diff --git a/.gitattributes b/.gitattributes
index bdf3e836a5d632bd09566ba06e01f6faee2b94c7..9c24676beb68851799956f374928f1ad551c37b3 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -153,3 +153,27 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 8b7178b88b/evaluation/generation/examples.8b7178b88b_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text
 8b7178b88b/evaluation/generation/examples.8b7178b88b_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text
 */eval/examples*.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text
+8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..7b90d0b8ec98130fc743f5e562bf4a4c5961e889
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.332418164076265, "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": 0.03696058294042095}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07190940889482068, "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": 0.001455025906136879}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.301390732870209, "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": 0.004402601720305443}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.1095978356180801, "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": 0.0019564248982681257}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03366735249156069, "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": 0.0008858326464608315}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.1465983694875745, "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": 0.003074755705857914}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05171405582224464, "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": 0.0012435373590367134}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06928463832111945, "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": 0.001354402286433117}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.29343421778124684, "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": 0.004302109252038838}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10587809310127003, "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": 0.001838006623068389}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06900976089065335, "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": 0.0013821359592628988}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.28936351476019084, "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": 0.004198483169030062}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.10516308015267403, "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": 0.0018547700987810625}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..99db7afda9e2eee3fd15064e2348445456b521ba
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.4396246502267527, "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": 0.03794273972678262}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.0739181124020759, "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": 0.0013418349953620108}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.35963891837485074, "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": 0.004935335446807934}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.11510858435008614, "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": 0.001829941745508391}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.034943394233011765, "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": 0.0008228677576697449}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.17989319170126253, "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": 0.003650522605621509}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.054655222423642985, "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": 0.0011574253411672022}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07022432800426698, "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": 0.0012223544306487109}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3398876745824502, "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": 0.004493731176695288}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10946339983990763, "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": 0.0016790473876574434}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.07093990858477271, "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": 0.0012725781012108558}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.34408662950943764, "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": 0.004619974377582772}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.11046019470928523, "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": 0.00173280705768612}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..1830b63157d57c9393b41c63830f5ff75cf78a9b
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.47929145559638225, "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": 0.013932123962412855}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07137936932112236, "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": 0.0011784730418670042}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.3699801668532645, "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": 0.004983372147117968}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.11266051583386952, "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": 0.0016388264831012904}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03309847277281182, "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": 0.0007256900997219835}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.18647973916218474, "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": 0.0037435312434141257}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05259910261699664, "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": 0.0010491604565333935}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06751660699477897, "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": 0.0011071302423418996}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3460463516284548, "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": 0.0044526867532594374}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10644239169147508, "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": 0.0015316327496444973}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06854436178289768, "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": 0.001132855557018181}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.35357532668740393, "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": 0.004680159458874175}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.10811495254365688, "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": 0.0015702834219670347}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..d812408d9593de0a662a8adfcc0a20ecdb2985f3
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.5254091236383978, "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": 0.0272707184705863}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07190916345114307, "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": 0.0011342056239523493}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.3796797864121142, "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": 0.0049211015597907335}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.1137800918874328, "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": 0.0015623641314802495}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03359440011812607, "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": 0.000717267417649812}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.19204855728023304, "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": 0.003700810575997827}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.053524415343767374, "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": 0.0010377150477586447}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06797419059481667, "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": 0.0010722591518842702}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3549241769775831, "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": 0.0044079173685938056}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10739509357535582, "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": 0.0014688768045950926}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06883524450761919, "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": 0.0010904375559758742}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.36157753989860286, "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": 0.00458238890896547}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.10880190459995145, "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": 0.0014957717696141243}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..a10c5f8b719cfe26b831a14e3886229402391e1b
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.5896016424303352, "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": 0.04348163762184696}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07280177888449052, "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": 0.001167476102151522}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.38454519285609656, "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": 0.004901871012575138}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.1152098647187527, "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": 0.0015875085813414037}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03384968429202272, "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": 0.0007316072980959663}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.19690825980706886, "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": 0.003822922236606215}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05404038379134397, "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": 0.001047558823714542}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06829385238072445, "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": 0.0010696413261370567}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3593088405468019, "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": 0.004380347845482903}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10796621981670128, "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": 0.0014415066070786182}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06983214496239268, "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": 0.0011145751003995281}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.3684081584518333, "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": 0.0046181910041404525}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.11042781164659983, "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": 0.0015072405756468101}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..bd610d69776074f2d36146e62db2a6d14efd7134
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.5579849887702564, "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": 0.02566777731605262}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.0722244811765284, "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": 0.0010883491004439172}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.39225252025509727, "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": 0.00500239708089686}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.11496348733004745, "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": 0.0014986246232008803}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.033751098133716816, "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": 0.0007017585569903578}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.20045030871386427, "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": 0.0038136378057587856}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05406065553629826, "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": 0.001009602112409382}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06750750522157839, "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": 0.0010132953538675234}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3629468989772955, "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": 0.004411901125085533}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10724709950776415, "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": 0.001385394861578905}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06905880474217613, "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": 0.001041674323116577}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.37377123464513246, "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": 0.004666454165917922}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.10981073422881693, "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": 0.0014263114503938255}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..2b2e9cf3ba058e6db71a6f19f6a04387ccc3714f
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.15972274079475446, "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": 0.0019865559238896858}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.2700593421670508, "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": 0.0027737951668886907}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.1862365342289606, "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": 0.0019333176047893425}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.034556806570887444, "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": 0.0008425423478960415}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.05978905462791134, "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": 0.0014708640693064097}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.04032054400755849, "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": 0.0009252920084472916}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.12038536558218806, "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": 0.0013551069603724947}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.21115022540563333, "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": 0.0022023323083645396}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.14210549237770434, "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": 0.001352102962568602}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.1471563634835902, "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": 0.001816380499537014}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.24955829066428167, "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": 0.0025549018069577077}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.17172494748072423, "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": 0.0017652741846676486}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.831310525161332, "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": 0.08457373503805206}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..fada784fab4fae37349c44863c40e71941fe5970
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.20084840762025002, "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": 0.002375570727890994}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.3279331840452314, "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": 0.0029166900556576378}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.22713731519119962, "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": 0.0020303856541629157}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.05192805744789268, "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": 0.0011904825748754472}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.08693391944333162, "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": 0.0017928197332860247}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.05813673529140247, "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": 0.0010858552857269058}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.1432641278979817, "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": 0.0016838668333439412}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.24141036590043435, "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": 0.002321080600691811}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.16290527667884375, "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": 0.0013800590148163698}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.1885894929526097, "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": 0.0022300914877422806}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.3090983774717522, "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": 0.0027802990042071363}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.21344783101010534, "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": 0.0019004009451698382}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 3.1946229115600104, "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": 0.0902528894135031}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d3a0614cef57874e59e947817eff001d3dc66ff
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.2656984608711839, "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": 0.003475974826636605}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.3139253119933751, "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": 0.003012955655711283}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.24178148334371152, "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": 0.002084865329415859}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.08136466928288727, "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": 0.0021586497346161937}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.09042739130647694, "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": 0.0018404609298964}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.06887382606726644, "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": 0.0012807228279060876}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.20056631932614633, "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": 0.0029240196408032576}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.23442772665220632, "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": 0.002412584818753376}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.17903750582234018, "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": 0.0015877517832273015}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.2521499144307301, "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": 0.0033481985589333117}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.29706441266630634, "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": 0.0028655519018383232}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.22871976277916323, "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": 0.0019660579351207536}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 4.089342922787345, "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": 0.09294377977855839}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..9d828744a80e4e0d08cf335a3ba7df097e7df75d
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.25558962697073145, "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": 0.004282279704468573}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.23153110943427863, "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": 0.003438107905334785}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.19590336767483915, "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": 0.002603449114946719}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.08146818659563723, "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": 0.002448660534108266}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.06743455850825143, "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": 0.0017452087926378838}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.05767822682063389, "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": 0.0013980794793852763}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.19917268042172423, "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": 0.00359110440185509}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.17626539265723254, "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": 0.0027059496141968596}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.14912723506935083, "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": 0.0020363514995009485}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.24272073863797083, "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": 0.004109190949161484}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.2194427111114507, "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": 0.003281194179793178}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.18563647374529954, "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": 0.0024816986882333276}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 4.072610754323664, "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": 0.07525164017980863}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..4c9b676c07bd074abdeaca6e9633df196efdccb0
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.08272085590013521, "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": 0.003328470018227569}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.073607896755553, "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": 0.002786595724689709}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.060859438120474105, "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": 0.002186962487867776}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.027384557827759736, "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": 0.0017208392028580295}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.021828735652406926, "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": 0.0011755690210094216}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.018259934336381307, "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": 0.0009369665663167178}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.0663593638177798, "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": 0.002792690105843212}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.056938933254415285, "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": 0.0021770204347710985}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.047327721198656594, "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": 0.001720788977327356}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.0784447476522085, "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": 0.003187161977557443}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.06936769106400163, "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": 0.0026401376140555047}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.05738648078691023, "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": 0.0020702191744425805}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.30672054851921343, "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": 0.027801502217640873}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..84300cafdda519437d529189d29508d22e7f3c7f
