..44dbaef030c0f7b1ccfb207c242574884907ef3b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fe2f11c31b80ec7e2d7b2335ab87b5f75c4bb5e7c8759ec8d75be2a45b65eb8 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be82662109edaad66f7ea8cf95be533754288979 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f012b7fd513e7ab9a31f6029db31ed1e661ff0219d9f7ba2d031b3f5991a8e +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de389e147f6dd225a6bba0e397ff25cf952f7a27 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca1ef126f5f4da938f39b0b587f400fb156dc12a89a43438bd9ee8ec6e8fc6d +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5b5d2bac6c0c50bc86057d198724a7b48330c2f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b37d448e8cea5486d705e6c50af01217d8f5622eecb5c9941225af12c745a4c4 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..465c6bfc53d616c23946f462b0f3be2bad88ce7b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:850df4e2089435bad82c998509ec753956837927836b37dd4e36f27033be4655 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..72537c6cf97ec901bad921cbd5d5f3224101707c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445e049b81006b24a300f649c49a1850102efe9f4c2180ab335d4d0922d6d99a +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..659989b01859fbce79c330579eada3b4d100b400 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027c27c3eaa9be62fdcc8c460f1cb0362f565e655ae39a32cfba922cfc4cbe08 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a17f8dec9cb38860472d71d056ce3861889ad218 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fcb19f2839127a0f34083f5f5a73501b23c14154a90afd4014ce3c9ab3b00a7 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f12c89c98a6852eed3d8239bc5cb3bea7f8df64c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c4170e814ddaab382893f6e8e19611bbf3c2b6184600577a4d34c79d3b646a +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5c0e239d29d147f7dfeb0a9cd31c3956fffb477 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef15f242d58a35ed5f68b9e055e1e5ce4c26f5c3c6f58ec4c80df7a3c3cce9f +size 199058594 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4f20a800d2cb819d1be81a4b2ec5efeca6cf87a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49199b0973c38fe1a2fb2f3c7d2a65a6e4377dfb9fe61e4d920a1ef5e0ee5c50 +size 199058594 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0743df48c4fd8428be81eec33eca2fe58325f63 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9da086887efde660eac363154894908727b9a511ad5bf35592968d4544f9aa5 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..435f17a79e3fb9e050c05cc1208a3b0aba173ec9 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89bcc19237c6f2110b1232c4efc0ca7305305260d1fd81388c8631a54fcfaae9 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ef1da2ea3459d306d880ab085ebaee835b74606 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b1f0093b7ee2c8c6387b810d2043645640ba734f2108a7b108a1732427cb13 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..239708e974545c41080250bfc8f0ad9a4cbb8595 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02ec831ed03ee17edb086438777a0b1f59a235031eabfb0067d4732600a4b13 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..deb37708c51970e1e0e13e8487633f10807cb86c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3b8f065f40e862cf3840321596e3d4e1f6cebbc0761a36693433dfb6ec6bb8 +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..58c36721b23fde68779bfe440eae7d9204a4a237 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7dc1ee8dc8b61a9027db8e1d517d2675959f7fb0a73f1d44e01a81fc76ea83 +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a1619fcf3522fbd9fbfbe3a67791c98d69c9079 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c83e2c9195cea70b7197e7e9150f404964d6e2a3db3d0da1b7a3a98b108111 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9490f67b4b362852127b2ef5b6c9506857587f4f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a644d003287cad024861cb0304e1fd25a75a891a8d2ff72e77d80267e7a2a3 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cce014275f40ec03bd6216152d9406432c01d716 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f85f39d2b5562b9d2479dfda44ead7f96953a98564f1b17e4e1c862baaf13ba +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6099433579f5153965c6373d20c195748e8b51b0 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ed967324494ee7994ae17f33e7ed0f4d40cfa70e12d3d5062c17af11929117 +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5fd7940dfc7a8c64bcb43dbfa5e8bff1b98f2254 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ac1b5854263197bdc0bb9ccba3468d6da330fb61d35ebed62146f51c763c9f7 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17c8b581afefb04e916695a9c068d0a140f08f3e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb87fd4d16a65643ffd7816d2b0399e3be61b0dd7329aa63a0142a44ead74ef +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f49801c647f280e5bac7ba500be0bddff59b269 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:403453e23db6611b81c5da26240e9c02d39de79dfab5008746df3fb27495deaa +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..63191f2e6bbc7d4b32a876f84a516e40d11f9cc6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbb87c83a50f34b836c45647aebbc909d01c41231d549bdd5a573587214dca9 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..756618d2c916d7426f8e281d0fb4014072dfc202 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d2a49e85176edadc5e9a20fffa09821ab874b4cb9b8d4ab761ee406e6161bb +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6583b0f11ff4471d644cac10a13132037ee4e38 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e5bccdf9f86f9f4aacd2deca3a0a19bd63905a67f5222ec0665bfbc8ad6c02e +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ab54b355230fbb0d485dd8ea1e2b302af55c6f6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d0019781aebd52e0dcf1e70757f8033f4992c79ff5c613911f3f630688c607 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9dbd9830fbc347db2683606e03b08ce25acac8c5 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf8f5743bd621c649dd8b6f5181796b9ccf37af2e3d3afccffa6415be7f761f +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c037a37047d0eb5e6569f19f818c45a8bba9edc --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89795f3cea0865a5b3a8b6adfb656cfda543939299de0b430b33bcf7c034f76f +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..023ee73473418d11eb93a380e8a432c149700846 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54173f17cd6d8436c0dc0fdd88c57d746f7056543f6f2f88ecf595f96083ddd3 +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..316f5bc3a81747a43056cd94654fba1d510b28dc --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4529699cc1c84abc99f43df2ac9229605a46c0898f43f26ed54a3e6027ed6f +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3421e1ef89fdeed8a3887b15e7de23937cd6cea2 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b0f09c5f1d308771989453d3684c549572f4cf751b072cbe512b399758e7ff +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b75651bd3b4ffae7bf5fe0b65309ee217c7f3a4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35154e45d96e6c48029880e6f3cda60904375b4f4cd64d1e48357fee5f3518ef +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..64d17b64b4c04ff143bb9cef37f83321e88216fe --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1edb82d0fb4e0baf83dfc64037c1a5519246786ad4890273efa3ed49c93294eb +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b41fbed36887e409e9e53af2161632f89aa0e2ae --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8202737e234598e00ffc70df4b6ffd1b49ae91a0c35315dc53c44fe18ad0cee6 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..547655865d21d56d73d9e5e122e426c87527a830 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032e1220d5d24a14e91774ec76f099f5a4921dfcfa6a98f2407f13ebbee81e84 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8df654b7ea79c3d9aec4ed6cc44f5a215e5e38d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc90e06cb3113054b49b77af46ae53476ab42e733bf52518586d1e5acad128ce +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4da80d085c03f9f1fb7f07c4d9e8d36a18ece055 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ccac2dfcb6749a3ff915915a5fd7819efecd117951d881fefee8751185bffe6 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..695700373ff9ef6dafd7d6ff9b61447d72ddbb85 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54df5c03e1b29042d95fed749c7bee3bb074250ef04f8f56fc2126921037eda +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..041290087b49bf1345474779bb39fb77c55c047a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f8014081685ef79939afc26b4c24850edd7a0c1615fea056e170510d473457 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..19e48e89cf228f1e695fa091e88f5e211a3aa7a9 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f223de3acb3fd07bd252e9fbe1b511a93e3a4ba110021ff8f7961714b1b77a +size 199058775 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e12d0af14287ecccfd715aed4534a8f13d819570 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f502890eb84e3e25a3b1bfbc98982966b5a72cf67718ed5b19ca0019d544f0 +size 199058775 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2fa5e7b9113ae5483f69dfc934ae5375db042cd8 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45416015bff073ee7644693e4d64e891326269429af5716d3d8e663492951994 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc9072f3ac00842048c1dd92207b445c4ee83e8c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:612ebe05adbd09dea60b4f8f3bc716ff1e3aa19a69f0389d01beff2cb14b337f +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..53a93db52f175237e644d735549f17a252074b90 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b89c68cfdaef467cc5c16230272bd47f1392ec18b5a1131ec587cbefcd5580a +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4f936be44398ecec0efcf7f3d27c6180c4127e4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291aa62422bb5bd79e3c33902dcde79ab15ed191c4c1e88418bcfb26ccd1c2e8 +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..421475385f1dab429f714909da40395261d13bbb --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39b1a2de69141977ff010b0b5aa634241ef9f7e5601b47a6d08aca7b83656ce +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78bae98cfeddf911ecc8c02eb8941d8bb19d9893 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1d8d58a721bad28d35e8ec10001f039dede06e5a235ab398132b02c645caf0 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..02938b519e2d0ac14871d017d812a9c9e0353eea --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61547af448c97acdce824f007b1d93c4a10939b739b8b6e02b89e247281c3a8 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d98d5691f475baa11ed3ba9f135f518453dca027 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e772602ea64c2a99875095d43e0cd9c659a93fd2dacf790121aaf0cfa9fedf +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..546c1f6d23351543c931a48f28a98c3782457b05 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e9b028c034d3c0b8a33aaeedf7bc879bce7059ac287194dd9c9b256756ac93 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c45ef2d49a4ab334833d58d64dafd6cacf6c84e5 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31835d48e4807a86655364b9cbba42d344a1a3bcd16e1c64a1bd0aa9fef46226 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..927b44ca0bb17208bed28158a79166fa21c92533 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed15bc4858fc465b05e8477a57c285de4bdb7c96eb565bfb48e28b3ece6e9da9 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e98d645e8efe54fef1406f99daeae247e60c988b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7999a0a4fbe1f8c1ba18ada599eda6fb8c04fa606526b2f0171cf16c553ed74f +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..56677f9751b6a85e273f4fce44ae9528bcaa99f4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc94c9fc1756d4afba4812b2549a05c15615453ccfc934bb61f155347eef2ec +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f989c14c239448c50384e7201b7b08996681d3b1 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1b3701a9017c699bc9612420b97aa98fc1bb4825baadbda561a40bc848a66e +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0af12cffef073046ce89d5d76f09a3234dd58b71 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc2aa67663866f1fc4a0acbb09723cc1c2f06056a03b59adc439eff4d83eed3 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..caa61155aafe32f6cca522cf0e850fe48599b189 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb325081510aacd3b3662b0a7fdfc7f57ccb982eba19e77c405634244eb31a8d +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cfcf8849c7c612152170173046bdb4499478daa --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea31aeebf5f67d3b16a87fa4c3c09ae172bc4f3c25e53e63c83485a382d653f +size 199058914 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5a1d519c20433fff099929d9bcdc0893b3c919a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c0814a4b115779df0493222d0e0b0e7a2d71cc1373ebba43b26c9f3d8b331ab +size 199058914 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..049d17166d41d3ab489604cf2eae6644171f9fc8 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a07b706d8dc95540ece0e89a7874db51b77343b77bb6d16cfad790f0177ae5 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..21eda6c3ade9b3c56a3dfcc87909bb7fd091ce79 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2872969d1a055c88c2af67a5951d7a0bd8223ccac0003939e9d581baa4e8f7ba +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a869437bbf00e2172321df5a3b66712087069756 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c9a5d38c58394d6f2e9d1ed704e41f4dd9eb846fc4c2070449926b943df9af +size 199058711 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c913c496483f879bbc87c802c195ea7350f16a7 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7713fdf8161587687f5cdc0c6630c4a3cf98e0ab770432ed7ca250b884abc1a3 +size 199058711 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d24f7b281c882038b9d0948425ce6091bc61e57b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b152f8d7458f6fb433b18c80b3d7dcb11b3d8915019264daa0f7688c7bf3a13d +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff75255ae182fc8e7c6fc540f290fa6842af8e6a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b6499614c51bf7907e78109acaa82cfd9a9ee8bc54d353ad46707e0415e2b07 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c374bb9a4de533a46f8a0079010c8e7b264776eb --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab3ea7aa07d56b68a1753095f9dfda61b607aa7ea1fe5054352be705e17bbe0 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1715923185f2b3b7b9e1245d31cf78ea6a51eb85 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67dc5e6a4c59b9fb4f6a3498c47a0f76a1c20dd25e9e7bbce0697b84e1a871e4 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b9734eddb09e9d096ec80d3099edd13905319ad --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76bc2a70a84f87bd7030c6ab706ea2a3ecd2d2407093448253fbc2334a1fcb2 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dad325874ec33db0253e01f3ca73cc2afb1d1587 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41534f7f9fc9b5c98dc949e0de640743ca911d5a2b58b93e1382b781d01d8024 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..69139228ed092164b309c000a839f9804754b085 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3ffa8ce43b1cae36c8abd4392de915f03dae3d1cf34d072cd794332033573c +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f58ecaf825c5da7a4fea9de4f2cf75f2b4195678 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:673e04451f801ddd92ec3add0dacc91ad42b316305af41f06878d7b0ae117156 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b178e73c87d74fe2dde4eed3947078e3f847b566 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810e72d0012115b5117fb6708b35fdc9314708e61106ee2f2b3edb8ff183e411 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dbc0a915ef4aee9c7d7285de5716f88d30e08124 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4bf01e1dc5f9cdf0d0bfbddf86ab5fba2414e7164fd00f65063aeb144640da6 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f80db699a04e7257d65f8fb0cb9480bc3c232290 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a72758a00b961bc6b289693162bc714ae0971c78c21dfd502206d408ae17d36 +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..177a7015be2d7031f162ead951c9f33ac038c0c4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ab2bb375cf1784cff32fdf7c2fda80bc1e1cc7b0679b0f8550989ed41d9b30 +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8040356dec78165a5fa3ecafd0277b46dcc77b0 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61863be7371467ff44afa44f6a4eb235daa7c10671a5a16cd139b428e74298b +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0b3c0d732a9d453baeb0c5833494594b9e9673e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:041b67081b7692e9ef8bc29f18f6f1dedfe03f6f791420cb85df0e1906ad0367 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ed8d236bb4f11607b1f300e9c22e7052322516e0 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38476aa3b32ce8ed10a451a0137440a801af4d239f4f2e54716b1c4f2867938d +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8c981aa6d16c63ae4f9607f0e5c05faaf6a30ae --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7246e7c3d3fb4fc0478295bcf9830209620db3fc81f527938ba167e7c565f4c1 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4289bb1296c19ff24c43efe84f57dada3f4c67a2 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf6709dcd0e91ecaaae2a84dbb294159cfa24ec5c8c6a60fa779923bc41cc0b +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..22abd287468551eb3fa8930059b7a25e3e0077be --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc4a17855abaa455b82ed5fd791d3ee345c5ba2ac30569bfd673c32e176ac0b +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d81e56fbfb9b5a050a2140b42c002a1129602f23 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8324629e859047443a6bc1aeab9de5fcbbc01ed36ce28b8f28bcdb634e2c1061 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b37549cb234caf116ce0ce77d019a993ff27fee --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef98e1f5c865cb9f5d10d798c152e6bd4423b87eaada3a51053eb03986e4b97 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..52b62c494935dd0c87eeff4f63e74e32f3c19201 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9edee45fe5ad063f5bb9bb62f9d4f6670075b16db0e6109284e771f9452d5fde +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3fa3115e3392963b9acafadc85afa22288543498 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72af944f8f35c9ad1841df9c9bb1c4d8b9c8d1a85f120d3bd9769e0f32904f7 +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb7f008972887cd66d61fd78ba8ce0de64f5c952 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba4fb23704904f4c3ddaf4d05def16a1ad484eca4a8d117acbf0ea25fee760f +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36b6c226a4b86c789060f83143ae85f4cc61eecf --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abe9c1512ef7f185775769f2bf203ad44408b461cba6a7353e708964019bfa6 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4a5c1438bfa6ab109650a7daa975c75dc8d2a3b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7885dcae4aac4dd81b3b9a36aa4306be6f193414eea9614dae6e968d0689661 