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.013957270253644866, "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": 0.0015489152693527737}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.010948829734039874, "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": 0.001189429950745709}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.009545168655738663, "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": 0.0009833205973525279}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.005346599799374829, "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": 0.000922536579868288}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.003447960863177172, "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": 0.0005097345293134105}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.003194781805527316, "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": 0.00046191164979125494}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.011558443617862643, "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": 0.0013357028661274022}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.00878713432773727, "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": 0.0009510460692818358}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.00771353363185855, "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": 0.0008078330599179273}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.013380501718320581, "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": 0.0014992977277420356}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.010421509428125204, "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": 0.0011325542079141924}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.009095278752494966, "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": 0.0009411593635337467}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.0767109875104664e-10, "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": 2.7041266760972117e-09}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c86a8a5b6c96886de57f51fac1be9c5e22e91a5
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 2.1637748729872377, "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": 0.04708061810035152}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.17571114021612258, "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": 0.00234001350004936}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.2403810966028036, "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": 0.001917930986446359}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.1857729182904806, "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": 0.0015977758615005752}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.03853560508356721, "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": 0.0008749576393956302}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.04848364378645718, "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": 0.001080661761475741}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.038846854218182576, "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": 0.0008031687884467253}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.13673433720639006, "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": 0.0018383470645185228}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.19020915483344014, "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": 0.0015344656813421698}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.14517349755186024, "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": 0.00122530969799679}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.16441038855158038, "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": 0.00216945133305093}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.22661830578107306, "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": 0.0019584009970905515}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.17477219266422644, "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": 0.0015733449442962115}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..e730ae6dc9a6958acf233f1328895039bb0aea93
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 12.699076129183206, "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": 0.10399531996709636}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.5458616254773436, "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": 0.0034897518863656377}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.44911695528747547, "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": 0.003049432231004983}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.46200013120745637, "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": 0.0023848096470577393}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.2625771628656913, "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": 0.002777565484439754}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.21189977549122158, "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": 0.0022330452298268692}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.21840214637971003, "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": 0.0020520500269639213}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.4020226840139383, "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": 0.003079117739342717}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.3281876590745158, "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": 0.002505390281354571}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.3377881512152975, "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": 0.0020544234738392457}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.45027802951118134, "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": 0.0033307854923309735}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.3687964450646062, "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": 0.002811107425715743}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.3799905020241611, "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": 0.0023491152850802477}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..c60a159011e70c75537a254e7625b71bc366c571
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 15.349320073567956, "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": 0.20065362471122622}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.5641138089260663, "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": 0.003122162389799746}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.4993081674056431, "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": 0.0029190169239720776}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.5062690903947293, "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": 0.0022184418781909503}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.28480233937098404, "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": 0.0026558013765171293}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.2505303415532217, "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": 0.002363227578711657}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.25323692889972166, "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": 0.002116475114261491}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.4134223803505085, "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": 0.0027884299786810726}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.364967373581058, "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": 0.0025050008227674118}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.3699075196394537, "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": 0.002038510745722095}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.4701745407770204, "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": 0.0030588655833951616}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.415665042099645, "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": 0.0027902197560574714}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.42153114614795945, "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": 0.0022965855563879564}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..e0af370d76eff43a1061790dd2be972e6bd2996b
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 14.321380888062812, "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": 0.13332556788591748}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.5163006609255177, "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": 0.002848705467042193}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.5103725325478746, "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": 0.002812023353115975}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.4942167403659075, "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": 0.0021128256597481797}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.2568516782752942, "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": 0.0023590125409771855}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.2546224310607835, "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": 0.0023818244395298806}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.24523127893147686, "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": 0.0020480988327082963}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3787196100484137, "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": 0.0024985656409790852}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.3741605928354789, "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": 0.002454556248255368}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.36209783653768146, "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": 0.001959264414079404}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.4306732810674897, "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": 0.002754882401260447}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.42590630743564917, "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": 0.0027265425997138994}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.41228039547049994, "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": 0.002190141578787795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..72bbf6883a014a9318c35ad209e356297eb8f3b8
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 13.722841928196777, "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": 0.13804846172826613}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.48828386592969264, "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": 0.0024858404633992743}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.5114305264974095, "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": 0.002697661923152199}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.48393429045188835, "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": 0.0019859645893939115}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.24059108499141613, "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": 0.00210840059224509}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.25365084544842664, "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": 0.0023384488190548417}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.23840855028747443, "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": 0.0019573193912396634}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3566021510402825, "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": 0.002136311576118472}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.3747086531915837, "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": 0.0023926470384127776}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.3537873295650889, "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": 0.0018387088951343877}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.4075869423080161, "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": 0.0024174778601222056}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.4276935666531386, "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": 0.002665628883634715}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.4043059323351792, "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": 0.002080752243862837}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..2803bb27a696f99682fd53f7c2768982d22c6964
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 13.372484418259432, "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": 0.12631428400851766}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.47557867752442456, "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": 0.0023360428027170664}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.5107946193055894, "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": 0.002625085316285608}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.47859053217432174, "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": 0.0019398187941902603}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.23277405462932813, "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": 0.00205201253568292}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.2519154898433275, "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": 0.0023288239477406566}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.23444687287756075, "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": 0.001962765988186735}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3476553000546008, "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": 0.0020361706787158022}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.3751201703103127, "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": 0.002384327433554856}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.35043527019394044, "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": 0.0018309395599414636}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.39968395508657584, "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": 0.0023326315704367095}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.42940604077002287, "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": 0.002605951608709431}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.4022665348493678, "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": 0.002066528906487744}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_0.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..b5f33b9346590c5c48e85865624374b94d9b75a8
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_0.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.16652504564117318, "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": 0.0020480225617605856}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.37848923564363685, "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": 0.0045711110875955915}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.2252785173179299, "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": 0.0025302839963541515}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.04023090834156273, "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": 0.0012912806060900344}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.09751455692123925, "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": 0.003144590481436754}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.05560640356600142, "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": 0.0017257721593849657}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.12391529652302673, "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": 0.0015698267806295476}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.28383434867259993, "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": 0.003658695564054696}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.1678662401695973, "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": 0.0019429705177302374}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.1310543700695647, "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": 0.0017000651189640957}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.30107876434344966, "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": 0.004054884960237835}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.17781888968117063, "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": 0.0021578317596841075}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 2.381704327009844, "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": 0.11413286241675519}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_1.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..5ce18553bff8681ca948c4bbc5e98d6e44a04117
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_1.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.13823526560660052, "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": 0.0020944863718590696}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.33753001607653804, "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": 0.004807587398146579}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.1938089585188387, "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": 0.002822597453009016}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.03166938333546749, "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": 0.0011689549810166263}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.07993218887659431, "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": 0.0029743255309706987}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.04477392420959174, "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": 0.001637714965321643}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.10613937916799303, "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": 0.001538610633349276}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.2616251241654161, "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": 0.0037053413551593833}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.1491400353009075, "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": 0.002089252796225244}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.11026653419842858, "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": 0.001720420262105802}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.27172748877390046, "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": 0.004162646884513488}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.15494229567861334, "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": 0.002347654380789924}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 1.9568092253132736, "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": 0.08743638623038145}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_2.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5cba845dd876fe735e2ae8ad9b26b0121f98250
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_2.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.14402898776642667, "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": 0.001998944393289479}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.351517404045027, "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": 0.004610583100015181}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.20197965634555684, "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": 0.002690267282815034}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.035886973035083945, "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": 0.001190491610976737}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.09015312700835054, "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": 0.003061506688050075}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.050742990668066985, "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": 0.0016773265894277122}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.11355508618202974, "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": 0.0015669742839297053}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.27829233445848645, "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": 0.0036956919869857914}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.15939919631832364, "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": 0.002118290262084322}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.11304178539172682, "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": 0.0016600760618328486}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.27844833955215303, "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": 0.004022259545774517}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.15895119262920798, "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": 0.002273913023033009}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 2.1208498600162966, "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": 0.08489840925537316}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_3.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..9529d173423c591fd661c47768e189c392ffe2dc
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_3.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.14192323740566237, "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": 0.002270573664293402}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.3317122838307692, "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": 0.0048796302898910975}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.19449648740464862, "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": 0.002859916967955778}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.03602126113927686, "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": 0.0012539266263007617}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.0878057273475559, "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": 0.0030959059452337553}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.049958285647633605, "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": 0.0017043147625524138}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.11305477995205825, "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": 0.0017434930500077924}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.2663468354538728, "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": 0.0039010875469112365}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.15536673840207987, "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": 0.0022317734298045364}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.11102920371579805, "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": 0.001876855631693002}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.2613081764654086, "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": 0.004217382008118568}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.15242546645043564, "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": 0.002411210173116271}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 2.1488883346464993, "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": 0.10061894207225484}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_4.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..1b28d6dd1acfec0b49c2c94824dd162555bfaa25
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_4.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.04622581157969239, "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": 0.002758425516324379}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.0843663512427161, "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": 0.004754251649959729}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.053859811302847754, "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": 0.0029259257948128737}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.009725911780399114, "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": 0.0008407639061619823}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.021588809000409173, "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": 0.0018787516143550758}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.012848562232113562, "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": 0.0010859365945209303}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.03656500907804365, "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": 0.002224872922024987}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.06728556626210627, "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": 0.003838297011101563}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.042690265385557376, "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": 0.0023298094610187006}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.03647468832987227, "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": 0.0022537297464633585}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.06688889415336839, "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": 0.0038935277003977983}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.04238885022609439, "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": 0.002344653333666526}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 1.030072955735859, "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": 0.1448131273948289}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_5.json b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..be71660dee385c914a83567e8cb24fadfff7f1d5
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/agg.8b7178b178b_gem_xsum_article_DOC_summary_5.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.002521194639962509, "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": 0.0007796352087425173}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.004189678674165279, "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": 0.0012085716148740944}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.0028858004896843946, "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": 0.0008256676759201416}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.0006208832859776256, "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": 0.00029409209860814094}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.001041831827070451, "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": 0.0004529249135232237}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.0007107345703701913, "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": 0.00031220919556434665}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.001959124935014627, "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": 0.0005749051558534733}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.003422811625192831, "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": 0.0010061472311316847}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.0023094434195131235, "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": 0.0006631782952940002}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.0021015099772572314, "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": 0.00067865052077321}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.0034125788706789104, "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": 0.000959892406042587}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.0023727145860087903, "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": 0.0006800010549959292}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 1.5116856439856716e-16, "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": 7.251120818898454e-14}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 4, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..8f20a168963ffa359090493a5b7ab2b1425c2355
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8785546c00bf77aef039b217d0a1f0d9d4377f8157da16d77ab26367665eae0
+size 4096746
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..4305d7e513422b246bb8174b8780a9ac6e131896
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b77263ef5a7caf4763aca264667aa22427123a5134406d052d7f3d35f3915c8
+size 5108592
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..906062a9d8785a1162e1430c6cbd7349509d8ffa
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3ab11b9dc610c57ce6085d8acf1057d8d7a6c161dc5c282d8e3df68a038ae6
+size 6009302
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..0a361fa7836b133ea2e36b3d143f843df54c921c
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb75d308396667c239d33948bf1f5bbb6e71ba4091e12f410662bbb247a4df4
+size 6926163
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..2b8b392a372e2289f15d8e7c7a8bde964797447d
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5ebec668cbf82d614f1ad8998a7e2158866d45a1e33808565ca7f8c9f002c4
+size 7828256
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..bd361f6353bde89cd9ea53a03fac19d4918228d2
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac9aa94a5c627828d34d017a6ad47da6b12e6ca159e8d104608bc08c78933ed
+size 8731073
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..5d00f8582bd5a39a38708c33ab8923594efaff02
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245239acc4545f7ecfe5eaeddf09397ece7d0c9685dd3d91bfe03b0f278a259a
+size 7679158
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..6b16a5aefec6c2e836df68e37fbabd08c90c032e
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0703c108092dd9e6d780514572aeb7c099186bd54eb6c8d06e722d7d5abdb38b
+size 13289374
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..c6c9c69dc9133f318bf57942d3017d2b3425fa46
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9537730bb72eb797dd125481435f2cbfcf8c8d996a4ba0ededc5702a5a86e17
+size 18772105
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..1f92f6c0e6e0e2409747c9a22982112c14e3e25d
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9aa21c31a7e192bea932700b064de319608dee4d06277c243736d3a8317096
+size 24129232
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..4f634b2fa626ded98b4427c1a68191316a7516c2
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70b10c299ed13e992c4081ab7d7e88119b3f055ce285274acc8a1c63cd8b141
+size 29399019
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..628dd060a5cab175a990a5490666be0d76c70be0
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b664fd3ab7f7a7bb9b4ddbfa3acf2f28649cbf4fa27b6792e92fc900e90931
+size 34786365
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..7f6b88ae4e209553207da73dc800f11c5254319e
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73914be3a415710a4fdab8135b15b3888e32d8cee656429b7f8ccf98571491fc
+size 4378660
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..cc7e1677051f59e8dfd191b12e00753c59577d5e
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a512a43e34b16a47c562a13c63c523916fa609702f658df0d1bf88d17260c07
+size 5061249
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..601dc4d4bd21cef4b95e6d23cca9010af97ea202
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5c9dd5bf67263365ea47e896f48e776c5edbeb59bb89a6cca0f6cbbb607ce5
+size 6156989
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..335765b30afabc7934a1a1a950738bdf53d5e6b9
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b217325605baf9d6312d197eeddc4a5177b8b43172cb7f80c7884d1eb548a8
+size 7279947
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..624406b0c6c7aa2e8d767e33d3163a1e91471c73
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1affa759dd85ece3d3b095038eb9c5f0478b5a915da61e20746e1462ccd82ee2
+size 8379018
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..f02db8170320a0447347a496b6a873f6bd5f8260
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd82565e11d5cc3389c01b189c34d5f315c8a3ee0708a9253289d5dec9d1c4e
+size 9475771
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_0.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_0.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..33ff3571f4d614b8dee814ce744588f4e090d919
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_0.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248cdfd749630fbbbc5beca16b9b190b31e3bbdec3719f453944bd16474459fb
+size 2822077
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_1.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_1.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..e87eedb9a19084d8a1bd24d1fdc1687ddf183d0f
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_1.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0c3a9586164938d135b3d0efff1c4f84bb6b7e7232582ec65f4d1cd8934f3e
+size 5105834
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_2.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_2.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..da51d61da3d4b0780ecc76ed463f06e2287659a4
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_2.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1032b6f2bb926523fffbd108653451c828363b98d3fbf6a8b433610e7b086c74
+size 7380745
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_3.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_3.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..b5c93915857b81e4e7cc79c77c0e05090067b075
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_3.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f740dd78d91ddfcce9697980fc419b1a124c0c80deca5657441db8a5d8c54358
+size 9649918
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_4.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_4.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..34039494330a08ab3ead84dc380a6d19e9bef0bf
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_4.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444aee3bbfe9e4fd1297f7744aa0038d229d401785285a92f32e72bc4c56b7ae
+size 11674383
diff --git a/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_5.jsonl b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_5.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..87b7960ac4ba3c004b5f023eb1d77d7fa66d481d
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/examples.8b7178b178b_gem_xsum_article_DOC_summary_5.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6bcf8e22c9abd339939405e5365e8a158afefbbfad527d117e927fb3c35543
+size 13899553
diff --git a/8b7178b178b/evaluation/generation/merged.csv b/8b7178b178b/evaluation/generation/merged.csv
new file mode 100644
index 0000000000000000000000000000000000000000..d32720d9b242f1de40647efebc7714c1e4c057f5
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/merged.csv
@@ -0,0 +1,53 @@
+dataset,fewshots,prompt,metric,value
+e2e_nlg_cleaned,0,generate_text_restaurant,rouge2_fmeasure,0.038846854218182576
+e2e_nlg_cleaned,0,median,rouge2_fmeasure,0.038846854218182576
+e2e_nlg_cleaned,1,generate_text_restaurant,rouge2_fmeasure,0.21840214637971003
+e2e_nlg_cleaned,1,median,rouge2_fmeasure,0.21840214637971003
+e2e_nlg_cleaned,2,generate_text_restaurant,rouge2_fmeasure,0.25323692889972166
+e2e_nlg_cleaned,2,median,rouge2_fmeasure,0.25323692889972166
+e2e_nlg_cleaned,3,generate_text_restaurant,rouge2_fmeasure,0.24523127893147686
+e2e_nlg_cleaned,3,median,rouge2_fmeasure,0.24523127893147686
+e2e_nlg_cleaned,4,generate_text_restaurant,rouge2_fmeasure,0.23840855028747443
+e2e_nlg_cleaned,4,median,rouge2_fmeasure,0.23840855028747443
+e2e_nlg_cleaned,5,generate_text_restaurant,rouge2_fmeasure,0.23444687287756075
+e2e_nlg_cleaned,5,median,rouge2_fmeasure,0.23444687287756075
+e2e_nlg_cleaned,5,average,multiple,0.20476210526568772
+gem_xsum,0,article_DOC_summary,rouge2_fmeasure,0.05560640356600142
+gem_xsum,0,median,rouge2_fmeasure,0.05560640356600142
+gem_xsum,1,article_DOC_summary,rouge2_fmeasure,0.04477392420959174
+gem_xsum,1,median,rouge2_fmeasure,0.04477392420959174
+gem_xsum,2,article_DOC_summary,rouge2_fmeasure,0.050742990668066985
+gem_xsum,2,median,rouge2_fmeasure,0.050742990668066985
+gem_xsum,3,article_DOC_summary,rouge2_fmeasure,0.049958285647633605
+gem_xsum,3,median,rouge2_fmeasure,0.049958285647633605
+gem_xsum,4,article_DOC_summary,rouge2_fmeasure,0.012848562232113562
+gem_xsum,4,median,rouge2_fmeasure,0.012848562232113562
+gem_xsum,5,article_DOC_summary,rouge2_fmeasure,0.0007107345703701913
+gem_xsum,5,median,rouge2_fmeasure,0.0007107345703701913
+gem_xsum,5,average,multiple,0.03577348348229625
+web_nlg_en,0,PALM_prompt,rouge2_fmeasure,0.05171405582224464
+web_nlg_en,0,median,rouge2_fmeasure,0.05171405582224464
+web_nlg_en,1,PALM_prompt,rouge2_fmeasure,0.054655222423642985
+web_nlg_en,1,median,rouge2_fmeasure,0.054655222423642985
+web_nlg_en,2,PALM_prompt,rouge2_fmeasure,0.05259910261699664
+web_nlg_en,2,median,rouge2_fmeasure,0.05259910261699664
+web_nlg_en,3,PALM_prompt,rouge2_fmeasure,0.053524415343767374
+web_nlg_en,3,median,rouge2_fmeasure,0.053524415343767374
+web_nlg_en,4,PALM_prompt,rouge2_fmeasure,0.05404038379134397
+web_nlg_en,4,median,rouge2_fmeasure,0.05404038379134397
+web_nlg_en,5,PALM_prompt,rouge2_fmeasure,0.05406065553629826
+web_nlg_en,5,median,rouge2_fmeasure,0.05406065553629826
+web_nlg_en,5,average,multiple,0.05343230592238231
+wiki_lingua_en,0,tldr_en,rouge2_fmeasure,0.04032054400755849
+wiki_lingua_en,0,median,rouge2_fmeasure,0.04032054400755849
+wiki_lingua_en,1,tldr_en,rouge2_fmeasure,0.05813673529140247
+wiki_lingua_en,1,median,rouge2_fmeasure,0.05813673529140247
+wiki_lingua_en,2,tldr_en,rouge2_fmeasure,0.06887382606726644
+wiki_lingua_en,2,median,rouge2_fmeasure,0.06887382606726644
+wiki_lingua_en,3,tldr_en,rouge2_fmeasure,0.05767822682063389
+wiki_lingua_en,3,median,rouge2_fmeasure,0.05767822682063389
+wiki_lingua_en,4,tldr_en,rouge2_fmeasure,0.018259934336381307
+wiki_lingua_en,4,median,rouge2_fmeasure,0.018259934336381307
+wiki_lingua_en,5,tldr_en,rouge2_fmeasure,0.003194781805527316
+wiki_lingua_en,5,median,rouge2_fmeasure,0.003194781805527316
+wiki_lingua_en,5,average,multiple,0.04107734138812832
diff --git a/8b7178b178b/evaluation/generation/merged.json b/8b7178b178b/evaluation/generation/merged.json
new file mode 100644
index 0000000000000000000000000000000000000000..f038d048a99fe196e3d207e677b0740db02d3a9a
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/merged.json
@@ -0,0 +1 @@
+{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.332418164076265, "bleu_stderr": 0.03696058294042095, "rouge1_fmeasure": 0.1095978356180801, "rouge1_fmeasure_stderr": 0.0019564248982681257, "rouge1_precision": 0.07190940889482068, "rouge1_precision_stderr": 0.001455025906136879, "rouge1_recall": 0.301390732870209, "rouge1_recall_stderr": 0.004402601720305443, "rouge2_fmeasure": 0.05171405582224464, "rouge2_fmeasure_stderr": 0.0012435373590367134, "rouge2_precision": 0.03366735249156069, "rouge2_precision_stderr": 0.0008858326464608315, "rouge2_recall": 0.1465983694875745, "rouge2_recall_stderr": 0.003074755705857914, "rougeL_fmeasure": 0.10587809310127003, "rougeL_fmeasure_stderr": 0.001838006623068389, "rougeL_precision": 0.06928463832111945, "rougeL_precision_stderr": 0.001354402286433117, "rougeL_recall": 0.29343421778124684, "rougeL_recall_stderr": 0.004302109252038838, "rougeLsum_fmeasure": 0.10516308015267403, "rougeLsum_fmeasure_stderr": 0.0018547700987810625, "rougeLsum_precision": 0.06900976089065335, "rougeLsum_precision_stderr": 0.0013821359592628988, "rougeLsum_recall": 0.28936351476019084, "rougeLsum_recall_stderr": 0.004198483169030062}}, "1": {"PALM_prompt": {"bleu": 0.4396246502267527, "bleu_stderr": 0.03794273972678262, "rouge1_fmeasure": 0.11510858435008614, "rouge1_fmeasure_stderr": 0.001829941745508391, "rouge1_precision": 0.0739181124020759, "rouge1_precision_stderr": 0.0013418349953620108, "rouge1_recall": 0.35963891837485074, "rouge1_recall_stderr": 0.004935335446807934, "rouge2_fmeasure": 0.054655222423642985, "rouge2_fmeasure_stderr": 0.0011574253411672022, "rouge2_precision": 0.034943394233011765, "rouge2_precision_stderr": 0.0008228677576697449, "rouge2_recall": 0.17989319170126253, "rouge2_recall_stderr": 0.003650522605621509, "rougeL_fmeasure": 0.10946339983990763, "rougeL_fmeasure_stderr": 0.0016790473876574434, "rougeL_precision": 0.07022432800426698, "rougeL_precision_stderr": 0.0012223544306487109, "rougeL_recall": 0.3398876745824502, "rougeL_recall_stderr": 0.004493731176695288, "rougeLsum_fmeasure": 0.11046019470928523, "rougeLsum_fmeasure_stderr": 0.00173280705768612, "rougeLsum_precision": 0.07093990858477271, "rougeLsum_precision_stderr": 0.0012725781012108558, "rougeLsum_recall": 0.34408662950943764, "rougeLsum_recall_stderr": 0.004619974377582772}}, "2": {"PALM_prompt": {"bleu": 0.47929145559638225, "bleu_stderr": 0.013932123962412855, "rouge1_fmeasure": 0.11266051583386952, "rouge1_fmeasure_stderr": 0.0016388264831012904, "rouge1_precision": 0.07137936932112236, "rouge1_precision_stderr": 0.0011784730418670042, "rouge1_recall": 0.3699801668532645, "rouge1_recall_stderr": 0.004983372147117968, "rouge2_fmeasure": 0.05259910261699664, "rouge2_fmeasure_stderr": 0.0010491604565333935, "rouge2_precision": 0.03309847277281182, "rouge2_precision_stderr": 0.0007256900997219835, "rouge2_recall": 0.18647973916218474, "rouge2_recall_stderr": 0.0037435312434141257, "rougeL_fmeasure": 0.10644239169147508, "rougeL_fmeasure_stderr": 0.0015316327496444973, "rougeL_precision": 0.06751660699477897, "rougeL_precision_stderr": 0.0011071302423418996, "rougeL_recall": 0.3460463516284548, "rougeL_recall_stderr": 0.0044526867532594374, "rougeLsum_fmeasure": 0.10811495254365688, "rougeLsum_fmeasure_stderr": 0.0015702834219670347, "rougeLsum_precision": 0.06854436178289768, "rougeLsum_precision_stderr": 0.001132855557018181, "rougeLsum_recall": 0.35357532668740393, "rougeLsum_recall_stderr": 0.004680159458874175}}, "3": {"PALM_prompt": {"bleu": 0.5254091236383978, "bleu_stderr": 0.0272707184705863, "rouge1_fmeasure": 0.1137800918874328, "rouge1_fmeasure_stderr": 0.0015623641314802495, "rouge1_precision": 0.07190916345114307, "rouge1_precision_stderr": 0.0011342056239523493, "rouge1_recall": 0.3796797864121142, "rouge1_recall_stderr": 0.0049211015597907335, "rouge2_fmeasure": 0.053524415343767374, "rouge2_fmeasure_stderr": 0.0010377150477586447, "rouge2_precision": 0.03359440011812607, "rouge2_precision_stderr": 0.000717267417649812, "rouge2_recall": 0.19204855728023304, "rouge2_recall_stderr": 0.003700810575997827, "rougeL_fmeasure": 0.10739509357535582, "rougeL_fmeasure_stderr": 0.0014688768045950926, "rougeL_precision": 0.06797419059481667, "rougeL_precision_stderr": 0.0010722591518842702, "rougeL_recall": 0.3549241769775831, "rougeL_recall_stderr": 0.0044079173685938056, "rougeLsum_fmeasure": 0.10880190459995145, "rougeLsum_fmeasure_stderr": 0.0014957717696141243, "rougeLsum_precision": 0.06883524450761919, "rougeLsum_precision_stderr": 0.0010904375559758742, "rougeLsum_recall": 0.36157753989860286, "rougeLsum_recall_stderr": 0.00458238890896547}}, "4": {"PALM_prompt": {"bleu": 0.5896016424303352, "bleu_stderr": 0.04348163762184696, "rouge1_fmeasure": 0.1152098647187527, "rouge1_fmeasure_stderr": 0.0015875085813414037, "rouge1_precision": 0.07280177888449052, "rouge1_precision_stderr": 0.001167476102151522, "rouge1_recall": 0.38454519285609656, "rouge1_recall_stderr": 0.004901871012575138, "rouge2_fmeasure": 0.05404038379134397, "rouge2_fmeasure_stderr": 0.001047558823714542, "rouge2_precision": 0.03384968429202272, "rouge2_precision_stderr": 0.0007316072980959663, "rouge2_recall": 0.19690825980706886, "rouge2_recall_stderr": 0.003822922236606215, "rougeL_fmeasure": 0.10796621981670128, "rougeL_fmeasure_stderr": 0.0014415066070786182, "rougeL_precision": 0.06829385238072445, "rougeL_precision_stderr": 0.0010696413261370567, "rougeL_recall": 0.3593088405468019, "rougeL_recall_stderr": 0.004380347845482903, "rougeLsum_fmeasure": 0.11042781164659983, "rougeLsum_fmeasure_stderr": 0.0015072405756468101, "rougeLsum_precision": 0.06983214496239268, "rougeLsum_precision_stderr": 0.0011145751003995281, "rougeLsum_recall": 0.3684081584518333, "rougeLsum_recall_stderr": 0.0046181910041404525}}, "5": {"PALM_prompt": {"bleu": 0.5579849887702564, "bleu_stderr": 0.02566777731605262, "rouge1_fmeasure": 0.11496348733004745, "rouge1_fmeasure_stderr": 0.0014986246232008803, "rouge1_precision": 0.0722244811765284, "rouge1_precision_stderr": 0.0010883491004439172, "rouge1_recall": 0.39225252025509727, "rouge1_recall_stderr": 0.00500239708089686, "rouge2_fmeasure": 0.05406065553629826, "rouge2_fmeasure_stderr": 0.001009602112409382, "rouge2_precision": 0.033751098133716816, "rouge2_precision_stderr": 0.0007017585569903578, "rouge2_recall": 0.20045030871386427, "rouge2_recall_stderr": 0.0038136378057587856, "rougeL_fmeasure": 0.10724709950776415, "rougeL_fmeasure_stderr": 0.001385394861578905, "rougeL_precision": 0.06750750522157839, "rougeL_precision_stderr": 0.0010132953538675234, "rougeL_recall": 0.3629468989772955, "rougeL_recall_stderr": 0.004411901125085533, "rougeLsum_fmeasure": 0.10981073422881693, "rougeLsum_fmeasure_stderr": 0.0014263114503938255, "rougeLsum_precision": 0.06905880474217613, "rougeLsum_precision_stderr": 0.001041674323116577, "rougeLsum_recall": 0.37377123464513246, "rougeLsum_recall_stderr": 0.004666454165917922}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.831310525161332, "bleu_stderr": 0.08457373503805206, "rouge1_fmeasure": 0.1862365342289606, "rouge1_fmeasure_stderr": 0.0019333176047893425, "rouge1_precision": 0.15972274079475446, "rouge1_precision_stderr": 0.0019865559238896858, "rouge1_recall": 0.2700593421670508, "rouge1_recall_stderr": 0.0027737951668886907, "rouge2_fmeasure": 0.04032054400755849, "rouge2_fmeasure_stderr": 0.0009252920084472916, "rouge2_precision": 0.034556806570887444, "rouge2_precision_stderr": 0.0008425423478960415, "rouge2_recall": 0.05978905462791134, "rouge2_recall_stderr": 0.0014708640693064097, "rougeL_fmeasure": 0.14210549237770434, "rougeL_fmeasure_stderr": 0.001352102962568602, "rougeL_precision": 0.12038536558218806, "rougeL_precision_stderr": 0.0013551069603724947, "rougeL_recall": 0.21115022540563333, "rougeL_recall_stderr": 0.0022023323083645396, "rougeLsum_fmeasure": 0.17172494748072423, "rougeLsum_fmeasure_stderr": 0.0017652741846676486, "rougeLsum_precision": 0.1471563634835902, "rougeLsum_precision_stderr": 0.001816380499537014, "rougeLsum_recall": 0.24955829066428167, "rougeLsum_recall_stderr": 0.0025549018069577077}}, "1": {"tldr_en": {"bleu": 3.1946229115600104, "bleu_stderr": 0.0902528894135031, "rouge1_fmeasure": 0.22713731519119962, "rouge1_fmeasure_stderr": 0.0020303856541629157, "rouge1_precision": 0.20084840762025002, "rouge1_precision_stderr": 0.002375570727890994, "rouge1_recall": 0.3279331840452314, "rouge1_recall_stderr": 0.0029166900556576378, "rouge2_fmeasure": 0.05813673529140247, "rouge2_fmeasure_stderr": 0.0010858552857269058, "rouge2_precision": 0.05192805744789268, "rouge2_precision_stderr": 0.0011904825748754472, "rouge2_recall": 0.08693391944333162, "rouge2_recall_stderr": 0.0017928197332860247, "rougeL_fmeasure": 0.16290527667884375, "rougeL_fmeasure_stderr": 0.0013800590148163698, "rougeL_precision": 0.1432641278979817, "rougeL_precision_stderr": 0.0016838668333439412, "rougeL_recall": 0.24141036590043435, "rougeL_recall_stderr": 0.002321080600691811, "rougeLsum_fmeasure": 0.21344783101010534, "rougeLsum_fmeasure_stderr": 0.0019004009451698382, "rougeLsum_precision": 0.1885894929526097, "rougeLsum_precision_stderr": 0.0022300914877422806, "rougeLsum_recall": 0.3090983774717522, "rougeLsum_recall_stderr": 0.0027802990042071363}}, "2": {"tldr_en": {"bleu": 4.089342922787345, "bleu_stderr": 0.09294377977855839, "rouge1_fmeasure": 0.24178148334371152, "rouge1_fmeasure_stderr": 0.002084865329415859, "rouge1_precision": 0.2656984608711839, "rouge1_precision_stderr": 0.003475974826636605, "rouge1_recall": 0.3139253119933751, "rouge1_recall_stderr": 0.003012955655711283, "rouge2_fmeasure": 0.06887382606726644, "rouge2_fmeasure_stderr": 0.0012807228279060876, "rouge2_precision": 0.08136466928288727, "rouge2_precision_stderr": 0.0021586497346161937, "rouge2_recall": 0.09042739130647694, "rouge2_recall_stderr": 0.0018404609298964, "rougeL_fmeasure": 0.17903750582234018, "rougeL_fmeasure_stderr": 0.0015877517832273015, "rougeL_precision": 0.20056631932614633, "rougeL_precision_stderr": 0.0029240196408032576, "rougeL_recall": 0.23442772665220632, "rougeL_recall_stderr": 0.002412584818753376, "rougeLsum_fmeasure": 0.22871976277916323, "rougeLsum_fmeasure_stderr": 0.0019660579351207536, "rougeLsum_precision": 0.2521499144307301, "rougeLsum_precision_stderr": 0.0033481985589333117, "rougeLsum_recall": 0.29706441266630634, "rougeLsum_recall_stderr": 0.0028655519018383232}}, "3": {"tldr_en": {"bleu": 4.072610754323664, "bleu_stderr": 0.07525164017980863, "rouge1_fmeasure": 0.19590336767483915, "rouge1_fmeasure_stderr": 0.002603449114946719, "rouge1_precision": 0.25558962697073145, "rouge1_precision_stderr": 0.004282279704468573, "rouge1_recall": 0.23153110943427863, "rouge1_recall_stderr": 0.003438107905334785, "rouge2_fmeasure": 0.05767822682063389, "rouge2_fmeasure_stderr": 0.0013980794793852763, "rouge2_precision": 0.08146818659563723, "rouge2_precision_stderr": 0.002448660534108266, "rouge2_recall": 0.06743455850825143, "rouge2_recall_stderr": 0.0017452087926378838, "rougeL_fmeasure": 0.14912723506935083, "rougeL_fmeasure_stderr": 