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..776b5ccfc389727976b29cb915141c45763a97d7 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73ccbfd10484d0bb40fad9cbbe8b771b0e4926a324213cfb1a9f339b17cfdd12 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34b0bc4fc5665207973896784c748c33acdf9df8 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5a25245e2df12746874512e7bae8c93a032d24ee2eff45d73b62660f5d547a +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bddb5b3d678645ab44f589fa57696726773adf3 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95dd48ae119dd9bc3f914ce3746621a3fedc0b06dcc2f15380bf0779a265fdaa +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d4e93685c0856becd1448556ee24c9c3c9bad9d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1523d4e534e305da2a18c8623b998213094fec38c98fbc8853eefa59f247fe8e +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c12994d9a465c1967746e2ecf834bbf499e6c044 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff71a8fe42eb612b61456248af1f211d8a569ea886b54215efdb81490c7be6e +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e7e55e46fc7107227045a4e8c741cf2a6b300c6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4efd8554fd547d1965baf711ed2478ab181728b5083e695bf82dcb1a0ca81b +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8879566a4ff74142d94989c4a34d6bc2bf5fde30 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c750cb9c28e09762382e1ff5e58ee2447eb9371da27cf01da2763ac4872fa0ec +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fab2373bdcba2e6b77e63fd3a385c252e94909ed --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:980d790a1f6df6fdf35790cea242fd437a0a2523685a767658cff138e2ac1e2d +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a83e088b84ca5a88e40264fec0bebfd7ad880bd3 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1d9a7a0002f838c276b226aed24bc7aa2dab080afa621a65ed4796e1f26ad29 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb3c9c8680dc3814c0d09d1edb0080a00ae65809 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ed6d79a3fb8ac24ae7b8a2272ac83679f5e2d466d0b7c7c99ceb28eddc0dd0 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae2dc818baa4937efd44c094c61e41ab9c2cc1d8 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437ef8f08e3d3b8c805b9b6cc3cc1f139b203b970fdadaa37d0aeb53c1937af6 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1675ab018a8fef7b1fd2b0c80fb6e7a212e545fd --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5298359ceee8963bf23986654921a97c0552a4d34f27367ec7e515e8ef296693 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a21b408979342c7440958cb5e9255a0b56f39dde --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e89129a9eab19d96127680887eca70dc8b18904994baded7b853bd0e95f740 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe5348f6902bc3e9c5f5f04c15db54bd6abd62ac --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdedf33e4a13db95a68ab2faa0e63934654d92ce454a6d9e1a96cca5f258e4c5 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50f0f24e48d0fbdc46619fdc534df6b7b307d69d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14efde68c5f0dde67ea870e2b91978129d61f75fc2ea836c33a8e0c6ef0385f5 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de527fc5d89c91c415925deac654142e43c7676f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cb0ba3ca35e736f4a2b2d418e7dc2562f4a573f2e372b14165f6a6ef860377a +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..072c0b393dd64179c8a16f503f7dc01b83b08116 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72cbc48e719f02e565db1288ddfb0dd30d4ecc092402693495571d2b62ee9c7a +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0166ed8dac020cbdbd846818ec6c420851b78770 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92efa7b90d9b657542bc4858b4af6e19e3a83d3b17e2062d3741868d743990c9 +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16306cd3e8169d2ac6abbc100748b4d7f16b170a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46021de1013fed30c49acdb3b410004c9719faed27f50f82c2acfd452d7b7581 +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d386122d185079087bff539804fe51e5e5bd419 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf015189773088e1bcf6e55e76ca0035489676f4b6ff82af39b4394dfc31aa23 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef659d4e72e8310d60b43216ac14f781ecb05740 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8de2cc900e635e4846069d809e36ae41759e248f7dfa183a46541cdf15ae13d +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..83085369e630bebd6656d067d8b6c00858e04140 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e0aea417ebc4df24aaaea5b3366a807ee754167c32d76f0b03afae830beacb +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f5ceed1735c2ad4ee68348ad56a6fa14d7a13a6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9fe3c0db946be76d699a5935bfaddc836e7f1b8ef6c1c960ebed74e8337756e +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be2740533414aa3c63acd0ef4d716c9309b59efc --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:915f65f4ae2c74e0bedd35f55776f048c485d535da0037d1ae84644add817dd9 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d049d85a9a280089c13c52af05bdefed81f41c18 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ad85e6bd341ab43423187878c1b8c1a66bd8b0234ec9b94f9a0abd1d6da72f +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..11d4423ef7d8ab09abf289257094679f17bfd222 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:102e47d335fd88b0fc3e1632ced62867e92134bb5aa5ffe590aa021e17c18f70 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e3ff282af256631f9305ab897e976df74e6b304 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ae235a5f976a9324646597cb1d86bbfd3aa5d6e34ce1792b969a9deaa822e4 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d240c2496f87948276a2332596db68c96d04245b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a52bfc0c406827e3c429cea963f89cb29067f8a1e48a14c6c2908c6b893461 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ea9e04a8f033021ad5e85df520088889b7fca09 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f92d71256042a7d749064a728262c863614aec1fd826381fc44fc2250b97028b +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..918f0384b82cb01850a82ef05218fc8de9e46485 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752c3e38aa3f36dcfc9ded99eab42770bb5d025bdf92a422b073f8ea95ad114d +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eca8d1ff619dbc6fe5b86ee2d7a503d55796a8e1 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bea32f857aa213730eadcb02885b0092b72ad2540c4997bac79b7fbe578558c +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e2d19282f1523cce3aa8c896c56fc7ac74653df --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18bbae34950cf2b73a3ffc8219d71f38e6c26184c2d8b69206291fa37c27896d +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..45379f2c93dfd59e647c45702dc3d5c4bad6218a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2ec935349c92d303577b72ea265915d03938da2cca3a94421953ea6b59c5b6 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a2f48a6c467d2cb28193177c0e0bf56a7f13f24 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:361974c8a4e1a72b68b6e29ae35c186bf8738090fe03264d1bdf7a548b9b9624 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a87404a3a83af7a97c16b959b43021ed320527b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:131f436c50f657b365d5fe23588b0cc94195b889950113e69247f9d938b5cfc8 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..164b25943be43e9981cf787697afa1638bc2b731 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86f74399e4f807276f173a4fa990d6bae365712b645346f729cea43a9568808 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc21d181fc1d0c999011d6d607e1bd390ffdcdae --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce28caba82ef84e39ef6525ef0f65db88fe1994a4a3b5321499faa436be872c +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49948f41c6e661dc8e86281aaf193afbd364546b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6edc104cde3c7c97393dc7bfbffdda0753dba924e70c69ce181c84a1dfae738 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..07f081d3b39b8222a03b6be187d4e432db80b23e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691d6cf7446400dcd8e7195e35882b082db2e76bb4075d3c1905d9bfbe36d298 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..812f1437c59f42e2c33235387d34c94bf0a0b22c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa603363da5cc2c91c44e7a4cf570f596c77b61960c3559b6dfce4621afe31cd +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3f0b5b6d3468580e4e8f819e41c26728e76d269 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb66c5ae7dd61c23810ac11793b33646e467350ae829985df8cbfb93ee765724 +size 199058647 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9bdc6f63933eb49530142597cd8be5daa0ede103 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16108a7ec62ef5e153f0a89d80fc6a69453c9b47b6070c3f07ef0b0b84007006 +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4e3f3c00f8e15ba038eb91e84f65376a3eeb508 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b9722fcd1ce69d3569e23c2019a0a7ce95da68e75406cce19369f3c142747be +size 199058850 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8243f93665062017294ebc7581e789fe5f1b627f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df01a4d669c1016a918b5b8a6087a6533a68cb69dd314d7bbdde8e10acb9edc +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd60e53390f0f41ed19c7e6ddb87ac07bdc7b3d7 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb81c6dacf979879282d78b771867c74d5cebb05cb8436262ca061b22b37002 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f4c37df550a4f8310d2a052e9c3923e52f61d3c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca63ff2bc3f1a3215e0a4e48387a6c75c094d7a8640321c0bbabfa5b26b51e31 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9eda7a46c7f9c79ad614752fc4e6b68dc8aeb930 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557db8dca6fe24c5dd894ad262a753d26b8ec1fd69af27f59f142d59493a8b88 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ed290636f5c4b0f6bff7dbcc89995804f13c58d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa1b249ab6d1426546fd1823ee513c30955c0fe9020374b5bf526dd9b07f793 +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca5ba1f741e1daae35db32dc1342adbbb0089875 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fe01065cd91fd5d47107bcc57b120bf31df55cb4078eb22707bf19d00335a5b +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebc09a7cc3bfb3848943755890c127af6a722c5c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053d469d2e7534fdb3d0fbc145e9d7ab7b4a247e952cea8340dc619617e3f139 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a817adf07429811f2f1e82316f41ef073f122b1 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:317ceee7bf9b497c63fb3cf61279c371a62330490e5b1a885541ee381f0fcc6f +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..022e7a4a7497b59b5c352fefd720a8c7eb6ae137 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a927384a17625f7708e5f1714734501fbb1ab0a4ea05813b493cf967149a16b2 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a8fe916c3be9c48b14bab89a39ebb2d91ea1e9e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d430b6f2ff33f9911eda4321bdb6454ba4efac5948e7da3f9bc63528b4a6455 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f6f7c181905529b08a4ed6f3742e6d7810c2840 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c1dbedf6537ce2f2fac6603227fd076e8f7f4d99925a4a9e251da76ab03f0b0 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c5d8ffaaaab15c07e5182618636fcc788d994dc --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271ff262d76fc405af1454b934ce0068e9fa9fb49533a6442973d93fbd6fb874 +size 199058722 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9b7a4f086fdc1affe408e8cad46023af02c64ce --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea480711cc650ca287f1eba116ac659b7e685535beb0048c7d9f162815a06f2d +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c29097a2d931ac5e4440423abe806ca3b7ee300a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea746ceffcfb80cd049e1632478b885522809f1e60e9afeb6b74438c7ab9efa +size 199058786 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b74eca20aa3d72820d90724bf1a17fec5f73ef6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e6fa23d0a370bdd92cf4c29dd7df389286b71da2113cfacda8cac5b7d32c2c +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a04c9f79cfd7a6b32010b9f8da5414785375f687 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636f2803de88b0f8ffce8ef6420e1f23ad54bb1dd5b5e993e9a41f1b248b21b5 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c36e0b3bc92d95ea756a6b0dd13e4a036e3dfa0 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0537a40730b19e555b67166f3ef71e8bb3b045b2cfe0d7fb5e4cef362f4d792 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ac70d17994e3dc49f67e214582a419548e7d6bf --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d851f9119590ea5ca54b39bbbc08835e29e46613340b7686c853122befa67bd2 +size 199058658 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9fa5f17fc949528be82028c033ea96a1ee550fd0 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e466f4c633e4ceb76924eac2284d0f8035498db2bbc2dd8cfd61014b1bb3df2 +size 199058839 diff --git a/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b4dd85805118a2908eda36132278f9300eb3b56 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a97a52a0376673d4ecdfcbfc11516b9938456caabdb0041177cad04fa9eab2 +size 199058839 diff --git a/4b284b12bc4seed1/global_step80108/layer_01-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef1a16a22c66c2f5bdd4e81692275ac5d530b3f4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57347b41d0e5ec30edf914820377375fb382d96f4fb6b4ef49a8e59d6dd47e44 +size 167511299 diff --git a/4b284b12bc4seed1/global_step80108/layer_01-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_01-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cab9c314611dd1d4992dd29bf28ddde02a3d3a32 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_01-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c0bf9a9a87e9c0a6c12e6b39017cf2559c58572d185f241721f50a11343d565 +size 167511299 diff --git a/4b284b12bc4seed1/global_step80108/layer_03-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef256d404bb44e6f5512714e7bb182fd08dc1d89 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a011bbc7fa8d877bc98f4783cf1ee2d90973c20c2bf573b2130a046e8e0294a4 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_03-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_03-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d058fb766f9edc0c642293ce051bf3cf92f2c5ba --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_03-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17caafb80a438a51281e5c66470b36bb3e68ea7ebc4c17900d47f20511d3c2b2 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_04-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..276545064eb6a31a7c275f9ade92d5548a6ef51b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25008ebc02996c2db36a27ac34cd59ce4d0f80d8dd94c732e856d46516d13c86 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_04-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_04-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c92df488df824a0aeea8d7b469401b9852827f78 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_04-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:360c43b56a19c418a22c4c753e79752bb08b02bfe54a7cd51270f0d3f532985b +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_05-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..918e28639b13085632b53225fa4a825724cc32e3 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e775d5a9ee95c46184a31c670466c9f022375a34242576974ef8b4982758a246 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_05-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_05-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..376f7e60574b4bbf34cbef0386004aa1d19abc16 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_05-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2af1ed58c91c268860cec1dc2cd5dc07264c8d4f08cf84dee8b16600d2cb9c31 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_06-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..337b0b68e427c52baadabea39af9937634feb68c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb994ff130a1b2e7ca74dc2f7a7a20be87fa31de204b673ad4dbdc20254ba73 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_06-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_06-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e59d1a2956489e176c4a85e2870b7316bf2b62e4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_06-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f85ee7754f3b889c5e93bba763afb55e2be077b67972e6644914b294b41a32b +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_07-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a646b687839fe08e1c5d1baf60ec96c32ef5825 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6893a4040e7a77a17d3fc9db608ad29cf97b5a8fc49b90107710eca58d85dd +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_07-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_07-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9148a10984c2a56dd3d3c1f8a60c070bed5e865 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_07-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0931dfc2ff16f5bff0af5e8d9f3ba16f1ec56941580d6ddad298aa06b10f8334 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_08-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aee502894405dcef99f1542e61e2671804460311 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4bbd99efcad9cf98fe805c6fdbc48f71f91042a1e97e72dcb986278eec540cf +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_08-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_08-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2af898b71d06205d69d688fb6199f9b954613fb --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_08-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8be94a1a95a7796450ac92c7bcffae50501e672ef19cf936f5d17603609095a +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_09-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3ed0b5f23e4f266391cefd3dda957b71b0dd4c4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:986c38d1e49077d6a6ffb14d46cbf4927bbd71cb545640db33f8b17500b9d053 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_09-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_09-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7eafbd8cec16a9323c50f7e9348c6e6c0bb18c6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_09-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b18798567c495545216de8185c2b38832b969df37e637e240a778a471c9ffa8 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_10-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b368c79cb6383e4fc5e2a36a7c297c8023591dfb --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29e6609f64b49fbd61a75c59fc5f588928d7d2ee2c589ef5b8312a2a17b77dd7 