0.0020363514995009485, "rougeL_precision": 0.19917268042172423, "rougeL_precision_stderr": 0.00359110440185509, "rougeL_recall": 0.17626539265723254, "rougeL_recall_stderr": 0.0027059496141968596, "rougeLsum_fmeasure": 0.18563647374529954, "rougeLsum_fmeasure_stderr": 0.0024816986882333276, "rougeLsum_precision": 0.24272073863797083, "rougeLsum_precision_stderr": 0.004109190949161484, "rougeLsum_recall": 0.2194427111114507, "rougeLsum_recall_stderr": 0.003281194179793178}}, "4": {"tldr_en": {"bleu": 0.30672054851921343, "bleu_stderr": 0.027801502217640873, "rouge1_fmeasure": 0.060859438120474105, "rouge1_fmeasure_stderr": 0.002186962487867776, "rouge1_precision": 0.08272085590013521, "rouge1_precision_stderr": 0.003328470018227569, "rouge1_recall": 0.073607896755553, "rouge1_recall_stderr": 0.002786595724689709, "rouge2_fmeasure": 0.018259934336381307, "rouge2_fmeasure_stderr": 0.0009369665663167178, "rouge2_precision": 0.027384557827759736, "rouge2_precision_stderr": 0.0017208392028580295, "rouge2_recall": 0.021828735652406926, "rouge2_recall_stderr": 0.0011755690210094216, "rougeL_fmeasure": 0.047327721198656594, "rougeL_fmeasure_stderr": 0.001720788977327356, "rougeL_precision": 0.0663593638177798, "rougeL_precision_stderr": 0.002792690105843212, "rougeL_recall": 0.056938933254415285, "rougeL_recall_stderr": 0.0021770204347710985, "rougeLsum_fmeasure": 0.05738648078691023, "rougeLsum_fmeasure_stderr": 0.0020702191744425805, "rougeLsum_precision": 0.0784447476522085, "rougeLsum_precision_stderr": 0.003187161977557443, "rougeLsum_recall": 0.06936769106400163, "rougeLsum_recall_stderr": 0.0026401376140555047}}, "5": {"tldr_en": {"bleu": 1.0767109875104664e-10, "bleu_stderr": 2.7041266760972117e-09, "rouge1_fmeasure": 0.009545168655738663, "rouge1_fmeasure_stderr": 0.0009833205973525279, "rouge1_precision": 0.013957270253644866, "rouge1_precision_stderr": 0.0015489152693527737, "rouge1_recall": 0.010948829734039874, "rouge1_recall_stderr": 0.001189429950745709, "rouge2_fmeasure": 0.003194781805527316, "rouge2_fmeasure_stderr": 0.00046191164979125494, "rouge2_precision": 0.005346599799374829, "rouge2_precision_stderr": 0.000922536579868288, "rouge2_recall": 0.003447960863177172, "rouge2_recall_stderr": 0.0005097345293134105, "rougeL_fmeasure": 0.00771353363185855, "rougeL_fmeasure_stderr": 0.0008078330599179273, "rougeL_precision": 0.011558443617862643, "rougeL_precision_stderr": 0.0013357028661274022, "rougeL_recall": 0.00878713432773727, "rougeL_recall_stderr": 0.0009510460692818358, "rougeLsum_fmeasure": 0.009095278752494966, "rougeLsum_fmeasure_stderr": 0.0009411593635337467, "rougeLsum_precision": 0.013380501718320581, "rougeLsum_precision_stderr": 0.0014992977277420356, "rougeLsum_recall": 0.010421509428125204, "rougeLsum_recall_stderr": 0.0011325542079141924}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 2.1637748729872377, "bleu_stderr": 0.04708061810035152, "rouge1_fmeasure": 0.1857729182904806, "rouge1_fmeasure_stderr": 0.0015977758615005752, "rouge1_precision": 0.17571114021612258, "rouge1_precision_stderr": 0.00234001350004936, "rouge1_recall": 0.2403810966028036, "rouge1_recall_stderr": 0.001917930986446359, "rouge2_fmeasure": 0.038846854218182576, "rouge2_fmeasure_stderr": 0.0008031687884467253, "rouge2_precision": 0.03853560508356721, "rouge2_precision_stderr": 0.0008749576393956302, "rouge2_recall": 0.04848364378645718, "rouge2_recall_stderr": 0.001080661761475741, "rougeL_fmeasure": 0.14517349755186024, "rougeL_fmeasure_stderr": 0.00122530969799679, "rougeL_precision": 0.13673433720639006, "rougeL_precision_stderr": 0.0018383470645185228, "rougeL_recall": 0.19020915483344014, "rougeL_recall_stderr": 0.0015344656813421698, "rougeLsum_fmeasure": 0.17477219266422644, "rougeLsum_fmeasure_stderr": 0.0015733449442962115, "rougeLsum_precision": 0.16441038855158038, "rougeLsum_precision_stderr": 0.00216945133305093, "rougeLsum_recall": 0.22661830578107306, "rougeLsum_recall_stderr": 0.0019584009970905515}}, "1": {"generate_text_restaurant": {"bleu": 12.699076129183206, "bleu_stderr": 0.10399531996709636, "rouge1_fmeasure": 0.46200013120745637, "rouge1_fmeasure_stderr": 0.0023848096470577393, "rouge1_precision": 0.5458616254773436, "rouge1_precision_stderr": 0.0034897518863656377, "rouge1_recall": 0.44911695528747547, "rouge1_recall_stderr": 0.003049432231004983, "rouge2_fmeasure": 0.21840214637971003, "rouge2_fmeasure_stderr": 0.0020520500269639213, "rouge2_precision": 0.2625771628656913, "rouge2_precision_stderr": 0.002777565484439754, "rouge2_recall": 0.21189977549122158, "rouge2_recall_stderr": 0.0022330452298268692, "rougeL_fmeasure": 0.3377881512152975, "rougeL_fmeasure_stderr": 0.0020544234738392457, "rougeL_precision": 0.4020226840139383, "rougeL_precision_stderr": 0.003079117739342717, "rougeL_recall": 0.3281876590745158, "rougeL_recall_stderr": 0.002505390281354571, "rougeLsum_fmeasure": 0.3799905020241611, "rougeLsum_fmeasure_stderr": 0.0023491152850802477, "rougeLsum_precision": 0.45027802951118134, "rougeLsum_precision_stderr": 0.0033307854923309735, "rougeLsum_recall": 0.3687964450646062, "rougeLsum_recall_stderr": 0.002811107425715743}}, "2": {"generate_text_restaurant": {"bleu": 15.349320073567956, "bleu_stderr": 0.20065362471122622, "rouge1_fmeasure": 0.5062690903947293, "rouge1_fmeasure_stderr": 0.0022184418781909503, "rouge1_precision": 0.5641138089260663, "rouge1_precision_stderr": 0.003122162389799746, "rouge1_recall": 0.4993081674056431, "rouge1_recall_stderr": 0.0029190169239720776, "rouge2_fmeasure": 0.25323692889972166, "rouge2_fmeasure_stderr": 0.002116475114261491, "rouge2_precision": 0.28480233937098404, "rouge2_precision_stderr": 0.0026558013765171293, "rouge2_recall": 0.2505303415532217, "rouge2_recall_stderr": 0.002363227578711657, "rougeL_fmeasure": 0.3699075196394537, "rougeL_fmeasure_stderr": 0.002038510745722095, "rougeL_precision": 0.4134223803505085, "rougeL_precision_stderr": 0.0027884299786810726, "rougeL_recall": 0.364967373581058, "rougeL_recall_stderr": 0.0025050008227674118, "rougeLsum_fmeasure": 0.42153114614795945, "rougeLsum_fmeasure_stderr": 0.0022965855563879564, "rougeLsum_precision": 0.4701745407770204, "rougeLsum_precision_stderr": 0.0030588655833951616, "rougeLsum_recall": 0.415665042099645, "rougeLsum_recall_stderr": 0.0027902197560574714}}, "3": {"generate_text_restaurant": {"bleu": 14.321380888062812, "bleu_stderr": 0.13332556788591748, "rouge1_fmeasure": 0.4942167403659075, "rouge1_fmeasure_stderr": 0.0021128256597481797, "rouge1_precision": 0.5163006609255177, "rouge1_precision_stderr": 0.002848705467042193, "rouge1_recall": 0.5103725325478746, "rouge1_recall_stderr": 0.002812023353115975, "rouge2_fmeasure": 0.24523127893147686, "rouge2_fmeasure_stderr": 0.0020480988327082963, "rouge2_precision": 0.2568516782752942, "rouge2_precision_stderr": 0.0023590125409771855, "rouge2_recall": 0.2546224310607835, "rouge2_recall_stderr": 0.0023818244395298806, "rougeL_fmeasure": 0.36209783653768146, "rougeL_fmeasure_stderr": 0.001959264414079404, "rougeL_precision": 0.3787196100484137, "rougeL_precision_stderr": 0.0024985656409790852, "rougeL_recall": 0.3741605928354789, "rougeL_recall_stderr": 0.002454556248255368, "rougeLsum_fmeasure": 0.41228039547049994, "rougeLsum_fmeasure_stderr": 0.002190141578787795, "rougeLsum_precision": 0.4306732810674897, "rougeLsum_precision_stderr": 0.002754882401260447, "rougeLsum_recall": 0.42590630743564917, "rougeLsum_recall_stderr": 0.0027265425997138994}}, "4": {"generate_text_restaurant": {"bleu": 13.722841928196777, "bleu_stderr": 0.13804846172826613, "rouge1_fmeasure": 0.48393429045188835, "rouge1_fmeasure_stderr": 0.0019859645893939115, "rouge1_precision": 0.48828386592969264, "rouge1_precision_stderr": 0.0024858404633992743, "rouge1_recall": 0.5114305264974095, "rouge1_recall_stderr": 0.002697661923152199, "rouge2_fmeasure": 0.23840855028747443, "rouge2_fmeasure_stderr": 0.0019573193912396634, "rouge2_precision": 0.24059108499141613, "rouge2_precision_stderr": 0.00210840059224509, "rouge2_recall": 0.25365084544842664, "rouge2_recall_stderr": 0.0023384488190548417, "rougeL_fmeasure": 0.3537873295650889, "rougeL_fmeasure_stderr": 0.0018387088951343877, "rougeL_precision": 0.3566021510402825, "rougeL_precision_stderr": 0.002136311576118472, "rougeL_recall": 0.3747086531915837, "rougeL_recall_stderr": 0.0023926470384127776, "rougeLsum_fmeasure": 0.4043059323351792, "rougeLsum_fmeasure_stderr": 0.002080752243862837, "rougeLsum_precision": 0.4075869423080161, "rougeLsum_precision_stderr": 0.0024174778601222056, "rougeLsum_recall": 0.4276935666531386, "rougeLsum_recall_stderr": 0.002665628883634715}}, "5": {"generate_text_restaurant": {"bleu": 13.372484418259432, "bleu_stderr": 0.12631428400851766, "rouge1_fmeasure": 0.47859053217432174, "rouge1_fmeasure_stderr": 0.0019398187941902603, "rouge1_precision": 0.47557867752442456, "rouge1_precision_stderr": 0.0023360428027170664, "rouge1_recall": 0.5107946193055894, "rouge1_recall_stderr": 0.002625085316285608, "rouge2_fmeasure": 0.23444687287756075, "rouge2_fmeasure_stderr": 0.001962765988186735, "rouge2_precision": 0.23277405462932813, "rouge2_precision_stderr": 0.00205201253568292, "rouge2_recall": 0.2519154898433275, "rouge2_recall_stderr": 0.0023288239477406566, "rougeL_fmeasure": 0.35043527019394044, "rougeL_fmeasure_stderr": 0.0018309395599414636, "rougeL_precision": 0.3476553000546008, "rougeL_precision_stderr": 0.0020361706787158022, "rougeL_recall": 0.3751201703103127, "rougeL_recall_stderr": 0.002384327433554856, "rougeLsum_fmeasure": 0.4022665348493678, "rougeLsum_fmeasure_stderr": 0.002066528906487744, "rougeLsum_precision": 0.39968395508657584, "rougeLsum_precision_stderr": 0.0023326315704367095, "rougeLsum_recall": 0.42940604077002287, "rougeLsum_recall_stderr": 0.002605951608709431}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.381704327009844, "bleu_stderr": 0.11413286241675519, "rouge1_fmeasure": 0.2252785173179299, "rouge1_fmeasure_stderr": 0.0025302839963541515, "rouge1_precision": 0.16652504564117318, "rouge1_precision_stderr": 0.0020480225617605856, "rouge1_recall": 0.37848923564363685, "rouge1_recall_stderr": 0.0045711110875955915, "rouge2_fmeasure": 0.05560640356600142, "rouge2_fmeasure_stderr": 0.0017257721593849657, "rouge2_precision": 0.04023090834156273, "rouge2_precision_stderr": 0.0012912806060900344, "rouge2_recall": 0.09751455692123925, "rouge2_recall_stderr": 0.003144590481436754, "rougeL_fmeasure": 0.1678662401695973, "rougeL_fmeasure_stderr": 0.0019429705177302374, "rougeL_precision": 0.12391529652302673, "rougeL_precision_stderr": 0.0015698267806295476, "rougeL_recall": 0.28383434867259993, "rougeL_recall_stderr": 0.003658695564054696, "rougeLsum_fmeasure": 0.17781888968117063, "rougeLsum_fmeasure_stderr": 0.0021578317596841075, "rougeLsum_precision": 0.1310543700695647, "rougeLsum_precision_stderr": 0.0017000651189640957, "rougeLsum_recall": 0.30107876434344966, "rougeLsum_recall_stderr": 0.004054884960237835}}, "1": {"article_DOC_summary": {"bleu": 1.9568092253132736, "bleu_stderr": 0.08743638623038145, "rouge1_fmeasure": 0.1938089585188387, "rouge1_fmeasure_stderr": 0.002822597453009016, "rouge1_precision": 0.13823526560660052, "rouge1_precision_stderr": 0.0020944863718590696, "rouge1_recall": 0.33753001607653804, "rouge1_recall_stderr": 0.004807587398146579, "rouge2_fmeasure": 0.04477392420959174, "rouge2_fmeasure_stderr": 0.001637714965321643, "rouge2_precision": 0.03166938333546749, "rouge2_precision_stderr": 0.0011689549810166263, "rouge2_recall": 0.07993218887659431, "rouge2_recall_stderr": 0.0029743255309706987, "rougeL_fmeasure": 0.1491400353009075, "rougeL_fmeasure_stderr": 0.002089252796225244, "rougeL_precision": 0.10613937916799303, "rougeL_precision_stderr": 0.001538610633349276, "rougeL_recall": 0.2616251241654161, "rougeL_recall_stderr": 0.0037053413551593833, "rougeLsum_fmeasure": 0.15494229567861334, "rougeLsum_fmeasure_stderr": 0.002347654380789924, "rougeLsum_precision": 0.11026653419842858, "rougeLsum_precision_stderr": 0.001720420262105802, "rougeLsum_recall": 0.27172748877390046, "rougeLsum_recall_stderr": 0.004162646884513488}}, "2": {"article_DOC_summary": {"bleu": 2.1208498600162966, "bleu_stderr": 0.08489840925537316, "rouge1_fmeasure": 0.20197965634555684, "rouge1_fmeasure_stderr": 0.002690267282815034, "rouge1_precision": 0.14402898776642667, "rouge1_precision_stderr": 0.001998944393289479, "rouge1_recall": 0.351517404045027, "rouge1_recall_stderr": 0.004610583100015181, "rouge2_fmeasure": 0.050742990668066985, "rouge2_fmeasure_stderr": 0.0016773265894277122, "rouge2_precision": 0.035886973035083945, "rouge2_precision_stderr": 0.001190491610976737, "rouge2_recall": 0.09015312700835054, "rouge2_recall_stderr": 0.003061506688050075, "rougeL_fmeasure": 0.15939919631832364, "rougeL_fmeasure_stderr": 0.002118290262084322, "rougeL_precision": 0.11355508618202974, "rougeL_precision_stderr": 0.0015669742839297053, "rougeL_recall": 0.27829233445848645, "rougeL_recall_stderr": 0.0036956919869857914, "rougeLsum_fmeasure": 0.15895119262920798, "rougeLsum_fmeasure_stderr": 0.002273913023033009, "rougeLsum_precision": 0.11304178539172682, "rougeLsum_precision_stderr": 0.0016600760618328486, "rougeLsum_recall": 0.27844833955215303, "rougeLsum_recall_stderr": 0.004022259545774517}}, "3": {"article_DOC_summary": {"bleu": 2.1488883346464993, "bleu_stderr": 0.10061894207225484, "rouge1_fmeasure": 0.19449648740464862, "rouge1_fmeasure_stderr": 0.002859916967955778, "rouge1_precision": 0.14192323740566237, "rouge1_precision_stderr": 0.002270573664293402, "rouge1_recall": 0.3317122838307692, "rouge1_recall_stderr": 0.0048796302898910975, "rouge2_fmeasure": 0.049958285647633605, "rouge2_fmeasure_stderr": 0.0017043147625524138, "rouge2_precision": 0.03602126113927686, "rouge2_precision_stderr": 0.0012539266263007617, "rouge2_recall": 0.0878057273475559, "rouge2_recall_stderr": 0.0030959059452337553, "rougeL_fmeasure": 0.15536673840207987, "rougeL_fmeasure_stderr": 0.0022317734298045364, "rougeL_precision": 0.11305477995205825, "rougeL_precision_stderr": 0.0017434930500077924, "rougeL_recall": 0.2663468354538728, "rougeL_recall_stderr": 0.0039010875469112365, "rougeLsum_fmeasure": 0.15242546645043564, "rougeLsum_fmeasure_stderr": 0.002411210173116271, "rougeLsum_precision": 0.11102920371579805, "rougeLsum_precision_stderr": 0.001876855631693002, "rougeLsum_recall": 0.2613081764654086, "rougeLsum_recall_stderr": 0.004217382008118568}}, "4": {"article_DOC_summary": {"bleu": 1.030072955735859, "bleu_stderr": 0.1448131273948289, "rouge1_fmeasure": 0.053859811302847754, "rouge1_fmeasure_stderr": 0.0029259257948128737, "rouge1_precision": 0.04622581157969239, "rouge1_precision_stderr": 0.002758425516324379, "rouge1_recall": 0.0843663512427161, "rouge1_recall_stderr": 0.004754251649959729, "rouge2_fmeasure": 0.012848562232113562, "rouge2_fmeasure_stderr": 0.0010859365945209303, "rouge2_precision": 0.009725911780399114, "rouge2_precision_stderr": 0.0008407639061619823, "rouge2_recall": 0.021588809000409173, "rouge2_recall_stderr": 0.0018787516143550758, "rougeL_fmeasure": 0.042690265385557376, "rougeL_fmeasure_stderr": 0.0023298094610187006, "rougeL_precision": 0.03656500907804365, "rougeL_precision_stderr": 0.002224872922024987, "rougeL_recall": 0.06728556626210627, "rougeL_recall_stderr": 0.003838297011101563, "rougeLsum_fmeasure": 0.04238885022609439, "rougeLsum_fmeasure_stderr": 0.002344653333666526, "rougeLsum_precision": 0.03647468832987227, "rougeLsum_precision_stderr": 0.0022537297464633585, "rougeLsum_recall": 0.06688889415336839, "rougeLsum_recall_stderr": 0.0038935277003977983}}, "5": {"article_DOC_summary": {"bleu": 1.5116856439856716e-16, "bleu_stderr": 7.251120818898454e-14, "rouge1_fmeasure": 0.0028858004896843946, "rouge1_fmeasure_stderr": 0.0008256676759201416, "rouge1_precision": 0.002521194639962509, "rouge1_precision_stderr": 0.0007796352087425173, "rouge1_recall": 0.004189678674165279, "rouge1_recall_stderr": 0.0012085716148740944, "rouge2_fmeasure": 0.0007107345703701913, "rouge2_fmeasure_stderr": 0.00031220919556434665, "rouge2_precision": 0.0006208832859776256, "rouge2_precision_stderr": 0.00029409209860814094, "rouge2_recall": 0.001041831827070451, "rouge2_recall_stderr": 0.0004529249135232237, "rougeL_fmeasure": 0.0023094434195131235, "rougeL_fmeasure_stderr": 0.0006631782952940002, "rougeL_precision": 0.001959124935014627, "rougeL_precision_stderr": 0.0005749051558534733, "rougeL_recall": 0.003422811625192831, "rougeL_recall_stderr": 0.0010061472311316847, "rougeLsum_fmeasure": 0.0023727145860087903, "rougeLsum_fmeasure_stderr": 0.0006800010549959292, "rougeLsum_precision": 0.0021015099772572314, "rougeLsum_precision_stderr": 0.00067865052077321, "rougeLsum_recall": 0.0034125788706789104, "rougeLsum_recall_stderr": 0.000959892406042587}}}}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..96c2985f4e0d0b1a2dbaea3cf44e4d372f4a771b
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_0.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.332418164076265,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.03696058294042095
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.07190940889482068,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.001455025906136879
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.301390732870209,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.004402601720305443
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.1095978356180801,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0019564248982681257
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.03366735249156069,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0008858326464608315
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.1465983694875745,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.003074755705857914
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.05171405582224464,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0012435373590367134
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.06928463832111945,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.001354402286433117
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.29343421778124684,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.004302109252038838
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.10587809310127003,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.001838006623068389
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.06900976089065335,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0013821359592628988
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.28936351476019084,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.004198483169030062
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.10516308015267403,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0018547700987810625
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 0,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..563ba9c73ae1117cfb1fdbfc5d3bcad6975fbd6f
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_1.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.4396246502267527,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.03794273972678262
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.0739181124020759,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0013418349953620108
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.35963891837485074,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.004935335446807934
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.11510858435008614,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.001829941745508391
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.034943394233011765,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0008228677576697449
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.17989319170126253,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.003650522605621509
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.054655222423642985,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0011574253411672022
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.07022432800426698,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0012223544306487109
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.3398876745824502,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.004493731176695288
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.10946339983990763,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0016790473876574434
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.07093990858477271,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0012725781012108558
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.34408662950943764,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.004619974377582772
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.11046019470928523,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.00173280705768612
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 1,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..267bc8841e691eac6a4aff11ab9c271a24cfa647
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_2.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.47929145559638225,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.013932123962412855
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.07137936932112236,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0011784730418670042
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.3699801668532645,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.004983372147117968
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.11266051583386952,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0016388264831012904
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.03309847277281182,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0007256900997219835
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.18647973916218474,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0037435312434141257
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.05259910261699664,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0010491604565333935
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.06751660699477897,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0011071302423418996
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.3460463516284548,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.0044526867532594374
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.10644239169147508,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0015316327496444973
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.06854436178289768,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.001132855557018181
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.35357532668740393,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.004680159458874175
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.10811495254365688,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0015702834219670347
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 2,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..671bea7265b03f9073ddf4b0ad178fc2caa3ecb6
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_3.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.5254091236383978,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.0272707184705863
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.07190916345114307,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0011342056239523493
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.3796797864121142,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.0049211015597907335
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.1137800918874328,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0015623641314802495
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.03359440011812607,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.000717267417649812
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.19204855728023304,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.003700810575997827
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.053524415343767374,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0010377150477586447
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.06797419059481667,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0010722591518842702
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.3549241769775831,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.0044079173685938056
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.10739509357535582,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0014688768045950926
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.06883524450761919,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0010904375559758742
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.36157753989860286,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.00458238890896547
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.10880190459995145,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0014957717696141243
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 3,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2506312b5c6376abbc90c6e20106118f530373e
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_4.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.5896016424303352,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.04348163762184696
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.07280177888449052,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.001167476102151522
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.38454519285609656,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.004901871012575138
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.1152098647187527,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0015875085813414037
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.03384968429202272,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0007316072980959663
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.19690825980706886,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.003822922236606215
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.05404038379134397,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.001047558823714542
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.06829385238072445,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0010696413261370567
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.3593088405468019,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.004380347845482903
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.10796621981670128,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0014415066070786182
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.06983214496239268,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0011145751003995281
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.3684081584518333,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0046181910041404525
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.11042781164659983,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0015072405756468101
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 4,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..d04ba6428d5d063b9adc0ca608879c85692f1003
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-web_nlg_en_PALM_prompt_5.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.5579849887702564,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.02566777731605262
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.0722244811765284,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0010883491004439172
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.39225252025509727,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.00500239708089686
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.11496348733004745,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0014986246232008803
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.033751098133716816,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0007017585569903578
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.20045030871386427,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0038136378057587856
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.05406065553629826,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.001009602112409382
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.06750750522157839,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0010132953538675234
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.3629468989772955,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.004411901125085533
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.10724709950776415,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.001385394861578905
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.06905880474217613,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.001041674323116577
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.37377123464513246,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.004666454165917922
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.10981073422881693,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0014263114503938255
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 5,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..c116c499bd173322de1ac6d79677f6a1f871b606
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_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": 0.15972274079475446,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0019865559238896858
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.2700593421670508,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.0027737951668886907
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.1862365342289606,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0019333176047893425
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.034556806570887444,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0008425423478960415
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.05978905462791134,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0014708640693064097
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.04032054400755849,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0009252920084472916
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.12038536558218806,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0013551069603724947
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.21115022540563333,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.0022023323083645396
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.14210549237770434,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.001352102962568602
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.1471563634835902,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.001816380499537014
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.24955829066428167,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0025549018069577077
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.17172494748072423,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0017652741846676486
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 1.831310525161332,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.08457373503805206
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 0,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..c1f2e452f2a4a06a749ea531a3a49c694fc740e2
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_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": 0.20084840762025002,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.002375570727890994
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.3279331840452314,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.0029166900556576378
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.22713731519119962,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0020303856541629157
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.05192805744789268,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0011904825748754472
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.08693391944333162,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0017928197332860247
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.05813673529140247,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0010858552857269058
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.1432641278979817,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0016838668333439412
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.24141036590043435,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.002321080600691811
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.16290527667884375,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0013800590148163698
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.1885894929526097,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0022300914877422806
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.3090983774717522,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0027802990042071363
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.21344783101010534,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0019004009451698382
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 3.1946229115600104,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.0902528894135031
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 1,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..f8ff5661a4872a179a849f4aa4806dcf23ffca64
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_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": 0.2656984608711839,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.003475974826636605
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.3139253119933751,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.003012955655711283
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.24178148334371152,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.002084865329415859
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.08136466928288727,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0021586497346161937
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.09042739130647694,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0018404609298964
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.06887382606726644,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0012807228279060876
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.20056631932614633,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0029240196408032576
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.23442772665220632,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.002412584818753376
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.17903750582234018,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0015877517832273015
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.2521499144307301,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0033481985589333117
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.29706441266630634,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0028655519018383232
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.22871976277916323,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0019660579351207536
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 4.089342922787345,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.09294377977855839
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 2,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..55399f8a34df5870a82ce96747af6192ee4e38c5
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_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": 0.25558962697073145,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.004282279704468573
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.23153110943427863,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.003438107905334785
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.19590336767483915,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.002603449114946719
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.08146818659563723,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.002448660534108266
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.06743455850825143,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0017452087926378838
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.05767822682063389,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0013980794793852763
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.19917268042172423,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.00359110440185509
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.17626539265723254,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.0027059496141968596
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.14912723506935083,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0020363514995009485
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.24272073863797083,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.004109190949161484
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.2194427111114507,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.003281194179793178
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.18563647374529954,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0024816986882333276
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 4.072610754323664,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.07525164017980863
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 3,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..61a914125683611ca0c68e162a5910d4dd23130a
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_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": 0.08272085590013521,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.003328470018227569
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.073607896755553,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.002786595724689709
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.060859438120474105,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.002186962487867776
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.027384557827759736,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0017208392028580295
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.021828735652406926,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0011755690210094216
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.018259934336381307,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0009369665663167178
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.0663593638177798,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.002792690105843212
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.056938933254415285,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.0021770204347710985
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.047327721198656594,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.001720788977327356
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.0784447476522085,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.003187161977557443
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.06936769106400163,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0026401376140555047
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.05738648078691023,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0020702191744425805
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 0.30672054851921343,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.027801502217640873
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 4,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_GEM-wiki_lingua_en_tldr_en_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..a798d1d6ce431337b0fca75b96a5e4ce1410260b
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_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": 0.013957270253644866,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0015489152693527737
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.010948829734039874,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.001189429950745709
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.009545168655738663,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0009833205973525279
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.005346599799374829,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.000922536579868288
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.003447960863177172,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0005097345293134105
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.003194781805527316,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.00046191164979125494
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.011558443617862643,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0013357028661274022
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.00878713432773727,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.0009510460692818358
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.00771353363185855,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0008078330599179273
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.013380501718320581,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0014992977277420356
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.010421509428125204,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0011325542079141924
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.009095278752494966,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0009411593635337467
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 1.0767109875104664e-10,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 2.7041266760972117e-09
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 5,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..2a9b9d50762fbd73a8f0b1d647bef34ecd8864c3
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_0.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 2.1637748729872377,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.04708061810035152
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.17571114021612258,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.00234001350004936
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.2403810966028036,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.001917930986446359
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.1857729182904806,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0015977758615005752
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.03853560508356721,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.0008749576393956302
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.04848364378645718,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.001080661761475741
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.038846854218182576,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0008031687884467253
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.13673433720639006,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0018383470645185228
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.19020915483344014,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0015344656813421698
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.14517349755186024,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.00122530969799679
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.16441038855158038,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.00216945133305093
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.22661830578107306,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0019584009970905515
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.17477219266422644,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0015733449442962115
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 0,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..01341e581f1fd40db99ccdc850b42e8ae419be2d
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_1.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 12.699076129183206,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.10399531996709636
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.5458616254773436,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.0034897518863656377
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.44911695528747547,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.003049432231004983
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.46200013120745637,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0023848096470577393
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.2625771628656913,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.002777565484439754
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.21189977549122158,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.0022330452298268692
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.21840214637971003,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0020520500269639213
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.4020226840139383,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.003079117739342717
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.3281876590745158,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.002505390281354571
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.3377881512152975,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0020544234738392457
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.45027802951118134,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0033307854923309735
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.3687964450646062,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.002811107425715743
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.3799905020241611,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0023491152850802477
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 1,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..a04d18b5e49c500cf9314567c3c2e9d912e36583
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_2.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 15.349320073567956,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.20065362471122622
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.5641138089260663,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.003122162389799746
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.4993081674056431,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.0029190169239720776
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.5062690903947293,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0022184418781909503
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.28480233937098404,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.0026558013765171293
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.2505303415532217,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.002363227578711657
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.25323692889972166,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.002116475114261491
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.4134223803505085,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0027884299786810726
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.364967373581058,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0025050008227674118
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.3699075196394537,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.002038510745722095
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.4701745407770204,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0030588655833951616
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.415665042099645,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0027902197560574714
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.42153114614795945,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0022965855563879564