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_10-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_10-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..852569bdfb9d8f1ddac81b2ece5d69d2f5ffba81 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_10-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a373e72857c02f77ad3f2e414eb74c23fcdb20f220ffb2f02d92052cf7b34542 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_11-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..44a78ca90e4f3e8a740e38a343a006801d56748e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18683c6859a79abb9df40dcf35b69f9ae9f2a9f97428b8eb99a518a592472872 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_11-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_11-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3319de2423d4bc890ecef632fcc10e1d33b1ca9d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_11-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18208ea5062ce80a708a5c8b04a63f9de8d8cce03f335b86f2b34922c71c7290 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_12-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7639783e504ba6810a677ce69b1fe7ff8011141b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa9b2f4e886203b6133d851d5a4567971b74d9a634a8f3dac7f919167a8397d +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_12-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_12-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6bbfc98e4f79941a44c224a3d15b55a6fe34e6e4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_12-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48758fec5033e7e800191d98eaa50f1af1c2cf037f9841c19f731f573f928b08 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_13-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de72832a900cc128430ba2781f4b92d40cba1e33 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c30c39418dc36e19a513e32964e7d226c68a1035c8304e26e617ead8889935 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_13-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_13-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1db4ea249753e9c2a8bc7fed0b9a5e66edec32b3 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_13-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2ea980331ea858563a579f920bad7b5e4b5eeb4e766f9212c2ec4d7b2bb952 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_14-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e23776b8fbb76dac9fc391e6c25257da7ec57d4 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762db819ff94f756d87f310982f957ba5348915c3243208a67f3cfe6cb1e0852 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_14-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_14-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3468e0ad14039ae0dddaeec55f5ffabb09a61d88 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_14-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb5d08e08a3ed8036f7a21ff118faac3b8e4facf37d8de8f1752de4dda0d407d +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_15-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d7d9835824846aaee0106423589c104723f0a35 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6751836f2dca6d107fd878ca893d21abad5d9ce07d39b5bc422e2d944a6287b2 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_15-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_15-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..59e2faf36d24ae5ea2c487aed0ac98ddf9774bcc --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_15-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26258a98bcb8c90ff62e099fba4ecd8bdfcba699e4f4180a490ee69b060abb4 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_16-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3063d0a1e3938d7e56d61418637a1d1f00902aae --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181925d80a454821dc7c1a57e6c560c29efe3a39368f71c86403c1955f625e81 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_16-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_16-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cc9c74a8848a98b9151655c1e6861d65eedc88cf --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_16-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc529223efa7ed71114edcb5419ecc7260050b6607c0019dc512d6be22455306 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_17-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80b513ef5ed7e84ffaa97a2df5aa8a8ad2f0e2e9 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14aa83d2151d0ca8ebf82ff4dfdc1ecb6161ce1f3060d2cf13d08659df61af73 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_17-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_17-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..702bfb019b21c321cfbeb005d1f6f05f52e3e4d3 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_17-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bfe1d91388cef4bdc2b1dd8a02a422499ff3389ab0470e3ecca736231fa8414 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_18-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c06ece36e13500211aa6c2fe6c4bc56fa80861b1 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c470d3b9a2c1c2c4704487c69975877c2f6c59dc4f9ac2c403c261f7b5ed1e2 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_18-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_18-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bcb9bea4b7f664ecdd4cc27989f9204c5090a30c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_18-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e1d8f024c95d29c51ced8f1e66c24c8a2f21298af2d4d8e56ecfda273c5b08 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_19-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da2710aab094210348ed5d2aca568fa534b77c3d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2b94fed8f62a4bdbf5f314976174417b977518325573180d0c9296041a8ea5 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_19-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_19-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..40cd0d242c4085b509cdb33b77913e745ebe0862 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_19-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01fdcb76b95097d0ab14e15ee52afd3f62b724406bf7afdaa19469e55d2fea6 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_20-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..288c967a9cf82cfcbb67a342f4751f513663cd8a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:436c1fc5d09ca3223ed19306a2045b0429aff3a5172b68d3855515d2536b4a94 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_20-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_20-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c2a0030f389dc2e72f21d61391b6a68440a0f6e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_20-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03eb5fdc2a35343582dcf9a1f0b1e9c9f1246fc45730f49578106b4b0c01621c +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_21-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_21-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..00e6e2be5602aaed7baa2b48fd00d05fef76f990 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_21-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807dee6b2f173bd9f8291da40df4ef2b5de3d0eb8f62998a66a33d57aed00927 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_21-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_21-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4543a420de49ee93a943ae6f3cce980638aa6c49 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_21-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952293639b3ddf73cca45831677dc6d5e3ed28e4d0a31f66b3a07368c924fe14 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_22-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e99524306a8155856195746a226fd9472f1452ce --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba28d995d5af7b50b91520bb1de8c63f73f6d788595aa8f163566701f078105e +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_22-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_22-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eaddc1704c3e0484cd070a183386c69afeb9a812 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_22-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d86ed90efa8dfbf221f8b1953163337becf7b3fabf0b566d934e90cabe05676 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_23-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_23-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a16b5f4f67217e7a32d986d586cfa264f083c17 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_23-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc0bea6835895c28525cbc319741d1cec34f32970aea97716269b1298caa49ee +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_23-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_23-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..517c1980c499dc46149e32c5219eb96b3a781dc2 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_23-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd58ccf197f0e38f94e283bdaf83d54b4d49bfeb5c957cf23b24aa5719d5a0d +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_24-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_24-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a5142e7682881d7c6663a1e16882d7cfa9dd53f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_24-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d147a4a015db9b563d44521f74d6780561695997ef8bde2433c8a10fbbdb5e +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_24-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_24-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d6dded6d4a81de9c49ccf8b7f154d9e3b039b20 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_24-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f398c25bb4db91ee264a4d9b5aae36d955a61c6f8e97896b751b3ce05571fa +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_25-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_25-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dab7b6b81e278d11e3f89fb2ac0278a23c5ec8ad --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_25-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ba1636ffb214bd8e18c4ded9108de2fae34e3dae1fd1355bf86d6703877bc0 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_25-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_25-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9298cdac1dd608111492e69ee72890ca6122f5d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_25-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ad916f525bfc6f476b8eb71e7add8f37418a261adc0464b0836b94bff28813 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_26-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_26-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cd8a727d74333be238d09411cacd115d9390b4d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_26-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a1e360d85818a42a28698edd2e9bf01792cfe3301ba554de884d494520703b6 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_26-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_26-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..19145dfdbb71fd1f3e0a678c60710307f7293684 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_26-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97ec0be163185a133f3ac7b18ff0223b77c7ebfe4c2cf4defd7d1e31cd7d982 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_27-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_27-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..66d831e9290e6a89ad91c62a3b4beb3f616627cc --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_27-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cad5e1216f023d44668e290e71deea74271735561348b6ac27596009373d37c +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_27-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_27-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec7f03ad592774c0e98eb32fbf955919b2ae095c --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_27-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5309a7a7c51a36f63b2f7b64a137eb494fff95306ad37f26374db79e36ebf7 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_28-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_28-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cb20bca85c78ef92780caa2e3f24d62126f60001 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_28-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd72806f3c7ab33ea39a0e2d50fc9204da340915abd41819122dcda61313eef +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_28-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_28-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e2f6780178e777de2083025b9fa298edf6cbe8e --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_28-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5beb80dece73f5fcfffb626accfb3769cbf904e5732c47d387edc6d7b233dd6 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_29-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_29-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..605eb4485955a48410749ab51040ed40168de820 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_29-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64536ac7102ea4e7606b888fbe66b9ad1433a538f11f548e4d21d2d18c251108 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_29-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_29-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..66515c6a10cb32201b9bb31cb2a5f6ebfb00ee18 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_29-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94193fb9ffea0c4de5120b9c531bdf7a39a29f3383381b61f885102bfee68f87 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_30-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_30-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bd2ce6fb46e200d900c7ba006d1a318c6a4c4c9 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_30-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278198e806545304f668dd1a949d573e4c55d4456d53294d5406b0199e88ecd8 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_30-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_30-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c204f28803cd8b93ec3fa151971eac7796e6649b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_30-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d368507434e490fe9083881e52d071c5865a5e22bfdda74128ffe78821b40a +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_31-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_31-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8832c658e71c454cfd5cea2512c1b75938e86b2b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_31-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8977eb9d65f31f653e5ef2b9f79ebed676325f8160f5d0deae4323e3dee5d070 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_31-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_31-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd426270f9368c3a4ff34ec126e01a19f046425f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_31-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d4ac012c37fa53e26808879775a6d83b2221e2d995188cb8bb2a2076b212e1 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_32-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_32-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35ddb930dd1e575a398930c73a5e56771b8658f6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_32-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d610a8e0c1188cb73082b56c3148ba55c054fb08f44bd4974e703d6d33df49 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_32-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_32-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..372997dbd388dd12f50b5902756b9dc8ebb17b44 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_32-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4118a47636f08040b17fff6a02157eb282da581a64e31c5589e3a19a4644a080 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_33-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_33-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9cca7b09d5398822a88aa49c51f77c72dc521e35 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_33-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1798f20d8f68650b5b388d9cc5de65ec9b4482447642064a59fb97b4c45a3d42 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_33-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_33-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..58c1a060541823a02c37247bb800774be4b4a9d1 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_33-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b14dcc704a224d6d342bd61cf792e3a6f25b5a2de979bb997e0df521b78f3c +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_34-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_34-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..23302ef0c9b955ca9f19f78033eefc752277a126 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_34-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d969ebce179a50ba8203d82cbe8b06bc42dcebc79ea7c7865ac026b4f59351d +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_34-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_34-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e7a841aba0d4a833ad7084a9fa8ba8b5c24aa32 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_34-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afabeba23e3d88973105b6e4f065e9ab9347e6711e0438f8879df6f020d43413 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_35-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_35-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3fcee1c13833bf9ab00ea7ab19cb46ff88ac2e8 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_35-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd68fdf21ebcf9994299dba787740ba1a615d1425010dbaa8d9989adf783ad24 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_35-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_35-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..319d19f1ec405d95d51ace2a4d8ad47c06fb620a --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_35-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a664ef4315b2cfec2d8fc903f0fd832e24f3913d3c65e490819d91522923f9 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_36-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_36-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..571119d7232b900a9cdd403e16a6b67446733aaa --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_36-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c5ee5adba1e79d3934f4cd9cf4274d7e5cab56ea7020661d9a7b039d474f52 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_36-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_36-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b02b06824f824fa668d20a44d250397a6bcc42e5 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_36-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e0d2dc415338f5113e75217495dc30a37facc5ad0f54c4bc2fde04ffd5a3cfa +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_37-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_37-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e91dacb2b3dd860ad9c8802e31515dd11334704 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_37-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4765373e09e0b90722c9ff70b3b250141342281884765948b4872c83b5791ae6 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_37-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_37-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..74eabded0f4e8ac985b2181dd6b81ef1f0d808e6 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_37-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5b2772f99e1d35d0ed1691ae6601d3ffe8a6e63c3108a4057982f6324ce0351 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_38-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_38-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a49129e464e49c0a63ead8ea2e8b6c90b091c41f --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_38-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e0bd5c96eb6db63c431e8390b425cfc8eeb35b09239372f2c3cd4d5f1ef2d6 +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_38-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_38-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31ea21c524112484b602e7ef6b082516a7e54297 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_38-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76dcf339b5dede0d941e16df9dbe324c3a82865cbf6af5047456d3d48d68678e +size 113308931 diff --git a/4b284b12bc4seed1/global_step80108/layer_40-model_00-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_40-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0c44fceb9ff8b104fad5384e3ebf9dc06da4b93 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_40-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9959b5a25ce1b6d5e8fe3268306234603176ad1edb0da91783173bd482195a2 +size 13507 diff --git a/4b284b12bc4seed1/global_step80108/layer_40-model_01-model_states.pt b/4b284b12bc4seed1/global_step80108/layer_40-model_01-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76826ef508cd754d8f1fac476e0ca852a82b461d --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/layer_40-model_01-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce91fbc9d59ae5dbcf9af42ceee15b374cdea516376a16fd09c27d58945d7b06 +size 13507 diff --git a/4b284b12bc4seed1/global_step80108/mp_rank_00_model_states.pt b/4b284b12bc4seed1/global_step80108/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e91fde60a9e0511eefa598075167011ef707bf83 --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9c3421e5d1ecb512cc83c1135ef9c8fb2e38fe770b4a1f925b36efc4afe3e2 +size 51507 diff --git a/4b284b12bc4seed1/global_step80108/mp_rank_01_model_states.pt b/4b284b12bc4seed1/global_step80108/mp_rank_01_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98c879d2eb2fb44dbd729c24a9fd2b0d7e844c7b --- /dev/null +++ b/4b284b12bc4seed1/global_step80108/mp_rank_01_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0676a3c0186373fb1d8d2dfa93fe61ef5eb60b5e597668e0c2afcd3ba38599a4 +size 51507 diff --git a/4b284b12bc4seed1/transformers/config.json b/4b284b12bc4seed1/transformers/config.json new file mode 100644 index 0000000000000000000000000000000000000000..df814c3a71ee49044410636b5eeb4f43611690ba --- /dev/null +++ b/4b284b12bc4seed1/transformers/config.json @@ -0,0 +1 @@ +{"vocab_size": 50432, "n_positions": 2048, "n_embd": 3072, "n_layer": 36, "n_head": 24, "n_inner": 12288, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.25.0.dev0", "n_ctx": 1024, "gradient_checkpointing": false, "model_type": "gpt2"} \ No newline at end of file diff --git a/4b284b12bc4seed1/transformers/pytorch_model.bin b/4b284b12bc4seed1/transformers/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..0eb11630dc18904b9f3acfc6a92687c23695ef4a --- /dev/null +++ b/4b284b12bc4seed1/transformers/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94c7a78e0ec5745fb40ff8e1f5008c6cf679f737c3e994e5db101a1e63f1e174 +size 8781203669 diff --git a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_2.json b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_2.json index 51f25824fa06c2908a2eb024028bc5aa073d50c0..e2200004eeb6ce4ee945fbfc2edfa43cabef6776 100644 --- a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_2.json +++ b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_2.json @@ -48,6 +48,24 @@ "acc_stderr": 0.010096663811817683, "acc_norm": 0.5521885521885522, "acc_norm_stderr": 0.010203742451111527 + }, + "arc_challenge": { + "acc": 0.27559726962457337, + "acc_stderr": 0.01305716965576184, + "acc_norm": 0.310580204778157, + "acc_norm_stderr": 0.013522292098053057 + }, + "sciq": { + "acc": 0.847, + "acc_stderr": 0.011389500459665533, + "acc_norm": 0.793, + "acc_norm_stderr": 0.012818553557843986 + }, + "piqa": { + "acc": 0.7513601741022851, + "acc_stderr": 0.010084511234296857, + "acc_norm": 0.7611534276387377, + "acc_norm_stderr": 0.009948120385337484 } }, "versions": { @@ -61,6 +79,9 @@ "winogrande": 0, "storycloze_2016": 0, "boolq": 1, - "arc_easy": 0 + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_2_lm-eval_global_step80108_2023-02-24-21-34-52_2shots_backup.json b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_2_lm-eval_global_step80108_2023-02-24-21-34-52_2shots_backup.json index 51f25824fa06c2908a2eb024028bc5aa073d50c0..e2200004eeb6ce4ee945fbfc2edfa43cabef6776 100644 --- a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_2_lm-eval_global_step80108_2023-02-24-21-34-52_2shots_backup.json +++ b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_2_lm-eval_global_step80108_2023-02-24-21-34-52_2shots_backup.json @@ -48,6 +48,24 @@ "acc_stderr": 0.010096663811817683, "acc_norm": 0.5521885521885522, "acc_norm_stderr": 0.010203742451111527 + }, + "arc_challenge": { + "acc": 0.27559726962457337, + "acc_stderr": 0.01305716965576184, + "acc_norm": 0.310580204778157, + "acc_norm_stderr": 0.013522292098053057 + }, + "sciq": { + "acc": 0.847, + "acc_stderr": 0.011389500459665533, + "acc_norm": 0.793, + "acc_norm_stderr": 0.012818553557843986 + }, + "piqa": { + "acc": 0.7513601741022851, + "acc_stderr": 0.010084511234296857, + "acc_norm": 0.7611534276387377, + "acc_norm_stderr": 0.009948120385337484 } }, "versions": { @@ -61,6 +79,9 @@ "winogrande": 0, "storycloze_2016": 0, "boolq": 1, - "arc_easy": 0 + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_3.json b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_3.json index d9b2716578a8dae06c9810eda801b60ca760c04f..cf774fafd67e7c100ea47daf776bd295636a8d69 100644 --- a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_3.json +++ b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_3.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.7033671833244255, "acc_stderr": 0.010562819181563219 + }, + "boolq": { + "acc": 0.6048929663608563, + "acc_stderr": 0.008550454248280891 + }, + "arc_easy": { + "acc": 0.5896464646464646, + "acc_stderr": 0.010093531255765465, + "acc_norm": 0.5484006734006734, + "acc_norm_stderr": 0.010211600726405236 + }, + "arc_challenge": { + "acc": 0.2764505119453925, + "acc_stderr": 0.013069662474252425, + "acc_norm": 0.3046075085324232, + "acc_norm_stderr": 0.013449522109932492 + }, + "sciq": { + "acc": 0.856, + "acc_stderr": 0.01110798754893915, + "acc_norm": 0.798, + "acc_norm_stderr": 0.012702651587655137 + }, + "piqa": { + "acc": 0.7442872687704026, + "acc_stderr": 0.01017869010945986, + "acc_norm": 0.7557127312295974, + "acc_norm_stderr": 0.010024765172284253 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_3_lm-eval_global_step80108_2023-02-24-21-34-52_3shots_backup.json b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_3_lm-eval_global_step80108_2023-02-24-21-34-52_3shots_backup.json index d9b2716578a8dae06c9810eda801b60ca760c04f..cf774fafd67e7c100ea47daf776bd295636a8d69 100644 --- a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_3_lm-eval_global_step80108_2023-02-24-21-34-52_3shots_backup.json +++ b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_3_lm-eval_global_step80108_2023-02-24-21-34-52_3shots_backup.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.7033671833244255, "acc_stderr": 0.010562819181563219 + }, + "boolq": { + "acc": 0.6048929663608563, + "acc_stderr": 0.008550454248280891 + }, + "arc_easy": { + "acc": 0.5896464646464646, + "acc_stderr": 0.010093531255765465, + "acc_norm": 0.5484006734006734, + "acc_norm_stderr": 0.010211600726405236 + }, + "arc_challenge": { + "acc": 0.2764505119453925, + "acc_stderr": 0.013069662474252425, + "acc_norm": 0.3046075085324232, + "acc_norm_stderr": 0.013449522109932492 + }, + "sciq": { + "acc": 0.856, + "acc_stderr": 0.01110798754893915, + "acc_norm": 0.798, + "acc_norm_stderr": 0.012702651587655137 + }, + "piqa": { + "acc": 0.7442872687704026, + "acc_stderr": 0.01017869010945986, + "acc_norm": 0.7557127312295974, + "acc_norm_stderr": 0.010024765172284253 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_4.json b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_4.json index 79d4a5e867204405bfb9c9998b26145f1537b942..d7d81bf46230fbf4014382b33813dd71d90c5048 100644 --- a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_4.json +++ b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_4.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4671380203146783, + "acc_stderr": 0.004978992721242829, + "acc_norm": 0.6201951802429795, + "acc_norm_stderr": 0.004843462545943485 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.0300523034631437 + }, + "winogrande": { + "acc": 0.574585635359116, + "acc_stderr": 0.013895257666646378 + }, + "storycloze_2016": { + "acc": 0.706574024585783, + "acc_stderr": 0.01052948933474447 + }, + "boolq": { + "acc": 0.6085626911314985, + "acc_stderr": 0.00853643052440395 + }, + "arc_easy": { + "acc": 0.5816498316498316, + "acc_stderr": 0.01012206147074285, + "acc_norm": 0.5526094276094277, + "acc_norm_stderr": 0.01020283238541565 + }, + "arc_challenge": { + "acc": 0.27047781569965873, + "acc_stderr": 0.012980954547659554, + "acc_norm": 0.30631399317406144, + "acc_norm_stderr": 0.013470584417276511 + }, + "sciq": { + "acc": 0.851, + "acc_stderr": 0.011266140684632178, + "acc_norm": 0.802, + "acc_norm_stderr": 0.012607733934175313 + }, + "piqa": { + "acc": 0.7529923830250272, + "acc_stderr": 0.010062268140772629, + "acc_norm": 0.7622415669205659, + "acc_norm_stderr": 0.009932525779525494 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_4_lm-eval_global_step80108_2023-02-24-21-34-52_4shots_backup.json b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_4_lm-eval_global_step80108_2023-02-24-21-34-52_4shots_backup.json index 79d4a5e867204405bfb9c9998b26145f1537b942..d7d81bf46230fbf4014382b33813dd71d90c5048 100644 --- a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_4_lm-eval_global_step80108_2023-02-24-21-34-52_4shots_backup.json +++ b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_4_lm-eval_global_step80108_2023-02-24-21-34-52_4shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4671380203146783, + "acc_stderr": 0.004978992721242829, + "acc_norm": 0.6201951802429795, + "acc_norm_stderr": 0.004843462545943485 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.0300523034631437 + }, + "winogrande": { + "acc": 0.574585635359116, + "acc_stderr": 0.013895257666646378 + }, + "storycloze_2016": { + "acc": 0.706574024585783, + "acc_stderr": 0.01052948933474447 + }, + "boolq": { + "acc": 0.6085626911314985, + "acc_stderr": 0.00853643052440395 + }, + "arc_easy": { + "acc": 0.5816498316498316, + "acc_stderr": 0.01012206147074285, + "acc_norm": 0.5526094276094277, + "acc_norm_stderr": 0.01020283238541565 + }, + "arc_challenge": { + "acc": 0.27047781569965873, + "acc_stderr": 0.012980954547659554, + "acc_norm": 0.30631399317406144, + "acc_norm_stderr": 0.013470584417276511 + }, + "sciq": { + "acc": 0.851, + "acc_stderr": 0.011266140684632178, + "acc_norm": 0.802, + "acc_norm_stderr": 0.012607733934175313 + }, + "piqa": { + "acc": 0.7529923830250272, + "acc_stderr": 0.010062268140772629, + "acc_norm": 0.7622415669205659, + "acc_norm_stderr": 0.009932525779525494 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_5.json b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_5.json index 976bd030ab7d73db871d4bbf8d0679d52b2ff11c..307d41a0645efdb0b14e9778f13673d37cac876e 100644 --- a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_5.json +++ b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_5.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 + }, + "hellaswag": { + "acc": 0.46853216490738897, + "acc_stderr": 0.004979889597551664, + "acc_norm": 0.6222863971320454, + "acc_norm_stderr": 0.00483824641078626 + }, + "rte": { + "acc": 0.5379061371841155, + "acc_stderr": 0.030009848912529117 + }, + "winogrande": { + "acc": 0.5840568271507498, + "acc_stderr": 0.013852485356798259 + }, + "storycloze_2016": { + "acc": 0.7055050774986639, + "acc_stderr": 0.010540668963800296 + }, + "boolq": { + "acc": 0.6073394495412844, + "acc_stderr": 0.008541161248702914 + }, + "arc_easy": { + "acc": 0.5829124579124579, + "acc_stderr": 0.010117738967781988, + "acc_norm": 0.5441919191919192, + "acc_norm_stderr": 0.010219631763437851 + }, + "arc_challenge": { + "acc": 0.28924914675767915, + "acc_stderr": 0.013250012579393443, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.01343890918477876 + }, + "sciq": { + "acc": 0.848, + "acc_stderr": 0.011358918303475275, + "acc_norm": 0.8, + "acc_norm_stderr": 0.01265543994336665 + }, + "piqa": { + "acc": 0.7475516866158868, + "acc_stderr": 0.010135665547362364, + "acc_norm": 0.7568008705114254, + "acc_norm_stderr": 0.010009611953858917 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_5_lm-eval_global_step80108_2023-02-24-21-34-52_5shots_backup.json b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_5_lm-eval_global_step80108_2023-02-24-21-34-52_5shots_backup.json index 976bd030ab7d73db871d4bbf8d0679d52b2ff11c..307d41a0645efdb0b14e9778f13673d37cac876e 100644 --- a/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_5_lm-eval_global_step80108_2023-02-24-21-34-52_5shots_backup.json +++ b/4b284b12bc4seed4/evaluation/rankeval/4b284b12bc4seed4_5_lm-eval_global_step80108_2023-02-24-21-34-52_5shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 + }, + "hellaswag": { + "acc": 0.46853216490738897, + "acc_stderr": 0.004979889597551664, + "acc_norm": 0.6222863971320454, + "acc_norm_stderr": 0.00483824641078626 + }, + "rte": { + "acc": 0.5379061371841155, + "acc_stderr": 0.030009848912529117 + }, + "winogrande": { + "acc": 0.5840568271507498, + "acc_stderr": 0.013852485356798259 + }, + "storycloze_2016": { + "acc": 0.7055050774986639, + "acc_stderr": 0.010540668963800296 + }, + "boolq": { + "acc": 0.6073394495412844, + "acc_stderr": 0.008541161248702914 + }, + "arc_easy": { + "acc": 0.5829124579124579, + "acc_stderr": 0.010117738967781988, + "acc_norm": 0.5441919191919192, + "acc_norm_stderr": 0.010219631763437851 + }, + "arc_challenge": { + "acc": 0.28924914675767915, + "acc_stderr": 0.013250012579393443, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.01343890918477876 + }, + "sciq": { + "acc": 0.848, + "acc_stderr": 0.011358918303475275, + "acc_norm": 0.8, + "acc_norm_stderr": 0.01265543994336665 + }, + "piqa": { + "acc": 0.7475516866158868, + "acc_stderr": 0.010135665547362364, + "acc_norm": 0.7568008705114254, + "acc_norm_stderr": 0.010009611953858917 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_2.json b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_2.json index 96b27015d02bcb3f871336edac9f4e384d0f3771..40d51e1255cc9de4f561f1e0be9e7dd847ab5074 100644 --- a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_2.json +++ b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_2.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.6980224478888295, "acc_stderr": 0.010616985436073357 + }, + "boolq": { + "acc": 0.617737003058104, + "acc_stderr": 0.008499149690449272 + }, + "arc_easy": { + "acc": 0.6043771043771043, + "acc_stderr": 0.010033741393430986, + "acc_norm": 0.5778619528619529, + "acc_norm_stderr": 0.01013462052459227 + }, + "arc_challenge": { + "acc": 0.27303754266211605, + "acc_stderr": 0.01301933276263575, + "acc_norm": 0.30119453924914674, + "acc_norm_stderr": 0.013406741767847626 + }, + "sciq": { + "acc": 0.896, + "acc_stderr": 0.009658016218524305, + "acc_norm": 0.863, + "acc_norm_stderr": 0.010878848714333316 + }, + "piqa": { + "acc": 0.7377584330794341, + "acc_stderr": 0.01026250256517245, + "acc_norm": 0.7442872687704026, + "acc_norm_stderr": 0.01017869010945987 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json index 96b27015d02bcb3f871336edac9f4e384d0f3771..40d51e1255cc9de4f561f1e0be9e7dd847ab5074 100644 --- a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json +++ b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.6980224478888295, "acc_stderr": 0.010616985436073357 + }, + "boolq": { + "acc": 0.617737003058104, + "acc_stderr": 0.008499149690449272 + }, + "arc_easy": { + "acc": 0.6043771043771043, + "acc_stderr": 0.010033741393430986, + "acc_norm": 0.5778619528619529, + "acc_norm_stderr": 0.01013462052459227 + }, + "arc_challenge": { + "acc": 0.27303754266211605, + "acc_stderr": 0.01301933276263575, + "acc_norm": 0.30119453924914674, + "acc_norm_stderr": 0.013406741767847626 + }, + "sciq": { + "acc": 0.896, + "acc_stderr": 0.009658016218524305, + "acc_norm": 0.863, + "acc_norm_stderr": 0.010878848714333316 + }, + "piqa": { + "acc": 0.7377584330794341, + "acc_stderr": 0.01026250256517245, + "acc_norm": 0.7442872687704026, + "acc_norm_stderr": 0.01017869010945987 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_3.json b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_3.json index f7622601ee79f992a6c8ec0b0c100be0ab6993e0..9922d75a28f3ef6180b9e972ccadca8156decdc9 100644 --- a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_3.json +++ b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_3.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.8, "acc_stderr": 0.04020151261036844 + }, + "hellaswag": { + "acc": 0.44851623182632944, + "acc_stderr": 0.004963259311700562, + "acc_norm": 0.5903206532563234, + "acc_norm_stderr": 0.004907694727935689 + }, + "rte": { + "acc": 0.5523465703971119, + "acc_stderr": 0.02993107036293953 + }, + "winogrande": { + "acc": 0.5643251775848461, + "acc_stderr": 0.01393570973961571 + }, + "storycloze_2016": { + "acc": 0.706574024585783, + "acc_stderr": 0.010529489334744471 + }, + "boolq": { + "acc": 0.5981651376146789, + "acc_stderr": 0.008574857171671134 + }, + "arc_easy": { + "acc": 0.5989057239057239, + "acc_stderr": 0.010057051106534372, + "acc_norm": 0.5812289562289562, + "acc_norm_stderr": 0.010123487160167819 + }, + "arc_challenge": { + "acc": 0.2832764505119454, + "acc_stderr": 0.013167478735134575, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.01343890918477876 + }, + "sciq": { + "acc": 0.899, + "acc_stderr": 0.009533618929341002, + "acc_norm": 0.872, + "acc_norm_stderr": 0.010570133761108658 + }, + "piqa": { + "acc": 0.7426550598476604, + "acc_stderr": 0.01019992106479251, + "acc_norm": 0.7535364526659413, + "acc_norm_stderr": 0.010054810789671811 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json index f7622601ee79f992a6c8ec0b0c100be0ab6993e0..9922d75a28f3ef6180b9e972ccadca8156decdc9 100644 --- a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json +++ b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.8, "acc_stderr": 0.04020151261036844 + }, + "hellaswag": { + "acc": 0.44851623182632944, + "acc_stderr": 0.004963259311700562, + "acc_norm": 0.5903206532563234, + "acc_norm_stderr": 0.004907694727935689 + }, + "rte": { + "acc": 0.5523465703971119, + "acc_stderr": 0.02993107036293953 + }, + "winogrande": { + "acc": 0.5643251775848461, + "acc_stderr": 0.01393570973961571 + }, + "storycloze_2016": { + "acc": 0.706574024585783, + "acc_stderr": 0.010529489334744471 + }, + "boolq": { + "acc": 0.5981651376146789, + "acc_stderr": 0.008574857171671134 + }, + "arc_easy": { + "acc": 0.5989057239057239, + "acc_stderr": 0.010057051106534372, + "acc_norm": 0.5812289562289562, + "acc_norm_stderr": 0.010123487160167819 + }, + "arc_challenge": { + "acc": 0.2832764505119454, + "acc_stderr": 0.013167478735134575, + "acc_norm": 0.3037542662116041, + "acc_norm_stderr": 0.01343890918477876 + }, + "sciq": { + "acc": 0.899, + "acc_stderr": 0.009533618929341002, + "acc_norm": 0.872, + "acc_norm_stderr": 0.010570133761108658 + }, + "piqa": { + "acc": 0.7426550598476604, + "acc_stderr": 0.01019992106479251, + "acc_norm": 0.7535364526659413, + "acc_norm_stderr": 0.010054810789671811 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_4.json b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_4.json index 5c561eda27aeee0d085cc263089cff34ddf22b8c..506b233d8626446b9d36f6d6790545f4badd3ec3 100644 --- a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_4.json +++ b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_4.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036622 + }, + "hellaswag": { + "acc": 0.4493128858793069, + "acc_stderr": 0.0049640758701203404, + "acc_norm": 0.5959968133837881, + "acc_norm_stderr": 0.0048969523785069215 + }, + "rte": { + "acc": 0.5451263537906137, + "acc_stderr": 0.029973636495415252 + }, + "winogrande": { + "acc": 0.5556432517758485, + "acc_stderr": 0.013965196769083553 + }, + "storycloze_2016": { + "acc": 0.6990913949759487, + "acc_stderr": 0.010606289538707344 + }, + "boolq": { + "acc": 0.6024464831804281, + "acc_stderr": 0.008559523256936824 + }, + "arc_easy": { + "acc": 0.6035353535353535, + "acc_stderr": 0.010037412763064526, + "acc_norm": 0.5854377104377104, + "acc_norm_stderr": 0.010108889212447783 + }, + "arc_challenge": { + "acc": 0.2773037542662116, + "acc_stderr": 0.013082095839059374, + "acc_norm": 0.30887372013651876, + "acc_norm_stderr": 0.013501770929344003 + }, + "sciq": { + "acc": 0.902, + "acc_stderr": 0.009406619184621236, + "acc_norm": 0.882, + "acc_norm_stderr": 0.01020686926438179 + }, + "piqa": { + "acc": 0.7383025027203483, + "acc_stderr": 0.010255630772708232, + "acc_norm": 0.7470076169749728, + "acc_norm_stderr": 0.01014288869886245 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json index 5c561eda27aeee0d085cc263089cff34ddf22b8c..506b233d8626446b9d36f6d6790545f4badd3ec3 100644 --- a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json +++ b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036622 + }, + "hellaswag": { + "acc": 0.4493128858793069, + "acc_stderr": 0.0049640758701203404, + "acc_norm": 0.5959968133837881, + "acc_norm_stderr": 0.0048969523785069215 + }, + "rte": { + "acc": 0.5451263537906137, + "acc_stderr": 0.029973636495415252 + }, + "winogrande": { + "acc": 0.5556432517758485, + "acc_stderr": 0.013965196769083553 + }, + "storycloze_2016": { + "acc": 0.6990913949759487, + "acc_stderr": 0.010606289538707344 + }, + "boolq": { + "acc": 0.6024464831804281, + "acc_stderr": 0.008559523256936824 + }, + "arc_easy": { + "acc": 0.6035353535353535, + "acc_stderr": 0.010037412763064526, + "acc_norm": 0.5854377104377104, + "acc_norm_stderr": 0.010108889212447783 + }, + "arc_challenge": { + "acc": 0.2773037542662116, + "acc_stderr": 0.013082095839059374, + "acc_norm": 0.30887372013651876, + "acc_norm_stderr": 0.013501770929344003 + }, + "sciq": { + "acc": 0.902, + "acc_stderr": 0.009406619184621236, + "acc_norm": 0.882, + "acc_norm_stderr": 0.01020686926438179 + }, + "piqa": { + "acc": 0.7383025027203483, + "acc_stderr": 0.010255630772708232, + "acc_norm": 0.7470076169749728, + "acc_norm_stderr": 0.01014288869886245 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_5.json b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_5.json index 0e203465b9be7659ec6d4d2007dc9fced1b83c1b..235373655f02ae7275ada64cb2204d7cc76efe29 100644 --- a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_5.json +++ b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_5.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 + }, + "hellaswag": { + "acc": 0.4470225054769966, + "acc_stderr": 0.004961693567208819, + "acc_norm": 0.5973909579764987, + "acc_norm_stderr": 0.004894210011303224 + }, + "rte": { + "acc": 0.5415162454873647, + "acc_stderr": 0.029992535385373314 + }, + "winogrande": { + "acc": 0.5572217837411207, + "acc_stderr": 0.013960157350784983 + }, + "storycloze_2016": { + "acc": 0.6996258685195083, + "acc_stderr": 0.010600915927985021 + }, + "boolq": { + "acc": 0.6009174311926605, + "acc_stderr": 0.008565077958836783 + }, + "arc_easy": { + "acc": 0.6094276094276094, + "acc_stderr": 0.010011059112064237, + "acc_norm": 0.5951178451178452, + "acc_norm_stderr": 0.0100724239603957 + }, + "arc_challenge": { + "acc": 0.2935153583617747, + "acc_stderr": 0.01330725044494112, + "acc_norm": 0.318259385665529, + "acc_norm_stderr": 0.013611993916971453 + }, + "sciq": { + "acc": 0.907, + "acc_stderr": 0.00918887563499668, + "acc_norm": 0.886, + "acc_norm_stderr": 0.010055103435823332 + }, + "piqa": { + "acc": 0.735038084874864, + "acc_stderr": 0.010296557993316047, + "acc_norm": 0.7529923830250272, + "acc_norm_stderr": 0.01006226814077264 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json index 0e203465b9be7659ec6d4d2007dc9fced1b83c1b..235373655f02ae7275ada64cb2204d7cc76efe29 100644 --- a/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json +++ b/4b284b17bc4seed1/evaluation/rankeval/4b284b17bc4seed1_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 + }, + "hellaswag": { + "acc": 0.4470225054769966, + "acc_stderr": 0.004961693567208819, + "acc_norm": 0.5973909579764987, + "acc_norm_stderr": 0.004894210011303224 + }, + "rte": { + "acc": 0.5415162454873647, + "acc_stderr": 0.029992535385373314 + }, + "winogrande": { + "acc": 0.5572217837411207, + "acc_stderr": 0.013960157350784983 + }, + "storycloze_2016": { + "acc": 0.6996258685195083, + "acc_stderr": 0.010600915927985021 + }, + "boolq": { + "acc": 0.6009174311926605, + "acc_stderr": 0.008565077958836783 + }, + "arc_easy": { + "acc": 0.6094276094276094, + "acc_stderr": 0.010011059112064237, + "acc_norm": 0.5951178451178452, + "acc_norm_stderr": 0.0100724239603957 + }, + "arc_challenge": { + "acc": 0.2935153583617747, + "acc_stderr": 0.01330725044494112, + "acc_norm": 0.318259385665529, + "acc_norm_stderr": 0.013611993916971453 + }, + "sciq": { + "acc": 0.907, + "acc_stderr": 0.00918887563499668, + "acc_norm": 0.886, + "acc_norm_stderr": 0.010055103435823332 + }, + "piqa": { + "acc": 0.735038084874864, + "acc_stderr": 0.010296557993316047, + "acc_norm": 0.7529923830250272, + "acc_norm_stderr": 0.01006226814077264 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_0.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_0.json new file mode 100644 index 0000000000000000000000000000000000000000..6404bc9f7e1ad74f8cdeda4d1afdffb2968acc20 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_0.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.333, + "acc_stderr": 0.014910846164229859 + }, + "anli_r2": { + "acc": 0.327, + "acc_stderr": 0.014842213153411247 + }, + "anli_r3": { + "acc": 0.3308333333333333, + "acc_stderr": 0.013588208070709006 + }, + "cb": { + "acc": 0.4107142857142857, + "acc_stderr": 0.0663363415035954, + "f1": 0.3057817998994469 + }, + "copa": { + "acc": 0.77, + "acc_stderr": 0.04229525846816506 + }, + "hellaswag": { + "acc": 0.47161919936267677, + "acc_stderr": 0.004981736689518751, + "acc_norm": 0.6169089822744473, + "acc_norm_stderr": 0.004851466623601434 + }, + "rte": { + "acc": 0.5848375451263538, + "acc_stderr": 0.02966006629089348 + }, + "winogrande": { + "acc": 0.5816890292028414, + "acc_stderr": 0.013863669961195904 + }, + "storycloze_2016": { + "acc": 0.7135221806520577, + "acc_stderr": 0.01045510591863303 + }, + "boolq": { + "acc": 0.618348623853211, + "acc_stderr": 0.008496550741178261 + }, + "arc_easy": { + "acc": 0.5837542087542088, + "acc_stderr": 0.010114819404500867, + "acc_norm": 0.5223063973063973, + "acc_norm_stderr": 0.010249568404555655 + }, + "arc_challenge": { + "acc": 0.26791808873720135, + "acc_stderr": 0.012942030195136435, + "acc_norm": 0.295221843003413, + "acc_norm_stderr": 0.013329750293382316 + }, + "sciq": { + "acc": 0.846, + "acc_stderr": 0.011419913065098715, + "acc_norm": 0.742, + "acc_norm_stderr": 0.013842963108656604 + }, + "piqa": { + "acc": 0.7557127312295974, + "acc_stderr": 0.010024765172284253, + "acc_norm": 0.764417845484222, + "acc_norm_stderr": 0.009901067586473883 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_0_lm-eval_global_step80108_2023-02-24-23-57-50_0shots_backup.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_0_lm-eval_global_step80108_2023-02-24-23-57-50_0shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..6404bc9f7e1ad74f8cdeda4d1afdffb2968acc20 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_0_lm-eval_global_step80108_2023-02-24-23-57-50_0shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.333, + "acc_stderr": 0.014910846164229859 + }, + "anli_r2": { + "acc": 0.327, + "acc_stderr": 0.014842213153411247 + }, + "anli_r3": { + "acc": 0.3308333333333333, + "acc_stderr": 0.013588208070709006 + }, + "cb": { + "acc": 0.4107142857142857, + "acc_stderr": 0.0663363415035954, + "f1": 0.3057817998994469 + }, + "copa": { + "acc": 0.77, + "acc_stderr": 0.04229525846816506 + }, + "hellaswag": { + "acc": 0.47161919936267677, + "acc_stderr": 0.004981736689518751, + "acc_norm": 0.6169089822744473, + "acc_norm_stderr": 0.004851466623601434 + }, + "rte": { + "acc": 0.5848375451263538, + "acc_stderr": 0.02966006629089348 + }, + "winogrande": { + "acc": 0.5816890292028414, + "acc_stderr": 0.013863669961195904 + }, + "storycloze_2016": { + "acc": 0.7135221806520577, + "acc_stderr": 0.01045510591863303 + }, + "boolq": { + "acc": 0.618348623853211, + "acc_stderr": 0.008496550741178261 + }, + "arc_easy": { + "acc": 0.5837542087542088, + "acc_stderr": 0.010114819404500867, + "acc_norm": 0.5223063973063973, + "acc_norm_stderr": 0.010249568404555655 + }, + "arc_challenge": { + "acc": 0.26791808873720135, + "acc_stderr": 0.012942030195136435, + "acc_norm": 0.295221843003413, + "acc_norm_stderr": 0.013329750293382316 + }, + "sciq": { + "acc": 0.846, + "acc_stderr": 0.011419913065098715, + "acc_norm": 0.742, + "acc_norm_stderr": 0.013842963108656604 + }, + "piqa": { + "acc": 0.7557127312295974, + "acc_stderr": 0.010024765172284253, + "acc_norm": 0.764417845484222, + "acc_norm_stderr": 0.009901067586473883 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_1.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_1.json new file mode 100644 index 0000000000000000000000000000000000000000..40f93f9ad2bb8dd4af3719bee54423537b07df94 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_1.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.328, + "acc_stderr": 0.014853842487270334 + }, + "anli_r2": { + "acc": 0.327, + "acc_stderr": 0.014842213153411242 + }, + "anli_r3": { + "acc": 0.35333333333333333, + "acc_stderr": 0.013804572162314928 + }, + "cb": { + "acc": 0.375, + "acc_stderr": 0.06527912098338669, + "f1": 0.2877899877899878 + }, + "copa": { + "acc": 0.76, + "acc_stderr": 0.04292346959909282 + }, + "hellaswag": { + "acc": 0.4675363473411671, + "acc_stderr": 0.004979252954977312, + "acc_norm": 0.614618601872137, + "acc_norm_stderr": 0.004856906473719403 + }, + "rte": { + "acc": 0.5234657039711191, + "acc_stderr": 0.03006330041190266 + }, + "winogrande": { + "acc": 0.590370955011839, + "acc_stderr": 0.013821049109655476 + }, + "storycloze_2016": { + "acc": 0.709246392303581, + "acc_stderr": 0.010501233625213078 + }, + "boolq": { + "acc": 0.6143730886850153, + "acc_stderr": 0.008513189460768051 + }, + "arc_easy": { + "acc": 0.601010101010101, + "acc_stderr": 0.010048240683798755, + "acc_norm": 0.5669191919191919, + "acc_norm_stderr": 0.010167478013701792 + }, + "arc_challenge": { + "acc": 0.2986348122866894, + "acc_stderr": 0.013374078615068752, + "acc_norm": 0.31399317406143346, + "acc_norm_stderr": 0.013562691224726297 + }, + "sciq": { + "acc": 0.895, + "acc_stderr": 0.00969892102602495, + "acc_norm": 0.867, + "acc_norm_stderr": 0.01074366913239733 + }, + "piqa": { + "acc": 0.750816104461371, + "acc_stderr": 0.010091882770120214, + "acc_norm": 0.7633297062023939, + "acc_norm_stderr": 0.009916841655042809 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_1_lm-eval_global_step80108_2023-02-24-23-57-50_1shots_backup.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_1_lm-eval_global_step80108_2023-02-24-23-57-50_1shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..40f93f9ad2bb8dd4af3719bee54423537b07df94 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_1_lm-eval_global_step80108_2023-02-24-23-57-50_1shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.328, + "acc_stderr": 0.014853842487270334 + }, + "anli_r2": { + "acc": 0.327, + "acc_stderr": 0.014842213153411242 + }, + "anli_r3": { + "acc": 0.35333333333333333, + "acc_stderr": 0.013804572162314928 + }, + "cb": { + "acc": 0.375, + "acc_stderr": 0.06527912098338669, + "f1": 0.2877899877899878 + }, + "copa": { + "acc": 0.76, + "acc_stderr": 0.04292346959909282 + }, + "hellaswag": { + "acc": 0.4675363473411671, + "acc_stderr": 0.004979252954977312, + "acc_norm": 0.614618601872137, + "acc_norm_stderr": 0.004856906473719403 + }, + "rte": { + "acc": 0.5234657039711191, + "acc_stderr": 0.03006330041190266 + }, + "winogrande": { + "acc": 0.590370955011839, + "acc_stderr": 0.013821049109655476 + }, + "storycloze_2016": { + "acc": 0.709246392303581, + "acc_stderr": 0.010501233625213078 + }, + "boolq": { + "acc": 0.6143730886850153, + "acc_stderr": 0.008513189460768051 + }, + "arc_easy": { + "acc": 0.601010101010101, + "acc_stderr": 0.010048240683798755, + "acc_norm": 0.5669191919191919, + "acc_norm_stderr": 0.010167478013701792 + }, + "arc_challenge": { + "acc": 0.2986348122866894, + "acc_stderr": 0.013374078615068752, + "acc_norm": 0.31399317406143346, + "acc_norm_stderr": 0.013562691224726297 + }, + "sciq": { + "acc": 0.895, + "acc_stderr": 0.00969892102602495, + "acc_norm": 0.867, + "acc_norm_stderr": 0.01074366913239733 + }, + "piqa": { + "acc": 0.750816104461371, + "acc_stderr": 0.010091882770120214, + "acc_norm": 0.7633297062023939, + "acc_norm_stderr": 0.009916841655042809 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_2.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_2.json new file mode 100644 index 0000000000000000000000000000000000000000..ab6c14d5bf3ae85028b61141005d2f2634890ff1 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_2.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.332, + "acc_stderr": 0.014899597242811476 + }, + "anli_r2": { + "acc": 0.34, + "acc_stderr": 0.014987482264363937 + }, + "anli_r3": { + "acc": 0.3233333333333333, + "acc_stderr": 0.01350837286730022 + }, + "cb": { + "acc": 0.35714285714285715, + "acc_stderr": 0.06460957383809221, + "f1": 0.2989672364672365 + }, + "copa": { + "acc": 0.8, + "acc_stderr": 0.04020151261036845 + }, + "hellaswag": { + "acc": 0.4649472216689902, + "acc_stderr": 0.004977504446608999, + "acc_norm": 0.6183031268671579, + "acc_norm_stderr": 0.004848099661619672 + }, + "rte": { + "acc": 0.5234657039711191, + "acc_stderr": 0.03006330041190266 + }, + "winogrande": { + "acc": 0.5974743488555643, + "acc_stderr": 0.013782866831703044 + }, + "storycloze_2016": { + "acc": 0.7103153393907001, + "acc_stderr": 0.010489808091946617 + }, + "boolq": { + "acc": 0.6168195718654435, + "acc_stderr": 0.008503021391450791 + }, + "arc_easy": { + "acc": 0.6182659932659933, + "acc_stderr": 0.009968648851839668, + "acc_norm": 0.5963804713804713, + "acc_norm_stderr": 0.010067368960348226 + }, + "arc_challenge": { + "acc": 0.295221843003413, + "acc_stderr": 0.013329750293382316, + "acc_norm": 0.2986348122866894, + "acc_norm_stderr": 0.013374078615068744 + }, + "sciq": { + "acc": 0.917, + "acc_stderr": 0.008728527206074794, + "acc_norm": 0.891, + "acc_norm_stderr": 0.009859828407037188 + }, + "piqa": { + "acc": 0.7584330794341676, + "acc_stderr": 0.009986718001804467, + "acc_norm": 0.7698585418933623, + "acc_norm_stderr": 0.009820832826839803 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_2_lm-eval_global_step80108_2023-02-24-23-57-50_2shots_backup.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_2_lm-eval_global_step80108_2023-02-24-23-57-50_2shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..ab6c14d5bf3ae85028b61141005d2f2634890ff1 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_2_lm-eval_global_step80108_2023-02-24-23-57-50_2shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.332, + "acc_stderr": 0.014899597242811476 + }, + "anli_r2": { + "acc": 0.34, + "acc_stderr": 0.014987482264363937 + }, + "anli_r3": { + "acc": 0.3233333333333333, + "acc_stderr": 0.01350837286730022 + }, + "cb": { + "acc": 0.35714285714285715, + "acc_stderr": 0.06460957383809221, + "f1": 0.2989672364672365 + }, + "copa": { + "acc": 0.8, + "acc_stderr": 0.04020151261036845 + }, + "hellaswag": { + "acc": 0.4649472216689902, + "acc_stderr": 0.004977504446608999, + "acc_norm": 0.6183031268671579, + "acc_norm_stderr": 0.004848099661619672 + }, + "rte": { + "acc": 0.5234657039711191, + "acc_stderr": 0.03006330041190266 + }, + "winogrande": { + "acc": 0.5974743488555643, + "acc_stderr": 0.013782866831703044 + }, + "storycloze_2016": { + "acc": 0.7103153393907001, + "acc_stderr": 0.010489808091946617 + }, + "boolq": { + "acc": 0.6168195718654435, + "acc_stderr": 0.008503021391450791 + }, + "arc_easy": { + "acc": 0.6182659932659933, + "acc_stderr": 0.009968648851839668, + "acc_norm": 0.5963804713804713, + "acc_norm_stderr": 0.010067368960348226 + }, + "arc_challenge": { + "acc": 0.295221843003413, + "acc_stderr": 0.013329750293382316, + "acc_norm": 0.2986348122866894, + "acc_norm_stderr": 0.013374078615068744 + }, + "sciq": { + "acc": 0.917, + "acc_stderr": 0.008728527206074794, + "acc_norm": 0.891, + "acc_norm_stderr": 0.009859828407037188 + }, + "piqa": { + "acc": 0.7584330794341676, + "acc_stderr": 0.009986718001804467, + "acc_norm": 0.7698585418933623, + "acc_norm_stderr": 0.009820832826839803 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_3.