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 2,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..3af43c25b3e0e6990daca76eed55a0e2d5e90084
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_3.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 14.321380888062812,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.13332556788591748
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.5163006609255177,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.002848705467042193
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.5103725325478746,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.002812023353115975
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.4942167403659075,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0021128256597481797
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.2568516782752942,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.0023590125409771855
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.2546224310607835,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.0023818244395298806
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.24523127893147686,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0020480988327082963
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.3787196100484137,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0024985656409790852
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.3741605928354789,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.002454556248255368
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.36209783653768146,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.001959264414079404
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.4306732810674897,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.002754882401260447
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.42590630743564917,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0027265425997138994
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.41228039547049994,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002190141578787795
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 3,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..30d49f1b1340432c64f1e1f943b9c136c8f97dcd
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_4.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 13.722841928196777,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.13804846172826613
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.48828386592969264,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.0024858404633992743
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.5114305264974095,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.002697661923152199
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.48393429045188835,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0019859645893939115
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.24059108499141613,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.00210840059224509
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.25365084544842664,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.0023384488190548417
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.23840855028747443,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0019573193912396634
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.3566021510402825,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.002136311576118472
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.3747086531915837,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0023926470384127776
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.3537873295650889,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0018387088951343877
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.4075869423080161,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0024174778601222056
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.4276935666531386,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.002665628883634715
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.4043059323351792,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002080752243862837
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 4,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..4a3ec0d8a0aabc9056841c9d62a0a39e12337339
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_e2e_nlg_cleaned_generate_text_restaurant_5.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 13.372484418259432,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.12631428400851766
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.47557867752442456,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.0023360428027170664
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.5107946193055894,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.002625085316285608
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.47859053217432174,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0019398187941902603
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.23277405462932813,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.00205201253568292
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.2519154898433275,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.0023288239477406566
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.23444687287756075,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.001962765988186735
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.3476553000546008,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0020361706787158022
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.3751201703103127,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.002384327433554856
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.35043527019394044,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0018309395599414636
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.39968395508657584,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0023326315704367095
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.42940604077002287,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.002605951608709431
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.4022665348493678,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002066528906487744
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 5,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_0.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..3a819fd4d4e6f228fab3072815608ab1ee7b1a7a
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_0.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.16652504564117318,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.0020480225617605856
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.37848923564363685,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.0045711110875955915
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.2252785173179299,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.0025302839963541515
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.04023090834156273,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.0012912806060900344
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.09751455692123925,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.003144590481436754
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.05560640356600142,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.0017257721593849657
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.12391529652302673,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0015698267806295476
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.28383434867259993,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.003658695564054696
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.1678662401695973,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.0019429705177302374
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.1310543700695647,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.0017000651189640957
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.30107876434344966,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.004054884960237835
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.17781888968117063,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.0021578317596841075
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 2.381704327009844,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.11413286241675519
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 0,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_1.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..2df3f38507faa05f35baf103b96c3960f4ebd1ce
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_1.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.13823526560660052,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.0020944863718590696
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.33753001607653804,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.004807587398146579
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.1938089585188387,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.002822597453009016
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.03166938333546749,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.0011689549810166263
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.07993218887659431,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.0029743255309706987
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.04477392420959174,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.001637714965321643
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.10613937916799303,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.001538610633349276
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.2616251241654161,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.0037053413551593833
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.1491400353009075,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.002089252796225244
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.11026653419842858,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.001720420262105802
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.27172748877390046,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.004162646884513488
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.15494229567861334,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.002347654380789924
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 1.9568092253132736,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.08743638623038145
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 1,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_2.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..d9b946755f49398acd87e572c984e255fd7947ee
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_2.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.14402898776642667,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.001998944393289479
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.351517404045027,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.004610583100015181
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.20197965634555684,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.002690267282815034
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.035886973035083945,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.001190491610976737
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.09015312700835054,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.003061506688050075
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.050742990668066985,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.0016773265894277122
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.11355508618202974,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0015669742839297053
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.27829233445848645,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.0036956919869857914
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.15939919631832364,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.002118290262084322
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.11304178539172682,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.0016600760618328486
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.27844833955215303,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.004022259545774517
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.15895119262920798,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.002273913023033009
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 2.1208498600162966,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.08489840925537316
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 2,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_3.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..8b926ecfbd67e1ea051996ac18559fa4fabb398d
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_3.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.14192323740566237,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.002270573664293402
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.3317122838307692,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.0048796302898910975
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.19449648740464862,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.002859916967955778
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.03602126113927686,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.0012539266263007617
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.0878057273475559,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.0030959059452337553
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.049958285647633605,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.0017043147625524138
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.11305477995205825,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0017434930500077924
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.2663468354538728,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.0039010875469112365
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.15536673840207987,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.0022317734298045364
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.11102920371579805,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.001876855631693002
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.2613081764654086,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.004217382008118568
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.15242546645043564,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.002411210173116271
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 2.1488883346464993,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.10061894207225484
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 3,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_4.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..1027042a980a8d7e76139dad491d9e66732d6944
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_4.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.04622581157969239,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.002758425516324379
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.0843663512427161,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.004754251649959729
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.053859811302847754,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.0029259257948128737
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.009725911780399114,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.0008407639061619823
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.021588809000409173,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.0018787516143550758
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.012848562232113562,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.0010859365945209303
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.03656500907804365,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.002224872922024987
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.06728556626210627,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.003838297011101563
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.042690265385557376,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.0023298094610187006
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.03647468832987227,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.0022537297464633585
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.06688889415336839,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.0038935277003977983
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.04238885022609439,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.002344653333666526
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 1.030072955735859,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.1448131273948289
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 4,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_5.json b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..71983015e730a2d49842bf744cd97db4f7e7b3df
--- /dev/null
+++ b/8b7178b178b/evaluation/generation/slim.8b7178b178b_gem_xsum_article_DOC_summary_5.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.002521194639962509,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.0007796352087425173
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.004189678674165279,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.0012085716148740944
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.0028858004896843946,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.0008256676759201416
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.0006208832859776256,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.00029409209860814094
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.001041831827070451,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.0004529249135232237
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.0007107345703701913,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.00031220919556434665
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.001959124935014627,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0005749051558534733
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.003422811625192831,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.0010061472311316847
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.0023094434195131235,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.0006631782952940002
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.0021015099772572314,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.00067865052077321
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.0034125788706789104,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.000959892406042587
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.0023727145860087903,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.0006800010549959292
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 1.5116856439856716e-16,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 7.251120818898454e-14
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-c4-repetitions/8b7178b178b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 5,
+    "batch_size": 4,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/8b7178b178b/evaluation/rankeval/8b7178b178b_0.csv b/8b7178b178b/evaluation/rankeval/8b7178b178b_0.csv
new file mode 100644
index 0000000000000000000000000000000000000000..949a05f8ba74663e5bc1521dadb90035c4419b25
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_0.csv
@@ -0,0 +1,21 @@
+task,metric,value,err,version
+anli_r1,acc,0.339,0.014976758771620342,0
+anli_r2,acc,0.336,0.014944140233795027,0
+anli_r3,acc,0.3458333333333333,0.013736245342311012,0
+arc_challenge,acc,0.31143344709897613,0.013532472099850945,0
+arc_challenge,acc_norm,0.3412969283276451,0.013855831287497719,0
+arc_easy,acc,0.6734006734006734,0.00962304703826764,0
+arc_easy,acc_norm,0.5892255892255892,0.010095101349348653,0
+boolq,acc,0.6351681957186545,0.00841944098496366,1
+cb,acc,0.39285714285714285,0.0658538889806635,1
+cb,f1,0.19047619047619047,,1
+copa,acc,0.82,0.038612291966536955,0
+hellaswag,acc,0.5356502688707429,0.004977081808179436,0
+hellaswag,acc_norm,0.7113124875522804,0.004522262128177007,0
+piqa,acc,0.780739934711643,0.00965335746360531,0
+piqa,acc_norm,0.7894450489662677,0.009512378081238743,0
+rte,acc,0.628158844765343,0.029091018492217447,0
+sciq,acc,0.896,0.009658016218524298,0
+sciq,acc_norm,0.823,0.012075463420375061,0
+storycloze_2016,acc,0.7589524318546232,0.009890946490576938,0
+winogrande,acc,0.648776637726914,0.013415981370545126,0
diff --git a/8b7178b178b/evaluation/rankeval/8b7178b178b_0.json b/8b7178b178b/evaluation/rankeval/8b7178b178b_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff98672fb7cf554caf6fbc928e78a7285500522f
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_0.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.339,
+            "acc_stderr": 0.014976758771620342
+        },
+        "anli_r2": {
+            "acc": 0.336,
+            "acc_stderr": 0.014944140233795027
+        },
+        "anli_r3": {
+            "acc": 0.3458333333333333,
+            "acc_stderr": 0.013736245342311012
+        },
+        "cb": {
+            "acc": 0.39285714285714285,
+            "acc_stderr": 0.0658538889806635,
+            "f1": 0.19047619047619047
+        },
+        "copa": {
+            "acc": 0.82,
+            "acc_stderr": 0.038612291966536955
+        },
+        "hellaswag": {
+            "acc": 0.5356502688707429,
+            "acc_stderr": 0.004977081808179436,
+            "acc_norm": 0.7113124875522804,
+            "acc_norm_stderr": 0.004522262128177007
+        },
+        "rte": {
+            "acc": 0.628158844765343,
+            "acc_stderr": 0.029091018492217447
+        },
+        "winogrande": {
+            "acc": 0.648776637726914,
+            "acc_stderr": 0.013415981370545126
+        },
+        "storycloze_2016": {
+            "acc": 0.7589524318546232,
+            "acc_stderr": 0.009890946490576938
+        },
+        "boolq": {
+            "acc": 0.6351681957186545,
+            "acc_stderr": 0.00841944098496366
+        },
+        "arc_easy": {
+            "acc": 0.6734006734006734,
+            "acc_stderr": 0.00962304703826764,
+            "acc_norm": 0.5892255892255892,
+            "acc_norm_stderr": 0.010095101349348653
+        },
+        "arc_challenge": {
+            "acc": 0.31143344709897613,
+            "acc_stderr": 0.013532472099850945,
+            "acc_norm": 0.3412969283276451,
+            "acc_norm_stderr": 0.013855831287497719
+        },
+        "sciq": {
+            "acc": 0.896,
+            "acc_stderr": 0.009658016218524298,
+            "acc_norm": 0.823,
+            "acc_norm_stderr": 0.012075463420375061
+        },
+        "piqa": {
+            "acc": 0.780739934711643,
+            "acc_stderr": 0.00965335746360531,
+            "acc_norm": 0.7894450489662677,
+            "acc_norm_stderr": 0.009512378081238743
+        }
+    },
+    "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/8b7178b178b/evaluation/rankeval/8b7178b178b_1.csv b/8b7178b178b/evaluation/rankeval/8b7178b178b_1.csv
new file mode 100644
index 0000000000000000000000000000000000000000..09467580693ffd9dbcb0924f2c78b1eacc17826a
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_1.csv
@@ -0,0 +1,21 @@
+task,metric,value,err,version
+anli_r1,acc,0.319,0.014746404865473487,0
+anli_r2,acc,0.331,0.014888272588203931,0
+anli_r3,acc,0.33666666666666667,0.013647602942406387,0
+arc_challenge,acc,0.33361774744027306,0.013778687054176545,0
+arc_challenge,acc_norm,0.34726962457337884,0.01391303452962044,0
+arc_easy,acc,0.6923400673400674,0.009470292575831181,0
+arc_easy,acc_norm,0.6531986531986532,0.009766326091716002,0
+boolq,acc,0.637308868501529,0.008408838061823175,1
+cb,acc,0.4107142857142857,0.0663363415035954,1
+cb,f1,0.22313546423135466,,1
+copa,acc,0.8,0.040201512610368445,0
+hellaswag,acc,0.5329615614419438,0.004978927164792885,0
+hellaswag,acc_norm,0.707329217287393,0.004540586983229989,0
+piqa,acc,0.7834602829162133,0.009609984714384606,0
+piqa,acc_norm,0.7878128400435256,0.009539299828174056,0
+rte,acc,0.5090252707581228,0.030091559826331334,0
+sciq,acc,0.929,0.008125578442487933,0
+sciq,acc_norm,0.922,0.008484573530118588,0
+storycloze_2016,acc,0.7562800641368252,0.009928097887358885,0
+winogrande,acc,0.6227308602999211,0.013622567928799501,0
diff --git a/8b7178b178b/evaluation/rankeval/8b7178b178b_1.json b/8b7178b178b/evaluation/rankeval/8b7178b178b_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..678fd137cf7ee9df10cb5d35e0d3a8e90c382dff
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_1.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.319,
+            "acc_stderr": 0.014746404865473487
+        },
+        "anli_r2": {
+            "acc": 0.331,
+            "acc_stderr": 0.014888272588203931
+        },
+        "anli_r3": {
+            "acc": 0.33666666666666667,
+            "acc_stderr": 0.013647602942406387
+        },
+        "cb": {
+            "acc": 0.4107142857142857,
+            "acc_stderr": 0.0663363415035954,
+            "f1": 0.22313546423135466
+        },
+        "copa": {
+            "acc": 0.8,
+            "acc_stderr": 0.040201512610368445
+        },
+        "hellaswag": {
+            "acc": 0.5329615614419438,
+            "acc_stderr": 0.004978927164792885,
+            "acc_norm": 0.707329217287393,
+            "acc_norm_stderr": 0.004540586983229989
+        },
+        "rte": {
+            "acc": 0.5090252707581228,
+            "acc_stderr": 0.030091559826331334
+        },
+        "winogrande": {
+            "acc": 0.6227308602999211,
+            "acc_stderr": 0.013622567928799501
+        },
+        "storycloze_2016": {
+            "acc": 0.7562800641368252,
+            "acc_stderr": 0.009928097887358885
+        },
+        "boolq": {
+            "acc": 0.637308868501529,
+            "acc_stderr": 0.008408838061823175
+        },
+        "arc_easy": {
+            "acc": 0.6923400673400674,
+            "acc_stderr": 0.009470292575831181,
+            "acc_norm": 0.6531986531986532,
+            "acc_norm_stderr": 0.009766326091716002
+        },
+        "arc_challenge": {
+            "acc": 0.33361774744027306,
+            "acc_stderr": 0.013778687054176545,
+            "acc_norm": 0.34726962457337884,
+            "acc_norm_stderr": 0.01391303452962044
+        },
+        "sciq": {
+            "acc": 0.929,
+            "acc_stderr": 0.008125578442487933,
+            "acc_norm": 0.922,
+            "acc_norm_stderr": 0.008484573530118588
+        },
+        "piqa": {
+            "acc": 0.7834602829162133,
+            "acc_stderr": 0.009609984714384606,
+            "acc_norm": 0.7878128400435256,
+            "acc_norm_stderr": 0.009539299828174056
+        }
+    },
+    "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/8b7178b178b/evaluation/rankeval/8b7178b178b_2.csv b/8b7178b178b/evaluation/rankeval/8b7178b178b_2.csv
new file mode 100644
index 0000000000000000000000000000000000000000..2ea7e569bf184c18c5bc3a76f3935b9114e7dadc
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_2.csv
@@ -0,0 +1,21 @@
+task,metric,value,err,version
+anli_r1,acc,0.304,0.014553205687950436,0
+anli_r2,acc,0.319,0.01474640486547348,0
+anli_r3,acc,0.335,0.013630871843821465,0
+arc_challenge,acc,0.3412969283276451,0.013855831287497719,0
+arc_challenge,acc_norm,0.36006825938566556,0.014027516814585186,0
+arc_easy,acc,0.6898148148148148,0.009491721291998517,0
+arc_easy,acc_norm,0.6734006734006734,0.00962304703826765,0
+boolq,acc,0.637308868501529,0.008408838061823179,1
+cb,acc,0.35714285714285715,0.06460957383809221,1
+cb,f1,0.20317460317460315,,1
+copa,acc,0.84,0.03684529491774709,0
+hellaswag,acc,0.5318661621190998,0.004979637330230314,0
+hellaswag,acc_norm,0.7107149970125473,0.004525037849178835,0
+piqa,acc,0.7763873775843307,0.009721489519176299,0
+piqa,acc_norm,0.7850924918389554,0.009583665082653308,0
+rte,acc,0.5776173285198556,0.02973162264649588,0
+sciq,acc,0.928,0.008178195576218681,0
+sciq,acc_norm,0.921,0.008534156773333463,0
+storycloze_2016,acc,0.757883484767504,0.009905870033193874,0
+winogrande,acc,0.6187845303867403,0.01365017216416031,0
diff --git a/8b7178b178b/evaluation/rankeval/8b7178b178b_2.json b/8b7178b178b/evaluation/rankeval/8b7178b178b_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..58cde41d553a59cef1a714bdfc5bef075b60ebb5
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_2.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.304,
+            "acc_stderr": 0.014553205687950436
+        },
+        "anli_r2": {
+            "acc": 0.319,
+            "acc_stderr": 0.01474640486547348
+        },
+        "anli_r3": {
+            "acc": 0.335,
+            "acc_stderr": 0.013630871843821465
+        },
+        "cb": {
+            "acc": 0.35714285714285715,
+            "acc_stderr": 0.06460957383809221,
+            "f1": 0.20317460317460315
+        },
+        "copa": {
+            "acc": 0.84,
+            "acc_stderr": 0.03684529491774709
+        },
+        "hellaswag": {
+            "acc": 0.5318661621190998,
+            "acc_stderr": 0.004979637330230314,
+            "acc_norm": 0.7107149970125473,
+            "acc_norm_stderr": 0.004525037849178835
+        },
+        "rte": {
+            "acc": 0.5776173285198556,
+            "acc_stderr": 0.02973162264649588
+        },
+        "winogrande": {
+            "acc": 0.6187845303867403,
+            "acc_stderr": 0.01365017216416031
+        },
+        "storycloze_2016": {
+            "acc": 0.757883484767504,
+            "acc_stderr": 0.009905870033193874
+        },
+        "boolq": {
+            "acc": 0.637308868501529,
+            "acc_stderr": 0.008408838061823179
+        },
+        "arc_easy": {
+            "acc": 0.6898148148148148,
+            "acc_stderr": 0.009491721291998517,
+            "acc_norm": 0.6734006734006734,
+            "acc_norm_stderr": 0.00962304703826765
+        },
+        "arc_challenge": {
+            "acc": 0.3412969283276451,
+            "acc_stderr": 0.013855831287497719,
+            "acc_norm": 0.36006825938566556,
+            "acc_norm_stderr": 0.014027516814585186
+        },
+        "sciq": {
+            "acc": 0.928,
+            "acc_stderr": 0.008178195576218681,
+            "acc_norm": 0.921,
+            "acc_norm_stderr": 0.008534156773333463
+        },
+        "piqa": {
+            "acc": 0.7763873775843307,
+            "acc_stderr": 0.009721489519176299,
+            "acc_norm": 0.7850924918389554,
+            "acc_norm_stderr": 0.009583665082653308
+        }
+    },
+    "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/8b7178b178b/evaluation/rankeval/8b7178b178b_3.csv b/8b7178b178b/evaluation/rankeval/8b7178b178b_3.csv
new file mode 100644
index 0000000000000000000000000000000000000000..502d10ab6553a788b273467c9991d6e242e2d70b
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_3.csv
@@ -0,0 +1,21 @@
+task,metric,value,err,version
+anli_r1,acc,0.325,0.014818724459095524,0
+anli_r2,acc,0.337,0.0149550879186536,0
+anli_r3,acc,0.3475,0.013751753243291852,0
+arc_challenge,acc,0.34982935153583616,0.01393680921215828,0
+arc_challenge,acc_norm,0.3626279863481229,0.014049106564955012,0
+arc_easy,acc,0.6893939393939394,0.009495260551195607,0
+arc_easy,acc_norm,0.6721380471380471,0.00963258707617002,0
+boolq,acc,0.6321100917431193,0.008434276591093038,1
+cb,acc,0.4107142857142857,0.06633634150359538,1
+cb,f1,0.3114633159610671,,1
+copa,acc,0.85,0.035887028128263714,0
+hellaswag,acc,0.5340569607647879,0.0049781928934062745,0
+hellaswag,acc_norm,0.7103166699860586,0.00452688302102762,0
+piqa,acc,0.7780195865070729,0.009696120744662026,0
+piqa,acc_norm,0.7878128400435256,0.009539299828174055,0
+rte,acc,0.5415162454873647,0.029992535385373314,0
+sciq,acc,0.934,0.007855297938697589,0
+sciq,acc_norm,0.933,0.007910345983177549,0
+storycloze_2016,acc,0.7659005879208979,0.009791868211495318,0
+winogrande,acc,0.6337805840568271,0.013540144376588896,0
diff --git a/8b7178b178b/evaluation/rankeval/8b7178b178b_3.json b/8b7178b178b/evaluation/rankeval/8b7178b178b_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..d845c38be82fe63322a66b7af94da8bb1c9b748e
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_3.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.325,
+            "acc_stderr": 0.014818724459095524
+        },
+        "anli_r2": {
+            "acc": 0.337,
+            "acc_stderr": 0.0149550879186536
+        },
+        "anli_r3": {
+            "acc": 0.3475,
+            "acc_stderr": 0.013751753243291852
+        },
+        "cb": {
+            "acc": 0.4107142857142857,
+            "acc_stderr": 0.06633634150359538,
+            "f1": 0.3114633159610671
+        },
+        "copa": {
+            "acc": 0.85,
+            "acc_stderr": 0.035887028128263714
+        },
+        "hellaswag": {
+            "acc": 0.5340569607647879,
+            "acc_stderr": 0.0049781928934062745,
+            "acc_norm": 0.7103166699860586,
+            "acc_norm_stderr": 0.00452688302102762
+        },
+        "rte": {
+            "acc": 0.5415162454873647,
+            "acc_stderr": 0.029992535385373314
+        },
+        "winogrande": {
+            "acc": 0.6337805840568271,
+            "acc_stderr": 0.013540144376588896
+        },
+        "storycloze_2016": {
+            "acc": 0.7659005879208979,
+            "acc_stderr": 0.009791868211495318
+        },
+        "boolq": {
+            "acc": 0.6321100917431193,
+            "acc_stderr": 0.008434276591093038
+        },
+        "arc_easy": {
+            "acc": 0.6893939393939394,
+            "acc_stderr": 0.009495260551195607,
+            "acc_norm": 0.6721380471380471,
+            "acc_norm_stderr": 0.00963258707617002
+        },
+        "arc_challenge": {
+            "acc": 0.34982935153583616,
+            "acc_stderr": 0.01393680921215828,
+            "acc_norm": 0.3626279863481229,
+            "acc_norm_stderr": 0.014049106564955012
+        },
+        "sciq": {
+            "acc": 0.934,
+            "acc_stderr": 0.007855297938697589,
+            "acc_norm": 0.933,
+            "acc_norm_stderr": 0.007910345983177549
+        },
+        "piqa": {
+            "acc": 0.7780195865070729,
+            "acc_stderr": 0.009696120744662026,
+            "acc_norm": 0.7878128400435256,
+            "acc_norm_stderr": 0.009539299828174055
+        }
+    },
+    "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/8b7178b178b/evaluation/rankeval/8b7178b178b_4.csv b/8b7178b178b/evaluation/rankeval/8b7178b178b_4.csv
new file mode 100644
index 0000000000000000000000000000000000000000..cc484436d7cf0984ae48a148cfc568a73ace6ef3
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_4.csv
@@ -0,0 +1,21 @@
+task,metric,value,err,version
+anli_r1,acc,0.342,0.01500870618212173,0
+anli_r2,acc,0.323,0.014794927843348642,0
+anli_r3,acc,0.33166666666666667,0.013596836729485163,0
+arc_challenge,acc,0.3583617747440273,0.014012883334859864,0
+arc_challenge,acc_norm,0.3677474402730375,0.01409099561816847,0
+arc_easy,acc,0.6919191919191919,0.009473887075826332,0
+arc_easy,acc_norm,0.6830808080808081,0.009547254611446373,0
+boolq,acc,0.6235474006116208,0.008473882279194586,1
+cb,acc,0.375,0.06527912098338669,1
+cb,f1,0.23907547851209823,,1
+copa,acc,0.86,0.03487350880197772,0
+hellaswag,acc,0.5319657438757219,0.0049795737655758615,0
+hellaswag,acc_norm,0.7148974307906791,0.00450540617660685,0
+piqa,acc,0.7812840043525572,0.009644731932667556,0
+piqa,acc_norm,0.7840043525571273,0.009601236303553544,0
+rte,acc,0.5992779783393501,0.029497229237163143,0
+sciq,acc,0.938,0.007629823996280307,0
+sciq,acc_norm,0.93,0.008072494358323499,0
+storycloze_2016,acc,0.7648316408337787,0.009807347513356905,0
+winogrande,acc,0.6290449881610103,0.013576399902231568,0
diff --git a/8b7178b178b/evaluation/rankeval/8b7178b178b_4.json b/8b7178b178b/evaluation/rankeval/8b7178b178b_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..152b3dcc46c789e413096b8f8440fff1761e6f39
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_4.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.342,
+            "acc_stderr": 0.01500870618212173
+        },
+        "anli_r2": {
+            "acc": 0.323,
+            "acc_stderr": 0.014794927843348642
+        },
+        "anli_r3": {
+            "acc": 0.33166666666666667,
+            "acc_stderr": 0.013596836729485163
+        },
+        "cb": {
+            "acc": 0.375,
+            "acc_stderr": 0.06527912098338669,
+            "f1": 0.23907547851209823
+        },
+        "copa": {
+            "acc": 0.86,
+            "acc_stderr": 0.03487350880197772
+        },
+        "hellaswag": {
+            "acc": 0.5319657438757219,
+            "acc_stderr": 0.0049795737655758615,
+            "acc_norm": 0.7148974307906791,
+            "acc_norm_stderr": 0.00450540617660685
+        },
+        "rte": {
+            "acc": 0.5992779783393501,
+            "acc_stderr": 0.029497229237163143
+        },
+        "winogrande": {
+            "acc": 0.6290449881610103,
+            "acc_stderr": 0.013576399902231568
+        },
+        "storycloze_2016": {
+            "acc": 0.7648316408337787,
+            "acc_stderr": 0.009807347513356905
+        },
+        "boolq": {
+            "acc": 0.6235474006116208,
+            "acc_stderr": 0.008473882279194586
+        },
+        "arc_easy": {
+            "acc": 0.6919191919191919,
+            "acc_stderr": 0.009473887075826332,
+            "acc_norm": 0.6830808080808081,
+            "acc_norm_stderr": 0.009547254611446373
+        },
+        "arc_challenge": {
+            "acc": 0.3583617747440273,
+            "acc_stderr": 0.014012883334859864,
+            "acc_norm": 0.3677474402730375,
+            "acc_norm_stderr": 0.01409099561816847
+        },
+        "sciq": {
+            "acc": 0.938,
+            "acc_stderr": 0.007629823996280307,
+            "acc_norm": 0.93,
+            "acc_norm_stderr": 0.008072494358323499
+        },
+        "piqa": {
+            "acc": 0.7812840043525572,
+            "acc_stderr": 0.009644731932667556,
+            "acc_norm": 0.7840043525571273,
+            "acc_norm_stderr": 0.009601236303553544
+        }
+    },
+    "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/8b7178b178b/evaluation/rankeval/8b7178b178b_5.csv b/8b7178b178b/evaluation/rankeval/8b7178b178b_5.csv
new file mode 100644
index 0000000000000000000000000000000000000000..a9e3dbb39e5ca3e4e3cb1d4ba8ef349713e0c261
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_5.csv
@@ -0,0 +1,21 @@
+task,metric,value,err,version
+anli_r1,acc,0.334,0.014922019523732968,0
+anli_r2,acc,0.339,0.014976758771620344,0
+anli_r3,acc,0.3308333333333333,0.013588208070709006,0
+arc_challenge,acc,0.35494880546075086,0.013983036904094099,0
+arc_challenge,acc_norm,0.36689419795221845,0.014084133118104298,0
+arc_easy,acc,0.6952861952861953,0.009444871667360213,0
+arc_easy,acc_norm,0.6797138047138047,0.009574152668739419,0
+boolq,acc,0.6165137614678899,0.008504304838837023,1
+cb,acc,0.35714285714285715,0.06460957383809221,1
+cb,f1,0.182648401826484,,1
+copa,acc,0.87,0.03379976689896309,0
+hellaswag,acc,0.5327623979286995,0.004979058078478698,0
+hellaswag,acc_norm,0.7144991037641903,0.004507296196227816,0
+piqa,acc,0.7774755168661589,0.009704600975718238,0
+piqa,acc_norm,0.79379760609358,0.009439460331609514,0
+rte,acc,0.5667870036101083,0.029826764082138274,0
+sciq,acc,0.942,0.007395315455792942,0
+sciq,acc_norm,0.934,0.007855297938697596,0
+storycloze_2016,acc,0.7696419027258151,0.009737002698356936,0
+winogrande,acc,0.6345698500394633,0.013533965097638793,0
diff --git a/8b7178b178b/evaluation/rankeval/8b7178b178b_5.json b/8b7178b178b/evaluation/rankeval/8b7178b178b_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..e325b12764519d7a6731348ca3bfc2c033a45846
--- /dev/null
+++ b/8b7178b178b/evaluation/rankeval/8b7178b178b_5.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.334,
+            "acc_stderr": 0.014922019523732968
+        },
+        "anli_r2": {
+            "acc": 0.339,
+            "acc_stderr": 0.014976758771620344
+        },
+        "anli_r3": {
+            "acc": 0.3308333333333333,
+            "acc_stderr": 0.013588208070709006
+        },
+        "cb": {
+            "acc": 0.35714285714285715,
+            "acc_stderr": 0.06460957383809221,
+            "f1": 0.182648401826484
+        },
+        "copa": {
+            "acc": 0.87,
+            "acc_stderr": 0.03379976689896309
+        },
+        "hellaswag": {
+            "acc": 0.5327623979286995,
+            "acc_stderr": 0.004979058078478698,
+            "acc_norm": 0.7144991037641903,
+            "acc_norm_stderr": 0.004507296196227816
+        },
+        "rte": {
+            "acc": 0.5667870036101083,
+            "acc_stderr": 0.029826764082138274
+        },
+        "winogrande": {
+            "acc": 0.6345698500394633,
+            "acc_stderr": 0.013533965097638793
+        },
+        "storycloze_2016": {
+            "acc": 0.7696419027258151,
+            "acc_stderr": 0.009737002698356936
+        },
+        "boolq": {
+            "acc": 0.6165137614678899,
+            "acc_stderr": 0.008504304838837023
+        },
+        "arc_easy": {
+            "acc": 0.6952861952861953,
+            "acc_stderr": 0.009444871667360213,
+            "acc_norm": 0.6797138047138047,
+            "acc_norm_stderr": 0.009574152668739419
+        },
+        "arc_challenge": {
+            "acc": 0.35494880546075086,
+            "acc_stderr": 0.013983036904094099,
+            "acc_norm": 0.36689419795221845,
+            "acc_norm_stderr": 0.014084133118104298
+        },
+        "sciq": {
+            "acc": 0.942,
+            "acc_stderr": 0.007395315455792942,
+            "acc_norm": 0.934,
+            "acc_norm_stderr": 0.007855297938697596
+        },
+        "piqa": {
+            "acc": 0.7774755168661589,
+            "acc_stderr": 0.009704600975718238,
+            "acc_norm": 0.79379760609358,
+            "acc_norm_stderr": 0.009439460331609514
+        }
+    },
+    "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/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4ff8991d6b4f097d3f4f7f94c457458c2ff63200
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a5e974000b11d2a2a9c5bc11a9daf8620d91564725e282a250fcbcd85a6e54
+size 208731415
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6ec448107f6614b74663a02064e9fe593dab5125
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802981c71ae70f000c2dec0505e9bd6f583d89393143b4bacc14a612af53e355
+size 208731415
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f36225b7a6f771c80b93c491ffb1dd2637070f6a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c2030f1e5cd3be574f94102efd56f72e1b9dc7c1f3f818f1c8d27c45db1a83
+size 208732183
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b1938db0eb5a4207995ecd40ecaff3c736215452
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_0_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc70152c28ddf82c8f985b2e7cecc6ae004f4dfe179ed3e447c981f7d4a5853d
+size 208732183
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8003da16b838b3b1f3a7cc7f30eed49b8dc72a1d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727ce01b8db569ce847083f1991cb93dd0361b74e16eb3a66a9f632f91d01903
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..065942e56d90549614988f4dfcd9315ebe1d15f8
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:cb0a86aa7de0f72b7d2b3b88aafbdb32673632302b6a9cbd54d5c3d9c39ccdeb
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b8099b333869ee49adb400c448a09162519ca4ff
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34122129276a9ea18c7cf3667da673e4daa4878cbc6fb43f89dafe24c2e00a0c
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c7d63af4619aa6b6fe1e7520611c396a20610837
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_100_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5030ea431f38372ed898b903e3982ee67d127a3d26f2d006320710bb0b8d62f8
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e4af21e40a72e3ee5976aa540aad8b5a61da7859
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ce783ad1714181aba6ff424faf581800e272cd3bbd32bf928a433dac503ccb99
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6d0813bf9105d7001e457f2683183d5f9cc806a0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80878fa9288418f04cbdb8d53471a72bbb74850d9a3bc15ea3e0662d90f1ab7a
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9675ac2aa5b5f7270486ac808c0d4332c1a14bef
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0a2b2bf8d1283bc36121cf3d0baa9e5e669853e985aa2db08a5831afd4290a
+size 208732077
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..42c2bfe412b14f01ba6d16a8f9c75307b0cc3ffc
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_101_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18d08ee536d8803edca715adbd9584cdd907637f685f658c0e6e03d8eff3fbb
+size 208732077
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..054d6e48641849490af52be21e6e704cdb4d5284
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:f5db07d59b7390ffad1cfef50d524dad4f2905db951e968e185e22383d6bca82
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..40297bc6afdaa6544e0ead663cf102fa645b7ad1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1672668dfe86fa7ff3f882f16c14243f69ccc19f63dddeccb577132601fd65
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d243f8a2a61901e2122d06c97298e7dc654b1339
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a732685330c5fe0080f66c75e0ec3f650aff2d578514da25140f03316792dab1
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..be22d9a621734cc59499de4a36d3392b345956fe
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_102_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d74d84fb23ae6f1bd5a5ffd2699653ec6e1ea22c865c635e3469e4ce526173
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5e7fbea4ae0b2fa8b3657d25a673adfed544b0d6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81016028f1e6e5a2539967cbcdef5d0d280e165b8eea86ea7227a2fa3b169571
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fe643199acd77e64d8a92113f064aca02c7f3af1
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:fbd723e44adc7594d1bd6e5a92a67bd291e17921b507af8d4a707d9ed665ba7a
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3de37556c592a143a3e8960f84e7fc3702b57b4f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a848cd0c4d4523d6f144694bdbdf2f2b199d4784c31a3ebdeff294c3bfafad7f
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7c6c38637a5aa0df19d31de93afd1015eb13f632
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_103_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921fcc995dfb67e064d16347f3d691f27dead2aa2a776a34c918801595f40f6a
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..58b47814fc69c74d0c5d6904af93947f23ede58c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b33d50c9acb142381470db01a65c4f1259a75dee7ac50bbe5a2f55f56a9ae1
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1c62878e76b2a4a6dec927a64445eaae58ce0e1f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97da5b4900df8e398f9e81f39827d33f1e91eb1952a7f8471b465942eda52fc7
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8571241719136dba10e594a31b86e7b7ae3a89b0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb2642e9bf8a596a529b1fc45a2f52e458d5ee3c35ed2b96c08876e34a741f8
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bcb3620f0568d0df89df02c2ea98f9534fd1bba9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_104_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f56d04ee3d48621fbde452cb9f0e6da0ef125ad9a629b46c9f9fcf00e2e875
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5fb20740756210a2dbf25c0a71024a0a880113b6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b68378447d564cb8538169102a141cf694c3d37ab2f28c4a43ac520d0f19ec5