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_3.json new file mode 100644 index 0000000000000000000000000000000000000000..efe45f149b86420a680fc18b5137af01ec77d8b2 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_3.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.324, + "acc_stderr": 0.014806864733738859 + }, + "anli_r2": { + "acc": 0.331, + "acc_stderr": 0.014888272588203933 + }, + "anli_r3": { + "acc": 0.32083333333333336, + "acc_stderr": 0.013480882752851553 + }, + "cb": { + "acc": 0.375, + "acc_stderr": 0.06527912098338669, + "f1": 0.34034722536464695 + }, + "copa": { + "acc": 0.8, + "acc_stderr": 0.040201512610368445 + }, + "hellaswag": { + "acc": 0.46863174666401114, + "acc_stderr": 0.004979952166595543, + "acc_norm": 0.6194981079466242, + "acc_norm_stderr": 0.00484518003427162 + }, + "rte": { + "acc": 0.5451263537906137, + "acc_stderr": 0.02997363649541526 + }, + "winogrande": { + "acc": 0.5872138910812944, + "acc_stderr": 0.013837060648682089 + }, + "storycloze_2016": { + "acc": 0.7129877071084981, + "acc_stderr": 0.010460934115933265 + }, + "boolq": { + "acc": 0.6097859327217126, + "acc_stderr": 0.008531643526263245 + }, + "arc_easy": { + "acc": 0.6241582491582491, + "acc_stderr": 0.00993843637317063, + "acc_norm": 0.5997474747474747, + "acc_norm_stderr": 0.010053550119896133 + }, + "arc_challenge": { + "acc": 0.30716723549488056, + "acc_stderr": 0.013481034054980945, + "acc_norm": 0.30802047781569963, + "acc_norm_stderr": 0.013491429517292038 + }, + "sciq": { + "acc": 0.914, + "acc_stderr": 0.008870325962594766, + "acc_norm": 0.894, + "acc_norm_stderr": 0.009739551265785138 + }, + "piqa": { + "acc": 0.7589771490750816, + "acc_stderr": 0.009979042717267314, + "acc_norm": 0.7595212187159956, + "acc_norm_stderr": 0.009971345364651071 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_3_lm-eval_global_step80108_2023-02-24-23-57-50_3shots_backup.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_3_lm-eval_global_step80108_2023-02-24-23-57-50_3shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..efe45f149b86420a680fc18b5137af01ec77d8b2 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_3_lm-eval_global_step80108_2023-02-24-23-57-50_3shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.324, + "acc_stderr": 0.014806864733738859 + }, + "anli_r2": { + "acc": 0.331, + "acc_stderr": 0.014888272588203933 + }, + "anli_r3": { + "acc": 0.32083333333333336, + "acc_stderr": 0.013480882752851553 + }, + "cb": { + "acc": 0.375, + "acc_stderr": 0.06527912098338669, + "f1": 0.34034722536464695 + }, + "copa": { + "acc": 0.8, + "acc_stderr": 0.040201512610368445 + }, + "hellaswag": { + "acc": 0.46863174666401114, + "acc_stderr": 0.004979952166595543, + "acc_norm": 0.6194981079466242, + "acc_norm_stderr": 0.00484518003427162 + }, + "rte": { + "acc": 0.5451263537906137, + "acc_stderr": 0.02997363649541526 + }, + "winogrande": { + "acc": 0.5872138910812944, + "acc_stderr": 0.013837060648682089 + }, + "storycloze_2016": { + "acc": 0.7129877071084981, + "acc_stderr": 0.010460934115933265 + }, + "boolq": { + "acc": 0.6097859327217126, + "acc_stderr": 0.008531643526263245 + }, + "arc_easy": { + "acc": 0.6241582491582491, + "acc_stderr": 0.00993843637317063, + "acc_norm": 0.5997474747474747, + "acc_norm_stderr": 0.010053550119896133 + }, + "arc_challenge": { + "acc": 0.30716723549488056, + "acc_stderr": 0.013481034054980945, + "acc_norm": 0.30802047781569963, + "acc_norm_stderr": 0.013491429517292038 + }, + "sciq": { + "acc": 0.914, + "acc_stderr": 0.008870325962594766, + "acc_norm": 0.894, + "acc_norm_stderr": 0.009739551265785138 + }, + "piqa": { + "acc": 0.7589771490750816, + "acc_stderr": 0.009979042717267314, + "acc_norm": 0.7595212187159956, + "acc_norm_stderr": 0.009971345364651071 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_4.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_4.json new file mode 100644 index 0000000000000000000000000000000000000000..3dea9a2ae8b3ce9e4621fedbcf026ac258ad8bba --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_4.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.336, + "acc_stderr": 0.014944140233795023 + }, + "anli_r2": { + "acc": 0.32, + "acc_stderr": 0.014758652303574876 + }, + "anli_r3": { + "acc": 0.3491666666666667, + "acc_stderr": 0.013767075395077249 + }, + "cb": { + "acc": 0.4642857142857143, + "acc_stderr": 0.0672477765493766, + "f1": 0.4400465860102907 + }, + "copa": { + "acc": 0.81, + "acc_stderr": 0.03942772444036622 + }, + "hellaswag": { + "acc": 0.46873132842063336, + "acc_stderr": 0.004980014536539821, + "acc_norm": 0.6197968532164907, + "acc_norm_stderr": 0.004844445265582643 + }, + "rte": { + "acc": 0.555956678700361, + "acc_stderr": 0.029907396333795983 + }, + "winogrande": { + "acc": 0.579321231254933, + "acc_stderr": 0.013874526372008315 + }, + "storycloze_2016": { + "acc": 0.7145911277391769, + "acc_stderr": 0.010443395884062118 + }, + "boolq": { + "acc": 0.6165137614678899, + "acc_stderr": 0.008504304838837023 + }, + "arc_easy": { + "acc": 0.6287878787878788, + "acc_stderr": 0.00991359900184574, + "acc_norm": 0.6031144781144782, + "acc_norm_stderr": 0.010039236800583199 + }, + "arc_challenge": { + "acc": 0.29692832764505117, + "acc_stderr": 0.013352025976725222, + "acc_norm": 0.310580204778157, + "acc_norm_stderr": 0.013522292098053057 + }, + "sciq": { + "acc": 0.908, + "acc_stderr": 0.009144376393151105, + "acc_norm": 0.905, + "acc_norm_stderr": 0.009276910103103324 + }, + "piqa": { + "acc": 0.7551686615886833, + "acc_stderr": 0.010032309105568795, + "acc_norm": 0.7622415669205659, + "acc_norm_stderr": 0.009932525779525489 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_4_lm-eval_global_step80108_2023-02-24-23-57-43_4shots_backup.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_4_lm-eval_global_step80108_2023-02-24-23-57-43_4shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..3dea9a2ae8b3ce9e4621fedbcf026ac258ad8bba --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_4_lm-eval_global_step80108_2023-02-24-23-57-43_4shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.336, + "acc_stderr": 0.014944140233795023 + }, + "anli_r2": { + "acc": 0.32, + "acc_stderr": 0.014758652303574876 + }, + "anli_r3": { + "acc": 0.3491666666666667, + "acc_stderr": 0.013767075395077249 + }, + "cb": { + "acc": 0.4642857142857143, + "acc_stderr": 0.0672477765493766, + "f1": 0.4400465860102907 + }, + "copa": { + "acc": 0.81, + "acc_stderr": 0.03942772444036622 + }, + "hellaswag": { + "acc": 0.46873132842063336, + "acc_stderr": 0.004980014536539821, + "acc_norm": 0.6197968532164907, + "acc_norm_stderr": 0.004844445265582643 + }, + "rte": { + "acc": 0.555956678700361, + "acc_stderr": 0.029907396333795983 + }, + "winogrande": { + "acc": 0.579321231254933, + "acc_stderr": 0.013874526372008315 + }, + "storycloze_2016": { + "acc": 0.7145911277391769, + "acc_stderr": 0.010443395884062118 + }, + "boolq": { + "acc": 0.6165137614678899, + "acc_stderr": 0.008504304838837023 + }, + "arc_easy": { + "acc": 0.6287878787878788, + "acc_stderr": 0.00991359900184574, + "acc_norm": 0.6031144781144782, + "acc_norm_stderr": 0.010039236800583199 + }, + "arc_challenge": { + "acc": 0.29692832764505117, + "acc_stderr": 0.013352025976725222, + "acc_norm": 0.310580204778157, + "acc_norm_stderr": 0.013522292098053057 + }, + "sciq": { + "acc": 0.908, + "acc_stderr": 0.009144376393151105, + "acc_norm": 0.905, + "acc_norm_stderr": 0.009276910103103324 + }, + "piqa": { + "acc": 0.7551686615886833, + "acc_stderr": 0.010032309105568795, + "acc_norm": 0.7622415669205659, + "acc_norm_stderr": 0.009932525779525489 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_5.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_5.json new file mode 100644 index 0000000000000000000000000000000000000000..64b0f8301c8c461b66852fd02cb72f95fb2b5744 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_5.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.329, + "acc_stderr": 0.01486539538592836 + }, + "anli_r2": { + "acc": 0.33, + "acc_stderr": 0.014876872027456736 + }, + "anli_r3": { + "acc": 0.33416666666666667, + "acc_stderr": 0.013622434813136778 + }, + "cb": { + "acc": 0.3392857142857143, + "acc_stderr": 0.06384226561930825, + "f1": 0.3130523153057618 + }, + "copa": { + "acc": 0.78, + "acc_stderr": 0.04163331998932261 + }, + "hellaswag": { + "acc": 0.4673371838279227, + "acc_stderr": 0.004979123236507975, + "acc_norm": 0.6237801234813782, + "acc_norm_stderr": 0.0048344619979448795 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.030052303463143706 + }, + "winogrande": { + "acc": 0.584846093133386, + "acc_stderr": 0.013848684086658587 + }, + "storycloze_2016": { + "acc": 0.7183324425440941, + "acc_stderr": 0.010401844358587665 + }, + "boolq": { + "acc": 0.6159021406727829, + "acc_stderr": 0.008506861063860251 + }, + "arc_easy": { + "acc": 0.6296296296296297, + "acc_stderr": 0.009908978578665758, + "acc_norm": 0.6119528619528619, + "acc_norm_stderr": 0.009999295905750669 + }, + "arc_challenge": { + "acc": 0.2977815699658703, + "acc_stderr": 0.013363080107244487, + "acc_norm": 0.31399317406143346, + "acc_norm_stderr": 0.013562691224726295 + }, + "sciq": { + "acc": 0.918, + "acc_stderr": 0.008680515615523727, + "acc_norm": 0.912, + "acc_norm_stderr": 0.008963053962592076 + }, + "piqa": { + "acc": 0.7486398258977149, + "acc_stderr": 0.01012115601681926, + "acc_norm": 0.7611534276387377, + "acc_norm_stderr": 0.009948120385337485 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_5_lm-eval_global_step80108_2023-02-25-00-00-35_5shots_backup.json b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_5_lm-eval_global_step80108_2023-02-25-00-00-35_5shots_backup.json new file mode 100644 index 0000000000000000000000000000000000000000..64b0f8301c8c461b66852fd02cb72f95fb2b5744 --- /dev/null +++ b/4b284b17bc4seed3/evaluation/rankeval/4b284b17bc4seed3_5_lm-eval_global_step80108_2023-02-25-00-00-35_5shots_backup.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.329, + "acc_stderr": 0.01486539538592836 + }, + "anli_r2": { + "acc": 0.33, + "acc_stderr": 0.014876872027456736 + }, + "anli_r3": { + "acc": 0.33416666666666667, + "acc_stderr": 0.013622434813136778 + }, + "cb": { + "acc": 0.3392857142857143, + "acc_stderr": 0.06384226561930825, + "f1": 0.3130523153057618 + }, + "copa": { + "acc": 0.78, + "acc_stderr": 0.04163331998932261 + }, + "hellaswag": { + "acc": 0.4673371838279227, + "acc_stderr": 0.004979123236507975, + "acc_norm": 0.6237801234813782, + "acc_norm_stderr": 0.0048344619979448795 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.030052303463143706 + }, + "winogrande": { + "acc": 0.584846093133386, + "acc_stderr": 0.013848684086658587 + }, + "storycloze_2016": { + "acc": 0.7183324425440941, + "acc_stderr": 0.010401844358587665 + }, + "boolq": { + "acc": 0.6159021406727829, + "acc_stderr": 0.008506861063860251 + }, + "arc_easy": { + "acc": 0.6296296296296297, + "acc_stderr": 0.009908978578665758, + "acc_norm": 0.6119528619528619, + "acc_norm_stderr": 0.009999295905750669 + }, + "arc_challenge": { + "acc": 0.2977815699658703, + "acc_stderr": 0.013363080107244487, + "acc_norm": 0.31399317406143346, + "acc_norm_stderr": 0.013562691224726295 + }, + "sciq": { + "acc": 0.918, + "acc_stderr": 0.008680515615523727, + "acc_norm": 0.912, + "acc_norm_stderr": 0.008963053962592076 + }, + "piqa": { + "acc": 0.7486398258977149, + "acc_stderr": 0.01012115601681926, + "acc_norm": 0.7611534276387377, + "acc_norm_stderr": 0.009948120385337485 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_2.json b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_2.json index bf3f16c097756a98361e567dd710802f07925c4d..2746e8034ab12b710df73a97bcfc7d5ce2bb1c3e 100644 --- a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_2.json +++ b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_2.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.7188669160876536, "acc_stderr": 0.010395836091628113 + }, + "boolq": { + "acc": 0.636697247706422, + "acc_stderr": 0.008411885836787163 + }, + "arc_easy": { + "acc": 0.6254208754208754, + "acc_stderr": 0.00993175882041061, + "acc_norm": 0.5993265993265994, + "acc_norm_stderr": 0.010055304474255585 + }, + "arc_challenge": { + "acc": 0.30716723549488056, + "acc_stderr": 0.013481034054980945, + "acc_norm": 0.33276450511945393, + "acc_norm_stderr": 0.013769863046192314 + }, + "sciq": { + "acc": 0.904, + "acc_stderr": 0.009320454434783222, + "acc_norm": 0.893, + "acc_norm_stderr": 0.009779910359847165 + }, + "piqa": { + "acc": 0.749727965179543, + "acc_stderr": 0.010106561880089786, + "acc_norm": 0.76550598476605, + "acc_norm_stderr": 0.00988520314324054 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json index bf3f16c097756a98361e567dd710802f07925c4d..2746e8034ab12b710df73a97bcfc7d5ce2bb1c3e 100644 --- a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json +++ b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.7188669160876536, "acc_stderr": 0.010395836091628113 + }, + "boolq": { + "acc": 0.636697247706422, + "acc_stderr": 0.008411885836787163 + }, + "arc_easy": { + "acc": 0.6254208754208754, + "acc_stderr": 0.00993175882041061, + "acc_norm": 0.5993265993265994, + "acc_norm_stderr": 0.010055304474255585 + }, + "arc_challenge": { + "acc": 0.30716723549488056, + "acc_stderr": 0.013481034054980945, + "acc_norm": 0.33276450511945393, + "acc_norm_stderr": 0.013769863046192314 + }, + "sciq": { + "acc": 0.904, + "acc_stderr": 0.009320454434783222, + "acc_norm": 0.893, + "acc_norm_stderr": 0.009779910359847165 + }, + "piqa": { + "acc": 0.749727965179543, + "acc_stderr": 0.010106561880089786, + "acc_norm": 0.76550598476605, + "acc_norm_stderr": 0.00988520314324054 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_3.json b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_3.json index e2471878a1bb9e44645e0a770c0f1ed07b8ec1f9..1708dd012c29c1e30d9c22890a5587ac54ac9d2e 100644 --- a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_3.json +++ b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_3.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4761999601672974, + "acc_stderr": 0.004984125363319067, + "acc_norm": 0.6349332802230632, + "acc_norm_stderr": 0.004804649197163698 + }, + "rte": { + "acc": 0.5306859205776173, + "acc_stderr": 0.030039730592197812 + }, + "winogrande": { + "acc": 0.5872138910812944, + "acc_stderr": 0.013837060648682094 + }, + "storycloze_2016": { + "acc": 0.7183324425440941, + "acc_stderr": 0.010401844358587662 + }, + "boolq": { + "acc": 0.6238532110091743, + "acc_stderr": 0.008472516562330725 + }, + "arc_easy": { + "acc": 0.627104377104377, + "acc_stderr": 0.009922743197129253, + "acc_norm": 0.6081649831649831, + "acc_norm_stderr": 0.010016835016834974 + }, + "arc_challenge": { + "acc": 0.30631399317406144, + "acc_stderr": 0.013470584417276513, + "acc_norm": 0.32593856655290104, + "acc_norm_stderr": 0.013697432466693246 + }, + "sciq": { + "acc": 0.909, + "acc_stderr": 0.009099549538400245, + "acc_norm": 0.898, + "acc_norm_stderr": 0.009575368801653886 + }, + "piqa": { + "acc": 0.7568008705114254, + "acc_stderr": 0.010009611953858917, + "acc_norm": 0.7665941240478781, + "acc_norm_stderr": 0.009869247889520994 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json index e2471878a1bb9e44645e0a770c0f1ed07b8ec1f9..1708dd012c29c1e30d9c22890a5587ac54ac9d2e 100644 --- a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json +++ b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4761999601672974, + "acc_stderr": 0.004984125363319067, + "acc_norm": 0.6349332802230632, + "acc_norm_stderr": 0.004804649197163698 + }, + "rte": { + "acc": 0.5306859205776173, + "acc_stderr": 0.030039730592197812 + }, + "winogrande": { + "acc": 0.5872138910812944, + "acc_stderr": 0.013837060648682094 + }, + "storycloze_2016": { + "acc": 0.7183324425440941, + "acc_stderr": 0.010401844358587662 + }, + "boolq": { + "acc": 0.6238532110091743, + "acc_stderr": 0.008472516562330725 + }, + "arc_easy": { + "acc": 0.627104377104377, + "acc_stderr": 0.009922743197129253, + "acc_norm": 0.6081649831649831, + "acc_norm_stderr": 0.010016835016834974 + }, + "arc_challenge": { + "acc": 0.30631399317406144, + "acc_stderr": 0.013470584417276513, + "acc_norm": 0.32593856655290104, + "acc_norm_stderr": 0.013697432466693246 + }, + "sciq": { + "acc": 0.909, + "acc_stderr": 0.009099549538400245, + "acc_norm": 0.898, + "acc_norm_stderr": 0.009575368801653886 + }, + "piqa": { + "acc": 0.7568008705114254, + "acc_stderr": 0.010009611953858917, + "acc_norm": 0.7665941240478781, + "acc_norm_stderr": 0.009869247889520994 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_4.json b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_4.json index 6c4e157c1f6e594b7f742018d9ef6ceeaae1cff4..e5c60eedda79fdb2fc8087612d8d2dde1c68d2e4 100644 --- a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_4.json +++ b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_4.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 + }, + "hellaswag": { + "acc": 0.47610037841067515, + "acc_stderr": 0.004984077906216097, + "acc_norm": 0.6333399721171081, + "acc_norm_stderr": 0.004809077205343497 + }, + "rte": { + "acc": 0.49097472924187724, + "acc_stderr": 0.030091559826331334 + }, + "winogrande": { + "acc": 0.5895816890292028, + "acc_stderr": 0.013825107120035866 + }, + "storycloze_2016": { + "acc": 0.721004810261892, + "acc_stderr": 0.010371620932652793 + }, + "boolq": { + "acc": 0.6321100917431193, + "acc_stderr": 0.008434276591093028 + }, + "arc_easy": { + "acc": 0.6435185185185185, + "acc_stderr": 0.009828046544504422, + "acc_norm": 0.6165824915824916, + "acc_norm_stderr": 0.009976995068264724 + }, + "arc_challenge": { + "acc": 0.3054607508532423, + "acc_stderr": 0.013460080478002501, + "acc_norm": 0.33361774744027306, + "acc_norm_stderr": 0.013778687054176546 + }, + "sciq": { + "acc": 0.916, + "acc_stderr": 0.008776162089491123, + "acc_norm": 0.905, + "acc_norm_stderr": 0.0092769101031033 + }, + "piqa": { + "acc": 0.749183895538629, + "acc_stderr": 0.010113869547069044, + "acc_norm": 0.7589771490750816, + "acc_norm_stderr": 0.009979042717267312 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json index 6c4e157c1f6e594b7f742018d9ef6ceeaae1cff4..e5c60eedda79fdb2fc8087612d8d2dde1c68d2e4 100644 --- a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json +++ b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 + }, + "hellaswag": { + "acc": 0.47610037841067515, + "acc_stderr": 0.004984077906216097, + "acc_norm": 0.6333399721171081, + "acc_norm_stderr": 0.004809077205343497 + }, + "rte": { + "acc": 0.49097472924187724, + "acc_stderr": 0.030091559826331334 + }, + "winogrande": { + "acc": 0.5895816890292028, + "acc_stderr": 0.013825107120035866 + }, + "storycloze_2016": { + "acc": 0.721004810261892, + "acc_stderr": 0.010371620932652793 + }, + "boolq": { + "acc": 0.6321100917431193, + "acc_stderr": 0.008434276591093028 + }, + "arc_easy": { + "acc": 0.6435185185185185, + "acc_stderr": 0.009828046544504422, + "acc_norm": 0.6165824915824916, + "acc_norm_stderr": 0.009976995068264724 + }, + "arc_challenge": { + "acc": 0.3054607508532423, + "acc_stderr": 0.013460080478002501, + "acc_norm": 0.33361774744027306, + "acc_norm_stderr": 0.013778687054176546 + }, + "sciq": { + "acc": 0.916, + "acc_stderr": 0.008776162089491123, + "acc_norm": 0.905, + "acc_norm_stderr": 0.0092769101031033 + }, + "piqa": { + "acc": 0.749183895538629, + "acc_stderr": 0.010113869547069044, + "acc_norm": 0.7589771490750816, + "acc_norm_stderr": 0.009979042717267312 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_5.json b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_5.json index c3bfebf7d5a03f62ed5945048b98bdb47350a7ac..c8b42e7cc1c246782629160b48d2556cc5d71e54 100644 --- a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_5.json +++ b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_5.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4753037243576977, + "acc_stderr": 0.0049836910991109115, + "acc_norm": 0.6382194781915953, + "acc_norm_stderr": 0.004795337009118188 + }, + "rte": { + "acc": 0.5487364620938628, + "acc_stderr": 0.029953149241808946 + }, + "winogrande": { + "acc": 0.5974743488555643, + "acc_stderr": 0.013782866831703048 + }, + "storycloze_2016": { + "acc": 0.7161945483698557, + "acc_stderr": 0.010425696279730922 + }, + "boolq": { + "acc": 0.6256880733944954, + "acc_stderr": 0.008464246656443233 + }, + "arc_easy": { + "acc": 0.6414141414141414, + "acc_stderr": 0.009840882301225297, + "acc_norm": 0.6136363636363636, + "acc_norm_stderr": 0.009991296778159619 + }, + "arc_challenge": { + "acc": 0.3148464163822526, + "acc_stderr": 0.01357265770308495, + "acc_norm": 0.3225255972696246, + "acc_norm_stderr": 0.013659980894277366 + }, + "sciq": { + "acc": 0.923, + "acc_stderr": 0.008434580140240643, + "acc_norm": 0.915, + "acc_norm_stderr": 0.008823426366942314 + }, + "piqa": { + "acc": 0.7584330794341676, + "acc_stderr": 0.009986718001804467, + "acc_norm": 0.7633297062023939, + "acc_norm_stderr": 0.009916841655042809 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_5_lm-eval_global_step80108_2023-02-24-21-45-59_5shots_backup.json b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_5_lm-eval_global_step80108_2023-02-24-21-45-59_5shots_backup.json index c3bfebf7d5a03f62ed5945048b98bdb47350a7ac..c8b42e7cc1c246782629160b48d2556cc5d71e54 100644 --- a/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_5_lm-eval_global_step80108_2023-02-24-21-45-59_5shots_backup.json +++ b/4b284b21bc4seed2/evaluation/rankeval/4b284b21bc4seed2_5_lm-eval_global_step80108_2023-02-24-21-45-59_5shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 + }, + "hellaswag": { + "acc": 0.4753037243576977, + "acc_stderr": 0.0049836910991109115, + "acc_norm": 0.6382194781915953, + "acc_norm_stderr": 0.004795337009118188 + }, + "rte": { + "acc": 0.5487364620938628, + "acc_stderr": 0.029953149241808946 + }, + "winogrande": { + "acc": 0.5974743488555643, + "acc_stderr": 0.013782866831703048 + }, + "storycloze_2016": { + "acc": 0.7161945483698557, + "acc_stderr": 0.010425696279730922 + }, + "boolq": { + "acc": 0.6256880733944954, + "acc_stderr": 0.008464246656443233 + }, + "arc_easy": { + "acc": 0.6414141414141414, + "acc_stderr": 0.009840882301225297, + "acc_norm": 0.6136363636363636, + "acc_norm_stderr": 0.009991296778159619 + }, + "arc_challenge": { + "acc": 0.3148464163822526, + "acc_stderr": 0.01357265770308495, + "acc_norm": 0.3225255972696246, + "acc_norm_stderr": 0.013659980894277366 + }, + "sciq": { + "acc": 0.923, + "acc_stderr": 0.008434580140240643, + "acc_norm": 0.915, + "acc_norm_stderr": 0.008823426366942314 + }, + "piqa": { + "acc": 0.7584330794341676, + "acc_stderr": 0.009986718001804467, + "acc_norm": 0.7633297062023939, + "acc_norm_stderr": 0.009916841655042809 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_2.json b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_2.json index 6ee2741ef9e3428033accba20cef82b2ebdb0334..24cac45800d9dad2e42d638a0c50252bdd1b4dae 100644 --- a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_2.json +++ b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_2.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.6755745590593266, "acc_stderr": 0.01082613134499089 + }, + "boolq": { + "acc": 0.6061162079510704, + "acc_stderr": 0.008545835792614982 + }, + "arc_easy": { + "acc": 0.5555555555555556, + "acc_stderr": 0.01019625483869168, + "acc_norm": 0.5366161616161617, + "acc_norm_stderr": 0.01023223506393303 + }, + "arc_challenge": { + "acc": 0.2568259385665529, + "acc_stderr": 0.0127669237941168, + "acc_norm": 0.30119453924914674, + "acc_norm_stderr": 0.01340674176784762 + }, + "sciq": { + "acc": 0.852, + "acc_stderr": 0.011234866364235239, + "acc_norm": 0.834, + "acc_norm_stderr": 0.011772110370812185 + }, + "piqa": { + "acc": 0.719804134929271, + "acc_stderr": 0.010478122015577082, + "acc_norm": 0.7181719260065288, + "acc_norm_stderr": 0.010496675231258159 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json index 6ee2741ef9e3428033accba20cef82b2ebdb0334..24cac45800d9dad2e42d638a0c50252bdd1b4dae 100644 --- a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json +++ b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.6755745590593266, "acc_stderr": 0.01082613134499089 + }, + "boolq": { + "acc": 0.6061162079510704, + "acc_stderr": 0.008545835792614982 + }, + "arc_easy": { + "acc": 0.5555555555555556, + "acc_stderr": 0.01019625483869168, + "acc_norm": 0.5366161616161617, + "acc_norm_stderr": 0.01023223506393303 + }, + "arc_challenge": { + "acc": 0.2568259385665529, + "acc_stderr": 0.0127669237941168, + "acc_norm": 0.30119453924914674, + "acc_norm_stderr": 0.01340674176784762 + }, + "sciq": { + "acc": 0.852, + "acc_stderr": 0.011234866364235239, + "acc_norm": 0.834, + "acc_norm_stderr": 0.011772110370812185 + }, + "piqa": { + "acc": 0.719804134929271, + "acc_stderr": 0.010478122015577082, + "acc_norm": 0.7181719260065288, + "acc_norm_stderr": 0.010496675231258159 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_3.json b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_3.json index f9700ace52e74ebeeb0ceb6ca363549e513b94ac..09970f7ccdfd2198092cb89473e193458ab74faf 100644 --- a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_3.json +++ b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_3.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816506 + }, + "hellaswag": { + "acc": 0.46036646086436966, + "acc_stderr": 0.004974080638364265, + "acc_norm": 0.6097390957976498, + "acc_norm_stderr": 0.004868117598481941 + }, + "rte": { + "acc": 0.5126353790613718, + "acc_stderr": 0.030086851767188564 + }, + "winogrande": { + "acc": 0.5627466456195738, + "acc_stderr": 0.013941393310695924 + }, + "storycloze_2016": { + "acc": 0.692143238909674, + "acc_stderr": 0.010674598158758186 + }, + "boolq": { + "acc": 0.617737003058104, + "acc_stderr": 0.008499149690449273 + }, + "arc_easy": { + "acc": 0.5753367003367004, + "acc_stderr": 0.010142653687480416, + "acc_norm": 0.5513468013468014, + "acc_norm_stderr": 0.010205540414612871 + }, + "arc_challenge": { + "acc": 0.2815699658703072, + "acc_stderr": 0.013143376735009022, + "acc_norm": 0.3054607508532423, + "acc_norm_stderr": 0.013460080478002498 + }, + "sciq": { + "acc": 0.848, + "acc_stderr": 0.01135891830347528, + "acc_norm": 0.845, + "acc_norm_stderr": 0.011450157470799475 + }, + "piqa": { + "acc": 0.7377584330794341, + "acc_stderr": 0.01026250256517245, + "acc_norm": 0.7404787812840044, + "acc_norm_stderr": 0.010227939888173923 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json index f9700ace52e74ebeeb0ceb6ca363549e513b94ac..09970f7ccdfd2198092cb89473e193458ab74faf 100644 --- a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json +++ b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816506 + }, + "hellaswag": { + "acc": 0.46036646086436966, + "acc_stderr": 0.004974080638364265, + "acc_norm": 0.6097390957976498, + "acc_norm_stderr": 0.004868117598481941 + }, + "rte": { + "acc": 0.5126353790613718, + "acc_stderr": 0.030086851767188564 + }, + "winogrande": { + "acc": 0.5627466456195738, + "acc_stderr": 0.013941393310695924 + }, + "storycloze_2016": { + "acc": 0.692143238909674, + "acc_stderr": 0.010674598158758186 + }, + "boolq": { + "acc": 0.617737003058104, + "acc_stderr": 0.008499149690449273 + }, + "arc_easy": { + "acc": 0.5753367003367004, + "acc_stderr": 0.010142653687480416, + "acc_norm": 0.5513468013468014, + "acc_norm_stderr": 0.010205540414612871 + }, + "arc_challenge": { + "acc": 0.2815699658703072, + "acc_stderr": 0.013143376735009022, + "acc_norm": 0.3054607508532423, + "acc_norm_stderr": 0.013460080478002498 + }, + "sciq": { + "acc": 0.848, + "acc_stderr": 0.01135891830347528, + "acc_norm": 0.845, + "acc_norm_stderr": 0.011450157470799475 + }, + "piqa": { + "acc": 0.7377584330794341, + "acc_stderr": 0.01026250256517245, + "acc_norm": 0.7404787812840044, + "acc_norm_stderr": 0.010227939888173923 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_4.json b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_4.json index 92a340d019f24cbe57a3cde76af952405d7631cd..09a3f0a6baaa07a229486aff64ab81b8ccd42e18 100644 --- a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_4.json +++ b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_4.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 + }, + "hellaswag": { + "acc": 0.46863174666401114, + "acc_stderr": 0.0049799521665955405, + "acc_norm": 0.6181039633539136, + "acc_norm_stderr": 0.004848583243606704 + }, + "rte": { + "acc": 0.5126353790613718, + "acc_stderr": 0.030086851767188564 + }, + "winogrande": { + "acc": 0.5643251775848461, + "acc_stderr": 0.013935709739615715 + }, + "storycloze_2016": { + "acc": 0.6958845537145911, + "acc_stderr": 0.010638172655194789 + }, + "boolq": { + "acc": 0.6100917431192661, + "acc_stderr": 0.00853043797286262 + }, + "arc_easy": { + "acc": 0.5984848484848485, + "acc_stderr": 0.010058790020755572, + "acc_norm": 0.571969696969697, + "acc_norm_stderr": 0.01015294331642626 + }, + "arc_challenge": { + "acc": 0.2815699658703072, + "acc_stderr": 0.01314337673500901, + "acc_norm": 0.3242320819112628, + "acc_norm_stderr": 0.01367881039951882 + }, + "sciq": { + "acc": 0.864, + "acc_stderr": 0.010845350230472995, + "acc_norm": 0.862, + "acc_norm_stderr": 0.01091215263250441 + }, + "piqa": { + "acc": 0.7393906420021763, + "acc_stderr": 0.010241826155811627, + "acc_norm": 0.7383025027203483, + "acc_norm_stderr": 0.010255630772708229 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json index 92a340d019f24cbe57a3cde76af952405d7631cd..09a3f0a6baaa07a229486aff64ab81b8ccd42e18 100644 --- a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json +++ b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 + }, + "hellaswag": { + "acc": 0.46863174666401114, + "acc_stderr": 0.0049799521665955405, + "acc_norm": 0.6181039633539136, + "acc_norm_stderr": 0.004848583243606704 + }, + "rte": { + "acc": 0.5126353790613718, + "acc_stderr": 0.030086851767188564 + }, + "winogrande": { + "acc": 0.5643251775848461, + "acc_stderr": 0.013935709739615715 + }, + "storycloze_2016": { + "acc": 0.6958845537145911, + "acc_stderr": 0.010638172655194789 + }, + "boolq": { + "acc": 0.6100917431192661, + "acc_stderr": 0.00853043797286262 + }, + "arc_easy": { + "acc": 0.5984848484848485, + "acc_stderr": 0.010058790020755572, + "acc_norm": 0.571969696969697, + "acc_norm_stderr": 0.01015294331642626 + }, + "arc_challenge": { + "acc": 0.2815699658703072, + "acc_stderr": 0.01314337673500901, + "acc_norm": 0.3242320819112628, + "acc_norm_stderr": 0.01367881039951882 + }, + "sciq": { + "acc": 0.864, + "acc_stderr": 0.010845350230472995, + "acc_norm": 0.862, + "acc_norm_stderr": 0.01091215263250441 + }, + "piqa": { + "acc": 0.7393906420021763, + "acc_stderr": 0.010241826155811627, + "acc_norm": 0.7383025027203483, + "acc_norm_stderr": 0.010255630772708229 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_5.json b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_5.json index feab211715346698e9b974d27036bac900dfe783..6383308da1c94c520916c8923e55170599f11915 100644 --- a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_5.json +++ b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_5.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 + }, + "hellaswag": { + "acc": 0.468034256124278, + "acc_stderr": 0.0049795737655758555, + "acc_norm": 0.6201951802429795, + "acc_norm_stderr": 0.004843462545943488 + }, + "rte": { + "acc": 0.5379061371841155, + "acc_stderr": 0.030009848912529113 + }, + "winogrande": { + "acc": 0.5824782951854776, + "acc_stderr": 0.013859978264440253 + }, + "storycloze_2016": { + "acc": 0.703901656867985, + "acc_stderr": 0.010557307688475116 + }, + "boolq": { + "acc": 0.6162079510703364, + "acc_stderr": 0.008505584729104967 + }, + "arc_easy": { + "acc": 0.6035353535353535, + "acc_stderr": 0.010037412763064526, + "acc_norm": 0.5782828282828283, + "acc_norm_stderr": 0.010133255284012327 + }, + "arc_challenge": { + "acc": 0.2815699658703072, + "acc_stderr": 0.013143376735009031, + "acc_norm": 0.3199658703071672, + "acc_norm_stderr": 0.013631345807016191 + }, + "sciq": { + "acc": 0.875, + "acc_stderr": 0.010463483381956722, + "acc_norm": 0.861, + "acc_norm_stderr": 0.010945263761042968 + }, + "piqa": { + "acc": 0.73449401523395, + "acc_stderr": 0.010303308653024429, + "acc_norm": 0.7459194776931447, + "acc_norm_stderr": 0.01015727199913505 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json index feab211715346698e9b974d27036bac900dfe783..6383308da1c94c520916c8923e55170599f11915 100644 --- a/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json +++ b/4b284b28bc4seed3/evaluation/rankeval/4b284b28bc4seed3_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 + }, + "hellaswag": { + "acc": 0.468034256124278, + "acc_stderr": 0.0049795737655758555, + "acc_norm": 0.6201951802429795, + "acc_norm_stderr": 0.004843462545943488 + }, + "rte": { + "acc": 0.5379061371841155, + "acc_stderr": 0.030009848912529113 + }, + "winogrande": { + "acc": 0.5824782951854776, + "acc_stderr": 0.013859978264440253 + }, + "storycloze_2016": { + "acc": 0.703901656867985, + "acc_stderr": 0.010557307688475116 + }, + "boolq": { + "acc": 0.6162079510703364, + "acc_stderr": 0.008505584729104967 + }, + "arc_easy": { + "acc": 0.6035353535353535, + "acc_stderr": 0.010037412763064526, + "acc_norm": 0.5782828282828283, + "acc_norm_stderr": 0.010133255284012327 + }, + "arc_challenge": { + "acc": 0.2815699658703072, + "acc_stderr": 0.013143376735009031, + "acc_norm": 0.3199658703071672, + "acc_norm_stderr": 0.013631345807016191 + }, + "sciq": { + "acc": 0.875, + "acc_stderr": 0.010463483381956722, + "acc_norm": 0.861, + "acc_norm_stderr": 0.010945263761042968 + }, + "piqa": { + "acc": 0.73449401523395, + "acc_stderr": 0.010303308653024429, + "acc_norm": 0.7459194776931447, + "acc_norm_stderr": 0.01015727199913505 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_2.json b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_2.json index aef66975ccf22959ede9c0068f62b6524cc97b0c..050ee91c296173fc8b82687a8422b9903bcee26d 100644 --- a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_2.json +++ b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_2.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.7156600748262961, "acc_stderr": 0.010431614128665244 + }, + "boolq": { + "acc": 0.6165137614678899, + "acc_stderr": 0.008504304838837027 + }, + "arc_easy": { + "acc": 0.6279461279461279, + "acc_stderr": 0.009918187193096471, + "acc_norm": 0.6069023569023569, + "acc_norm_stderr": 0.010022540618945315 + }, + "arc_challenge": { + "acc": 0.3003412969283277, + "acc_stderr": 0.013395909309957, + "acc_norm": 0.3319112627986348, + "acc_norm_stderr": 0.013760988200880536 + }, + "sciq": { + "acc": 0.911, + "acc_stderr": 0.009008893392651523, + "acc_norm": 0.891, + "acc_norm_stderr": 0.00985982840703719 + }, + "piqa": { + "acc": 0.7535364526659413, + "acc_stderr": 0.01005481078967182, + "acc_norm": 0.7633297062023939, + "acc_norm_stderr": 0.009916841655042809 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json index aef66975ccf22959ede9c0068f62b6524cc97b0c..050ee91c296173fc8b82687a8422b9903bcee26d 100644 --- a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json +++ b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json @@ -38,6 +38,34 @@ "storycloze_2016": { "acc": 0.7156600748262961, "acc_stderr": 0.010431614128665244 + }, + "boolq": { + "acc": 0.6165137614678899, + "acc_stderr": 0.008504304838837027 + }, + "arc_easy": { + "acc": 0.6279461279461279, + "acc_stderr": 0.009918187193096471, + "acc_norm": 0.6069023569023569, + "acc_norm_stderr": 0.010022540618945315 + }, + "arc_challenge": { + "acc": 0.3003412969283277, + "acc_stderr": 0.013395909309957, + "acc_norm": 0.3319112627986348, + "acc_norm_stderr": 0.013760988200880536 + }, + "sciq": { + "acc": 0.911, + "acc_stderr": 0.009008893392651523, + "acc_norm": 0.891, + "acc_norm_stderr": 0.00985982840703719 + }, + "piqa": { + "acc": 0.7535364526659413, + "acc_stderr": 0.01005481078967182, + "acc_norm": 0.7633297062023939, + "acc_norm_stderr": 0.009916841655042809 } }, "versions": { @@ -49,6 +77,11 @@ "hellaswag": 0, "rte": 0, "winogrande": 0, - "storycloze_2016": 0 + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_3.json b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_3.json index 6520ea671dccb6f07a3b2266e41871031aa48487..6ed579572798fc191e1081cee1c87c2a4dcdac31 100644 --- a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_3.json +++ b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_3.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.84, "acc_stderr": 0.03684529491774711 + }, + "hellaswag": { + "acc": 0.4788886675960964, + "acc_stderr": 0.004985331652408345, + "acc_norm": 0.6285600477992431, + "acc_norm_stderr": 0.004822022254886021 + }, + "rte": { + "acc": 0.48014440433212996, + "acc_stderr": 0.0300727231673172 + }, + "winogrande": { + "acc": 0.590370955011839, + "acc_stderr": 0.013821049109655465 + }, + "storycloze_2016": { + "acc": 0.7172634954569749, + "acc_stderr": 0.01041380648612127 + }, + "boolq": { + "acc": 0.6146788990825688, + "acc_stderr": 0.008511930879680645 + }, + "arc_easy": { + "acc": 0.6380471380471381, + "acc_stderr": 0.009860991466688486, + "acc_norm": 0.625, + "acc_norm_stderr": 0.009933992677987828 + }, + "arc_challenge": { + "acc": 0.29948805460750855, + "acc_stderr": 0.013385021637313565, + "acc_norm": 0.33276450511945393, + "acc_norm_stderr": 0.01376986304619231 + }, + "sciq": { + "acc": 0.916, + "acc_stderr": 0.008776162089491122, + "acc_norm": 0.9, + "acc_norm_stderr": 0.009491579957525049 + }, + "piqa": { + "acc": 0.7584330794341676, + "acc_stderr": 0.009986718001804463, + "acc_norm": 0.7562568008705114, + "acc_norm_stderr": 0.010017199471500609 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json index 6520ea671dccb6f07a3b2266e41871031aa48487..6ed579572798fc191e1081cee1c87c2a4dcdac31 100644 --- a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json +++ b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.84, "acc_stderr": 0.03684529491774711 + }, + "hellaswag": { + "acc": 0.4788886675960964, + "acc_stderr": 0.004985331652408345, + "acc_norm": 0.6285600477992431, + "acc_norm_stderr": 0.004822022254886021 + }, + "rte": { + "acc": 0.48014440433212996, + "acc_stderr": 0.0300727231673172 + }, + "winogrande": { + "acc": 0.590370955011839, + "acc_stderr": 0.013821049109655465 + }, + "storycloze_2016": { + "acc": 0.7172634954569749, + "acc_stderr": 0.01041380648612127 + }, + "boolq": { + "acc": 0.6146788990825688, + "acc_stderr": 0.008511930879680645 + }, + "arc_easy": { + "acc": 0.6380471380471381, + "acc_stderr": 0.009860991466688486, + "acc_norm": 0.625, + "acc_norm_stderr": 0.009933992677987828 + }, + "arc_challenge": { + "acc": 0.29948805460750855, + "acc_stderr": 0.013385021637313565, + "acc_norm": 0.33276450511945393, + "acc_norm_stderr": 0.01376986304619231 + }, + "sciq": { + "acc": 0.916, + "acc_stderr": 0.008776162089491122, + "acc_norm": 0.9, + "acc_norm_stderr": 0.009491579957525049 + }, + "piqa": { + "acc": 0.7584330794341676, + "acc_stderr": 0.009986718001804463, + "acc_norm": 0.7562568008705114, + "acc_norm_stderr": 0.010017199471500609 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_4.json b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_4.json index 90b0c3ad050950e9fc8e84889b07b4c9f28e7c69..1ed659ead93c21380463e58b56a5725340bdbbdd 100644 --- a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_4.json +++ b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_4.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.84, "acc_stderr": 0.0368452949177471 + }, + "hellaswag": { + "acc": 0.47470623381796456, + "acc_stderr": 0.004983392650570959, + "acc_norm": 0.6319458275243975, + "acc_norm_stderr": 0.004812905279066442 + }, + "rte": { + "acc": 0.47653429602888087, + "acc_stderr": 0.030063300411902652 + }, + "winogrande": { + "acc": 0.6108918705603789, + "acc_stderr": 0.013702520871485949 + }, + "storycloze_2016": { + "acc": 0.721004810261892, + "acc_stderr": 0.010371620932652795 + }, + "boolq": { + "acc": 0.6192660550458715, + "acc_stderr": 0.008492625561656215 + }, + "arc_easy": { + "acc": 0.6380471380471381, + "acc_stderr": 0.00986099146668847, + "acc_norm": 0.6216329966329966, + "acc_norm_stderr": 0.00995157568333195 + }, + "arc_challenge": { + "acc": 0.29948805460750855, + "acc_stderr": 0.013385021637313563, + "acc_norm": 0.3361774744027304, + "acc_norm_stderr": 0.013804855026205763 + }, + "sciq": { + "acc": 0.915, + "acc_stderr": 0.008823426366942323, + "acc_norm": 0.91, + "acc_norm_stderr": 0.009054390204866444 + }, + "piqa": { + "acc": 0.7529923830250272, + "acc_stderr": 0.010062268140772625, + "acc_norm": 0.7568008705114254, + "acc_norm_stderr": 0.010009611953858917 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json index 90b0c3ad050950e9fc8e84889b07b4c9f28e7c69..1ed659ead93c21380463e58b56a5725340bdbbdd 100644 --- a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json +++ b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.84, "acc_stderr": 0.0368452949177471 + }, + "hellaswag": { + "acc": 0.47470623381796456, + "acc_stderr": 0.004983392650570959, + "acc_norm": 0.6319458275243975, + "acc_norm_stderr": 0.004812905279066442 + }, + "rte": { + "acc": 0.47653429602888087, + "acc_stderr": 0.030063300411902652 + }, + "winogrande": { + "acc": 0.6108918705603789, + "acc_stderr": 0.013702520871485949 + }, + "storycloze_2016": { + "acc": 0.721004810261892, + "acc_stderr": 0.010371620932652795 + }, + "boolq": { + "acc": 0.6192660550458715, + "acc_stderr": 0.008492625561656215 + }, + "arc_easy": { + "acc": 0.6380471380471381, + "acc_stderr": 0.00986099146668847, + "acc_norm": 0.6216329966329966, + "acc_norm_stderr": 0.00995157568333195 + }, + "arc_challenge": { + "acc": 0.29948805460750855, + "acc_stderr": 0.013385021637313563, + "acc_norm": 0.3361774744027304, + "acc_norm_stderr": 0.013804855026205763 + }, + "sciq": { + "acc": 0.915, + "acc_stderr": 0.008823426366942323, + "acc_norm": 0.91, + "acc_norm_stderr": 0.009054390204866444 + }, + "piqa": { + "acc": 0.7529923830250272, + "acc_stderr": 0.010062268140772625, + "acc_norm": 0.7568008705114254, + "acc_norm_stderr": 0.010009611953858917 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_5.json b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_5.json index e7ed0dca6981b02a14f27cca3d7b29cf975501c5..1f1459c2cfb492dfda59c7b44d1e462772df3427 100644 --- a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_5.json +++ b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_5.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.82, "acc_stderr": 0.03861229196653697 + }, + "hellaswag": { + "acc": 0.4781915952997411, + "acc_stderr": 0.004985032806802436, + "acc_norm": 0.6330412268472416, + "acc_norm_stderr": 0.004809901151234833 + }, + "rte": { + "acc": 0.5379061371841155, + "acc_stderr": 0.030009848912529117 + }, + "winogrande": { + "acc": 0.5927387529597474, + "acc_stderr": 0.013808654122417845 + }, + "storycloze_2016": { + "acc": 0.7295563869588455, + "acc_stderr": 0.010271810373331022 + }, + "boolq": { + "acc": 0.6311926605504588, + "acc_stderr": 0.008438656079759072 + }, + "arc_easy": { + "acc": 0.6384680134680135, + "acc_stderr": 0.00985850654316206, + "acc_norm": 0.625, + "acc_norm_stderr": 0.009933992677987828 + }, + "arc_challenge": { + "acc": 0.29948805460750855, + "acc_stderr": 0.013385021637313565, + "acc_norm": 0.3267918088737201, + "acc_norm_stderr": 0.01370666597558734 + }, + "sciq": { + "acc": 0.913, + "acc_stderr": 0.008916866630745906, + "acc_norm": 0.908, + "acc_norm_stderr": 0.0091443763931511 + }, + "piqa": { + "acc": 0.7568008705114254, + "acc_stderr": 0.010009611953858917, + "acc_norm": 0.7589771490750816, + "acc_norm_stderr": 0.009979042717267315 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json index e7ed0dca6981b02a14f27cca3d7b29cf975501c5..1f1459c2cfb492dfda59c7b44d1e462772df3427 100644 --- a/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json +++ b/4b284b42bc4seed3/evaluation/rankeval/4b284b42bc4seed3_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.82, "acc_stderr": 0.03861229196653697 + }, + "hellaswag": { + "acc": 0.4781915952997411, + "acc_stderr": 0.004985032806802436, + "acc_norm": 0.6330412268472416, + "acc_norm_stderr": 0.004809901151234833 + }, + "rte": { + "acc": 0.5379061371841155, + "acc_stderr": 0.030009848912529117 + }, + "winogrande": { + "acc": 0.5927387529597474, + "acc_stderr": 0.013808654122417845 + }, + "storycloze_2016": { + "acc": 0.7295563869588455, + "acc_stderr": 0.010271810373331022 + }, + "boolq": { + "acc": 0.6311926605504588, + "acc_stderr": 0.008438656079759072 + }, + "arc_easy": { + "acc": 0.6384680134680135, + "acc_stderr": 0.00985850654316206, + "acc_norm": 0.625, + "acc_norm_stderr": 0.009933992677987828 + }, + "arc_challenge": { + "acc": 0.29948805460750855, + "acc_stderr": 0.013385021637313565, + "acc_norm": 0.3267918088737201, + "acc_norm_stderr": 0.01370666597558734 + }, + "sciq": { + "acc": 0.913, + "acc_stderr": 0.008916866630745906, + "acc_norm": 0.908, + "acc_norm_stderr": 0.0091443763931511 + }, + "piqa": { + "acc": 0.7568008705114254, + "acc_stderr": 0.010009611953858917, + "acc_norm": 0.7589771490750816, + "acc_norm_stderr": 0.009979042717267315 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_2.json b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_2.json index 7a46e0a1bc8214a19c12d5f85f9cd0cffbbf2947..94b3bb570177d9b9d6318464d032e4e6dcfbce4c 100644 --- a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_2.json +++ b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_2.json @@ -42,6 +42,30 @@ "boolq": { "acc": 0.6097859327217126, "acc_stderr": 0.00853164352626324 + }, + "arc_easy": { + "acc": 0.6212121212121212, + "acc_stderr": 0.009953737656542035, + "acc_norm": 0.6069023569023569, + "acc_norm_stderr": 0.010022540618945315 + }, + "arc_challenge": { + "acc": 0.2901023890784983, + "acc_stderr": 0.013261573677520764, + "acc_norm": 0.31143344709897613, + "acc_norm_stderr": 0.013532472099850945 + }, + "sciq": { + "acc": 0.916, + "acc_stderr": 0.008776162089491122, + "acc_norm": 0.899, + "acc_norm_stderr": 0.009533618929340988 + }, + "piqa": { + "acc": 0.7480957562568009, + "acc_stderr": 0.010128421335088683, + "acc_norm": 0.7693144722524483, + "acc_norm_stderr": 0.009828959550983096 } }, "versions": { @@ -54,6 +78,10 @@ "rte": 0, "winogrande": 0, "storycloze_2016": 0, - "boolq": 1 + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json index 7a46e0a1bc8214a19c12d5f85f9cd0cffbbf2947..94b3bb570177d9b9d6318464d032e4e6dcfbce4c 100644 --- a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json +++ b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_2_lm-eval_global_step80108_2023-02-24-21-45-54_2shots_backup.json @@ -42,6 +42,30 @@ "boolq": { "acc": 0.6097859327217126, "acc_stderr": 0.00853164352626324 + }, + "arc_easy": { + "acc": 0.6212121212121212, + "acc_stderr": 0.009953737656542035, + "acc_norm": 0.6069023569023569, + "acc_norm_stderr": 0.010022540618945315 + }, + "arc_challenge": { + "acc": 0.2901023890784983, + "acc_stderr": 0.013261573677520764, + "acc_norm": 0.31143344709897613, + "acc_norm_stderr": 0.013532472099850945 + }, + "sciq": { + "acc": 0.916, + "acc_stderr": 0.008776162089491122, + "acc_norm": 0.899, + "acc_norm_stderr": 0.009533618929340988 + }, + "piqa": { + "acc": 0.7480957562568009, + "acc_stderr": 0.010128421335088683, + "acc_norm": 0.7693144722524483, + "acc_norm_stderr": 0.009828959550983096 } }, "versions": { @@ -54,6 +78,10 @@ "rte": 0, "winogrande": 0, "storycloze_2016": 0, - "boolq": 1 + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_3.json b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_3.json index 229087857d6062a725ebcde2caf15771036d59fd..247ec8e20118a7e1bd45401fd6e02b3762c7f533 100644 --- a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_3.json +++ b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_3.json @@ -30,6 +30,42 @@ "rte": { "acc": 0.5234657039711191, "acc_stderr": 0.03006330041190266 + }, + "winogrande": { + "acc": 0.5872138910812944, + "acc_stderr": 0.01383706064868209 + }, + "storycloze_2016": { + "acc": 0.72367717797969, + "acc_stderr": 0.010340939873166824 + }, + "boolq": { + "acc": 0.6128440366972477, + "acc_stderr": 0.008519429207594416 + }, + "arc_easy": { + "acc": 0.6212121212121212, + "acc_stderr": 0.009953737656542037, + "acc_norm": 0.6077441077441077, + "acc_norm_stderr": 0.010018744689650043 + }, + "arc_challenge": { + "acc": 0.2790102389078498, + "acc_stderr": 0.01310678488360133, + "acc_norm": 0.2986348122866894, + "acc_norm_stderr": 0.013374078615068745 + }, + "sciq": { + "acc": 0.916, + "acc_stderr": 0.008776162089491115, + "acc_norm": 0.905, + "acc_norm_stderr": 0.009276910103103298 + }, + "piqa": { + "acc": 0.7524483133841132, + "acc_stderr": 0.010069703966857102, + "acc_norm": 0.764961915125136, + "acc_norm_stderr": 0.00989314668880531 } }, "versions": { @@ -39,6 +75,13 @@ "cb": 1, "copa": 0, "hellaswag": 0, - "rte": 0 + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json index 229087857d6062a725ebcde2caf15771036d59fd..247ec8e20118a7e1bd45401fd6e02b3762c7f533 100644 --- a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json +++ b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_3_lm-eval_global_step80108_2023-02-24-21-45-54_3shots_backup.json @@ -30,6 +30,42 @@ "rte": { "acc": 0.5234657039711191, "acc_stderr": 0.03006330041190266 + }, + "winogrande": { + "acc": 0.5872138910812944, + "acc_stderr": 0.01383706064868209 + }, + "storycloze_2016": { + "acc": 0.72367717797969, + "acc_stderr": 0.010340939873166824 + }, + "boolq": { + "acc": 0.6128440366972477, + "acc_stderr": 0.008519429207594416 + }, + "arc_easy": { + "acc": 0.6212121212121212, + "acc_stderr": 0.009953737656542037, + "acc_norm": 0.6077441077441077, + "acc_norm_stderr": 0.010018744689650043 + }, + "arc_challenge": { + "acc": 0.2790102389078498, + "acc_stderr": 0.01310678488360133, + "acc_norm": 0.2986348122866894, + "acc_norm_stderr": 0.013374078615068745 + }, + "sciq": { + "acc": 0.916, + "acc_stderr": 0.008776162089491115, + "acc_norm": 0.905, + "acc_norm_stderr": 0.009276910103103298 + }, + "piqa": { + "acc": 0.7524483133841132, + "acc_stderr": 0.010069703966857102, + "acc_norm": 0.764961915125136, + "acc_norm_stderr": 0.00989314668880531 } }, "versions": { @@ -39,6 +75,13 @@ "cb": 1, "copa": 0, "hellaswag": 0, - "rte": 0 + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_4.json b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_4.json index 2b62c87c9918224790f39127c2d8bd3859fde9bc..c12d2343330e602817476424e2219105c0aebd74 100644 --- a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_4.json +++ b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_4.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.83, "acc_stderr": 0.037752516806863715 + }, + "hellaswag": { + "acc": 0.4778928500298745, + "acc_stderr": 0.004984901752846394, + "acc_norm": 0.6368253335988847, + "acc_norm_stderr": 0.004799317209902008 + }, + "rte": { + "acc": 0.5126353790613718, + "acc_stderr": 0.030086851767188564 + }, + "winogrande": { + "acc": 0.595895816890292, + "acc_stderr": 0.013791610664670856 + }, + "storycloze_2016": { + "acc": 0.7311598075895244, + "acc_stderr": 0.010252563090396082 + }, + "boolq": { + "acc": 0.6207951070336392, + "acc_stderr": 0.008486012137246288 + }, + "arc_easy": { + "acc": 0.6224747474747475, + "acc_stderr": 0.00994722783346943, + "acc_norm": 0.6060606060606061, + "acc_norm_stderr": 0.010026305355981821 + }, + "arc_challenge": { + "acc": 0.28498293515358364, + "acc_stderr": 0.013191348179838795, + "acc_norm": 0.3165529010238908, + "acc_norm_stderr": 0.01359243151906808 + }, + "sciq": { + "acc": 0.925, + "acc_stderr": 0.00833333333333337, + "acc_norm": 0.913, + "acc_norm_stderr": 0.008916866630745911 + }, + "piqa": { + "acc": 0.7486398258977149, + "acc_stderr": 0.010121156016819257, + "acc_norm": 0.7633297062023939, + "acc_norm_stderr": 0.009916841655042809 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json index 2b62c87c9918224790f39127c2d8bd3859fde9bc..c12d2343330e602817476424e2219105c0aebd74 100644 --- a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json +++ b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_4_lm-eval_global_step80108_2023-02-24-21-45-54_4shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.83, "acc_stderr": 0.037752516806863715 + }, + "hellaswag": { + "acc": 0.4778928500298745, + "acc_stderr": 0.004984901752846394, + "acc_norm": 0.6368253335988847, + "acc_norm_stderr": 0.004799317209902008 + }, + "rte": { + "acc": 0.5126353790613718, + "acc_stderr": 0.030086851767188564 + }, + "winogrande": { + "acc": 0.595895816890292, + "acc_stderr": 0.013791610664670856 + }, + "storycloze_2016": { + "acc": 0.7311598075895244, + "acc_stderr": 0.010252563090396082 + }, + "boolq": { + "acc": 0.6207951070336392, + "acc_stderr": 0.008486012137246288 + }, + "arc_easy": { + "acc": 0.6224747474747475, + "acc_stderr": 0.00994722783346943, + "acc_norm": 0.6060606060606061, + "acc_norm_stderr": 0.010026305355981821 + }, + "arc_challenge": { + "acc": 0.28498293515358364, + "acc_stderr": 0.013191348179838795, + "acc_norm": 0.3165529010238908, + "acc_norm_stderr": 0.01359243151906808 + }, + "sciq": { + "acc": 0.925, + "acc_stderr": 0.00833333333333337, + "acc_norm": 0.913, + "acc_norm_stderr": 0.008916866630745911 + }, + "piqa": { + "acc": 0.7486398258977149, + "acc_stderr": 0.010121156016819257, + "acc_norm": 0.7633297062023939, + "acc_norm_stderr": 0.009916841655042809 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_5.json b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_5.json index 539ff08209ee2a544712bc85688f14c3494513d8..e541bb3ff3d05448624f964c8352e0d182fa935f 100644 --- a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_5.json +++ b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_5.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.83, "acc_stderr": 0.03775251680686371 + }, + "hellaswag": { + "acc": 0.4805815574586736, + "acc_stderr": 0.00498601693867853, + "acc_norm": 0.6412069308902609, + "acc_norm_stderr": 0.004786660691181924 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.030052303463143706 + }, + "winogrande": { + "acc": 0.5895816890292028, + "acc_stderr": 0.013825107120035861 + }, + "storycloze_2016": { + "acc": 0.7306253340459647, + "acc_stderr": 0.010258997754057014 + }, + "boolq": { + "acc": 0.6201834862385321, + "acc_stderr": 0.008488668235778617 + }, + "arc_easy": { + "acc": 0.6262626262626263, + "acc_stderr": 0.009927267058259628, + "acc_norm": 0.6174242424242424, + "acc_norm_stderr": 0.009972837790531479 + }, + "arc_challenge": { + "acc": 0.2901023890784983, + "acc_stderr": 0.01326157367752076, + "acc_norm": 0.310580204778157, + "acc_norm_stderr": 0.013522292098053052 + }, + "sciq": { + "acc": 0.923, + "acc_stderr": 0.008434580140240662, + "acc_norm": 0.915, + "acc_norm_stderr": 0.008823426366942314 + }, + "piqa": { + "acc": 0.7480957562568009, + "acc_stderr": 0.010128421335088681, + "acc_norm": 0.7714907508161044, + "acc_norm_stderr": 0.00979631351182951 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file diff --git a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json index 539ff08209ee2a544712bc85688f14c3494513d8..e541bb3ff3d05448624f964c8352e0d182fa935f 100644 --- a/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json +++ b/4b284b84bc4v2seed1/evaluation/rankeval/4b284b84bc4v2seed1_5_lm-eval_global_step80108_2023-02-24-21-45-54_5shots_backup.json @@ -20,6 +20,52 @@ "copa": { "acc": 0.83, "acc_stderr": 0.03775251680686371 + }, + "hellaswag": { + "acc": 0.4805815574586736, + "acc_stderr": 0.00498601693867853, + "acc_norm": 0.6412069308902609, + "acc_norm_stderr": 0.004786660691181924 + }, + "rte": { + "acc": 0.5270758122743683, + "acc_stderr": 0.030052303463143706 + }, + "winogrande": { + "acc": 0.5895816890292028, + "acc_stderr": 0.013825107120035861 + }, + "storycloze_2016": { + "acc": 0.7306253340459647, + "acc_stderr": 0.010258997754057014 + }, + "boolq": { + "acc": 0.6201834862385321, + "acc_stderr": 0.008488668235778617 + }, + "arc_easy": { + "acc": 0.6262626262626263, + "acc_stderr": 0.009927267058259628, + "acc_norm": 0.6174242424242424, + "acc_norm_stderr": 0.009972837790531479 + }, + "arc_challenge": { + "acc": 0.2901023890784983, + "acc_stderr": 0.01326157367752076, + "acc_norm": 0.310580204778157, + "acc_norm_stderr": 0.013522292098053052 + }, + "sciq": { + "acc": 0.923, + "acc_stderr": 0.008434580140240662, + "acc_norm": 0.915, + "acc_norm_stderr": 0.008823426366942314 + }, + "piqa": { + "acc": 0.7480957562568009, + "acc_stderr": 0.010128421335088681, + "acc_norm": 0.7714907508161044, + "acc_norm_stderr": 0.00979631351182951 } }, "versions": { @@ -27,6 +73,15 @@ "anli_r2": 0, "anli_r3": 0, "cb": 1, - "copa": 0 + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 } } \ No newline at end of file