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eef72d3c66317bc4f14cd2610923461b66576823
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e32bd9ff3632bd01939f99f633a63274180e267ab7f6957e971388724ffccb9
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c04849b369602dbf14956c08a29ca59b01cba50a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1718e2fec4589cc513bfdf4c807cd00528fa064a02ba12b80465a52eb82898d0
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c8886269f31309975406eec57eabb59d4eb4ef60
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_105_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e9661c382348450289742eaac1cc056db68b8260a17b17582676ad7d53ea81
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f3987cba923e355204898b0ea9e79485f2371e4e
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:bbf7eeead8f55e8e749618ec9a3843cd3bfa186f2541e3d690ec6868f8fecd6b
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7b5603d7becfc29f88817a8eb6b346fcf9edb05b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6470d382aa84bdbac066e457c57a33469fe1d0e68dac4ad862d39fa45030a69a
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..97e093072355132db757b141b053cb1a0dab38f5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30bd62ca0e7be536ae0066826deee1df57d1425e4b182e1a6d0cde7e8cd042b
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9d069a2c0f43d6043ae3b37bec24d490e4bcaa53
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_106_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f2a2df919b8a06911854fd82301992fe780b4b7c61a2f3cfd070ba5550e509
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8994ff3b2619881cbd53559086a85138e3bfd98b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651cedbd3789f0f42a6fe174342f6410437c7fb35f07575a1b13951f584e9e14
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ffd860cb67c90cb3d0efef2db3bc12fbcc9ad00a
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ed4c5e9f4a0957a5f15fe3df47d41bf7c5d6f4fb5639e751da307af2f501a26b
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..61c5918a2988d778bfea79ba147bca9857419c07
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc23fbb958ab0970cd98c978f22aafa9f8e183cac91ae2965da2c669b49d1a2
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cbe468bb3f09ec559c8b8d47c6abaab8734c21af
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_107_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ab941bd062698f84b27ed8575afbb924d901820380d75c519b5b86a6b85f92
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..21dfcf21621f4a7032418bbb3f22dfddb0843a17
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:f914067689ed054e8b39ab22e2a6adc8b9f656937ed86d5991d9316804103e06
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..24ceb171d1441f21259a1108ae3e63c544095a16
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312b904f07bb0bcf7236ca5f724eb464830612b1f5d1438db529947548da290f
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..314a2fbdbed324e65edeb2b20b3d571afcf9657b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a9a8a3e0fa97469c8b345a64e5f96b7bacec402c9c140e5e01fdcc9180d044
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c11951fb577a14a7442e91d87e83c26cadbcdfea
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_108_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e795ed2b23cc6630c003f40707ae359b5e79f67bd3d9e69633f373ff7fbb5ccc
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c2cbcd8ed8733addbf881574f22dc30a9f066eb8
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:edbea19484203eb3a690cfa7bf1689b00c7e0544aba41fb96dbdeddecbbe975f
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ac32a07fcdc2e0872969e91ba8e0f29281a387a9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9e5123bde208de069bdf94d35d588b584d0b46d67373f9d7e289d4c34fbd74
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4967f77114fe88d15d07fc822eeb9d12cc38940d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b374155222b2b7f53a8b4d548cf59907f873d725c8f7e6ea8d9960ff0aa1d781
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f950c03ddc52c912e47470876af3ac456979e546
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_109_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dabe7295440a996c3b6444f472172a56de6fa252fb5345dd4437f65590222e9
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9128acf349c652ec743f0a849c37a11f57e59e55
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea2cdea48eea1940ee0663a1bb46cadf2a9db25f8b50c431fabaa7323f8c4e8
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..97839181f4af29823cce0c6e03c128b0ece0eab0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e348d2a78369cce9aacc5b6c240d5341cc92f67d6d0be5f94c81af1ea6108d
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3968c1fcbcc00cfc199a3e8c13baff29611fa251
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed85db3cdcf56edf296b6c2b728d02d8b83a7d805c6cb136a9b965da4f33fe34
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f478b10c8a79b054bde06ac9f16b09e950c3a00f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_10_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45ee6fbb299ce32b9e29b3eeb418c816947c32399d7086c4f628850a41c9ebb
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e3bc0764879a17d241f5dd5e41ca7bf4621aab70
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ff8a3720109fe5dddb312fe35cdf55b8a18038056823f70f2679da3c310859c9
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e699d6dee628b41a4b92a3ca5784a58a4c1720ec
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ec6eea4e47ab924744df468da19d637d4d0d700069382681488259b35bef6a36
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..be711fb266e2e9e66625beee1f3ed04f44babb3d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3e9d7ed60a4771f37a89f5e225cb41433a5e83943c0065ff3222e174e96f2e
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8b83848b322e99d8e0c551e44df886d3e5a1150a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_110_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d135aca259b5f6c0a571995f5da0b5de8a4c79fa3bcec07b621ed8bc2e4174
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d2dc1619b389257a9f9e0d10ca68b4c65f8699d2
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c9fe24359495a259dd9ccf467884bdf929ffb64a6d5350e5216ffcf85f8263
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..244cb4d26bdd4f537d88c9fd853be3906b82b4a7
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:dec020efeb9417bffeeea40bf2cef37b8cfa3a7da513100155b7ef4d99d181b8
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eb79fb57eb1960b0790f72315bdf42f283a5c244
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd56f6c60768d90c0493ee53907aaa70d2084433dd6d91847619d19f8df2e3a
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6bb71e6188a635c4d8a0e26cfa8080da4231a7bb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_111_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b6022523bec0de44eb8c93b650832a9c5bf738a2e7b6f5189ef43b6811500f
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c23edeef1fe73f0a3d18188b65537b49a95f5617
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ba0ddf2f1ae7511281573cd4218f8c7137d5faccc6f812afd3c031b8862f16
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eae3f58d547b793e276d73036d85f2bfc702d0e1
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:f708fe60c1820ef2be892dccc958948f27a3d1742fd991943a73cc1c733795b3
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aab0a8ff0c6409ba4f20314d11b972fcaa6bb48c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2864defd4923d006b1a1870c539662688070bb259cd58bd14601d480166027
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..187aa5c7955f07aa9b254a32c37bfb8430dbf078
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_112_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d7957f4fffe32e265bc09c17ee7ab110d7e3cdea803d11de52e7a402d3b99d
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..720f87e1c1230b0ef024d040825b1141cb6813fe
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10206c7482875576932832dad7dc69d43af05bb88672ecf3b50ccabbbf68dca8
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..812b41731c7851655ee0cedd650a73e9459b8805
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c8a61f1b460d2ebb4e8fa3fa88a2aa9069e92357657d711fe676efaf1f760d
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..59b3a56622394f4d874818d84d3da103a8e77486
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f17a1a874fac0bf6ef60b1dea5c67822f1549e23875fafebe7c9ea4cf7a786
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..260cabef346271585197d172351968d27075885c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_113_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29b7529dbcf04c8f27c97290fc7e8444a5fda597052e136830bcea142cc8fe3
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aebf2a587e7fcb6ee53947f630aee76699b705f8
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d10d0d930cc86f38a15c64023bb188b2de7621e5d5de2b83ff302405561f40
+size 208731309
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f6dbca5dbb7c7466f8460a3af790eac74f153ffd
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027492382f8d8d82171fbaa46bffa4fbd41fc91b5959766d5f00092ae58cd829
+size 208731309
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4fcfad5379eab019656b8f1828c604bdbd89c247
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e9edc0707da9f6e1eb74398c7a5a866a39043c579b657c2827a4f5200c7b514
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8b1ce4a3796190c5975d33a1d10fdf7d9522bcd9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_114_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c06d0c407f1a0f8d4e94f519f8a56f8edad740e12ead94e114a228370245520
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..534331aa392e2d04ed2edb2e0edb760ce6c8ecd2
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81cf43782158de8bce2548fd295ab979364f732d7cb568247f8b0ddffa47ddd4
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a5281912cec4b9e3db86dcba07a3009e3018f0f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72022a3e7d5f7418e41022fef28a2cd5080ee9e5a50c14dea04ca165ebf0ef45
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8af9eab8fdebf1f37fe9fc88a4772ccc92b985a2
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a83fc7d5c34f32e1ea8cbe96ec3bf40fc05c74ee7107f5221af1808b0a18ec
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8f556fc20677a9b7575aa3f50ddd6105899c76ce
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_115_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a539b51e6c7a9807a7a36988e7a5db7f83c02f7f8cc964948863d0fbcb113e
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..71c4d995a8ede6cd79d8607256c0688eafb52b27
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e958c0ce9c504ed21be448ce040c57045e80a41c72e512eb9c4bcd1fc7a260a1
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3f0519216e0d16c798cb69f36d2e2e649256c47a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0690078cc5c4aaf659031f5ba802d4ff172439b2b24506978df5df9dfa62fdfa
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..943dcd14f71d83021a252d0ab0ca4a01d46410f5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38628023725cf06efc1a6aecde9b5d37fbda8064f1e656c29b83275d8f0615e0
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6eb82b04d2b5561984f3db6c2368de8be197fc42
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_116_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74861bc8459489111992276486626895b81d3d40f7ca1dbfbc855c2978ad0c7
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b71714cfcf634db4729da1bbed700f221b89140d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7541033ebdd2f1c7c2531061c18eae695587782e9dfbdeb58f35883b1dcacd92
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9dd3cf927e86914f26485c369aa73c3949f3b8c9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a9a99bf7a4f67b113016bc258fa26481b167a26b5dd13199c464ccd34d90eb
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9dabc721df619663e28448647fcf5bef2f510d45
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144be0bc3387ae8e41c6bd57230384db02a14a3bda374970cefdfbac0b7e3946
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..13d271f1a84067c7b44554cd45ccf7696824235b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_117_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eed9817dd3919e4a918e90cff53845dff39fe3339152a6912e3dfcc00464cc8
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aece8d7279232dfff55f71c9ff0053c632b4cebb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0638474e5b992f56efdc7539c012de630d525e6a38721af22da8665c3a862f
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..99162dad8b92d4c541058a98b402d586741d8b31
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6931d2c22896a0528dab6482a4b05ae0b5112107726491bf475efa7a831d26af
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8445b8dcd5b1298fc0d88d327eb95c19787c5706
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb96f1366c469c9b14709ff10eafc1e847a457c1df2f0c79c7ee63b23744200
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a91b482c49130a677225de46daa808fcb629ae34
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_118_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c00ec512149a58e86e8c13e9d7d27030697e03378c137ed05ffa53f3ef3bb6
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7699bd700f5a57edf6c4e15b8efc50b7553365c5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08903630de2354edd8b5d8eac675eebe8e48eeaec6d11d6d787e35582d0d301f
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e3fcdc47296ba9a9bda1afe7a0fbcdc9dbfec0d9
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:f0c8ac38f87dce5ecacc4e281f5dfd88adafff313f8edac0f76aa124f6d0d3d2
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0ca2adc56ec62536ed3798906efc34e1f82f6364
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47b704d0be4029f862243fcab6bc41d7cd9adfed8a1146b5ba06b4151854d9a
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1585805b5f0c36d503ed67a53afbce5d018d63df
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_119_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5888698358f6d415ff015da971d17871d8dc2007ea80715e407d55ddffb5a2
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c2d53bdd742e3ac00b92ae696c75a002622d2831
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5908093b754fba2f5f388479c84f3e1146eb774614b97b74ff9d2bf2176d3160
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..49ee1277da8ca9e9e2939210aa1f43d082eee841
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787f5a664aafd05369b94cae6c4135ff890b6cc0cc87f2a077abd8de8e7622bf
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3d4c8fd6a5ea873d04b637e27c1d17f7d0b29db1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45901719ed33cc6be4670a8ae1a8a86962a17d0066a811b06ee6caadf5ca1065
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..138e1a487320e4afa1e2a94996dbc7bffc0b328f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_11_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3d87b4450d2ef34a3ad76502e4ee1d23fa7483e5e1c3feea597ee969431da4
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..02d7bb72b67bf7c7a803058358f903bf369eef58
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e2af8e72f7c296fe9c34dbc69055be43b81ebee928b43f2af94d35580a04d6ef
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fe611166e0893472363dac71fab61486820cfc47
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097778dcf918d72b58a4a7f9b18c4b287aef02fbd03433c99bd79cb0390b3a26
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6d78b6d8daa5ef9aed7252d2172719398587d932
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2d6f4cef73352ff0018a8694fa1e32f06f4b2f21399ba009498572c47b53e3
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0219631ac89224727bae070a7b1a5b0c7b1f21d0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_120_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7ddd5e2541635b4eda528ac6f50107dc9b814b98d6a44a9be98b6492022f4f
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2728202217464328a08152df15832d6274b025b8
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:dd738a587b3320b2e23f81f4f912e85f3d690e35ca1c0ec2fe989e59e3a4ef35
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0460ef23b77598921c0b1df5873a09a3f6a05bd2
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d279ae9d37ac1c0653e38fa63a65297826c71dc18e344ce20b34025bf6718588
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..705be1a6f7875414ead975509a787c183ee11b78
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454e0bfa36d9c9884cd69255236742c3903adb68503a8a41c6ba8b17aa31193f
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8b66b62ef2cfbf4038ce47bb75d79043204de376
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_121_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41951970afa848c3ca6c7ddce4d32ce9d2ffeb0e20ecdf3840e26b1fd6a138e7
+size 208732205
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9356a01ac054327f289231ddf119b1fd4e3a7609
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71849a88b1414bdd2a419f09d79cc3a664f1721fcd9ff5bedb996c10d958234a
+size 208731309
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..439730cc6c3c7fe557d80a53315c20878ab3356d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6226ab461fd5d0f165a90bfcc0b1bf981be5828d1e1df8d3f74283528377f66c
+size 208731309
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0302bdfbf2f6eb0404bfc5a1755563a713d817a7
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9489ba9bb168ad194fa8cfc4dd5e15b2d5bcd03cb438b66b2cd050d449f7bb80
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a4dab2f403c73df8696f8466a998bbe553f9681f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_122_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b73a95dcba4c2312b46e03ea7aa2a7247a411ba86e28ad9014eb544c85ceb9
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..257b4bd2fc689739e214f064d07c8ba731f6c046
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:dee079dde7f24021e58ea265ef5393789381c674b57ef93a500bfe0dceb70ecf
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a3ba6162eb100b7bcf4e4c4cb6e17438ec73e58a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1807e8af2c23912febcb247834312e671758eb9f42b0bdabe441c06bef5df332
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e5001aed61e380721e8f0169b900654097d55098
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca08855a7bb40d1e3b715486d7420cfa14d0dfa2854e6d2a02015ef4d20cafbb
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e9eda65cb89d759cf3383f6bc46c968c251fe1dc
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_123_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b1d86dd763fbdcee2c6738e0cec7d4b927bd4420ebd64313aa466e2ef208ce
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..060f6c387c1494782099219e35fe63c68ac2442e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22237de355af0957cfb861941995e4c26b637ad81606fdc044f66c19f7188093
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..94beb146d2f4113bec349a29a3e19f62434daa19
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193ee3003dea1d946e71ac01a99441562c196683d0c3b0cb34fff2bb98dd66d5
+size 208731501
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..44a0960ecee4d8177feeaba8f146fa63145ec7f2
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8cc51fb9080167a85f3a9902fe391e6b028fe1dd8d1b6e8a8a7abec2ccea55
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fcd808e92fd20956154141da477d10c0573604da
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_124_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c11580369e405d49091298f0e2ca53003d692e93712114800bde6be8b854970
+size 208732269
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..00ea643f71c2e622b54f1565b15509c47807573b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265d0467abb9616dad10f8839eb2fc672e7899ba410408bc3df429944704a0ff
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ef5fc5bcab74abe8d14967960ea515d31a3ec123
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031749f84bab768dcd20d09e04a3497d2afd748df45eab19fc21fc32535f416d
+size 208731437
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1339b0442f153b25f9630882b34886c0efe7f472
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffbd7b3ccbc961768a2900f6927c5a5465ffe1b145929f4075d94a6e21d27ed9
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f1d96f313b7276fb2a35ebf5fb5205f66c686529
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_125_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fca74041bf95456f31aa1c677e778b5f6208797e99640f4366e06ef7f7c3dec
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8b1543da8a439420e87bd23918f983fdaf6c139f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4efd331d9858ea8449a98f7cde503569faca19eb356b9ae87af39d5adbdf82f0
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f325802b4cc8b6ed0bfc92cff6fbe2cdf3e78838
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b97b20cd28b2b2f9ef73f3043b15f77c520c3ec4347554b8052c1b11031dc353
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2ab2948f67077ab26726984562dd9781eda43e0d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df6671d951df236c6a46ca30645b0069eda77584dd304463985d775305be82e
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1efda3da3b08d46cb9f7cb348e5b091f23f519a7
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_126_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8478a481eff252f60a088c2afcc4d6b0cd7a554392cc7257d09000dd97d2e1c3
+size 208732141
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..069029e9b0c60e553b5360df51f757e7944f4b3d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f19801163287d3c84a0b4a58b7825597b92f323e6f00de01fc52d57fdca932e
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..635e4d52cc25f0c1ce397c48017a2849028bdb35
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ee39536e1d3ba660cc75f3944cbe5d74787192eb6dec2cefb97c994a6fd488bc
+size 208731373
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..22410935671a67cd14e31877dce5e1f384cd6def
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa574578004ad929fca0300817c8255fc1447407921bee3f747047742c7019db
+size 208732077
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b5f078b36a33b6453487ab1b9df9fe3e554ac0e1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_127_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f546ddae3f74eacca30828c1f40fff7f68c0b5354d8e3ced77764af17150d8da
+size 208732077
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a9d08d4f25761b06543d82c59ad2ae189bbfba7f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6bf4a7b3ef146eac1edd3ebf72edb082067f7d311e0ce173cc37e6d845bae4
+size 208731554
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e8886b2919e6873d8873f0babada0d285e3350c1
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:bc2e651a2b3c8aef673aad8eb7d50df68fd7648f2535adee59078a7bb44e6263
+size 208731554
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..82c657ec8f2892ba6c9f57d32087a67a06ffa492
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d84dc46a8bc639f390d6f59ff3659e68fa219a1873527b326f00f174e489e9a
+size 208732322
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bb5e0af555b67954538f3dd7adf362a715ac4301
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_12_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3a45f6a473bae6748f361011fd832fb9a38072a0ec59cf40cd1f05088ae4db
+size 208732322
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..942f40d31d6bd3a317b5fb0fe73b8ec566fd5a9c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:902065a033dcefb423ae40f4ab001b038266fdcb7f2d03ad4fd168ebed2636fc
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1ced8205638e19c4a4bfb6d0f8daa416f613e328
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e36cd4b1fce0be7a3cc8a7ed4817ae90b7b4444f3f25c3b8a4c1ff627ab14a30
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..555717c59ac7da990eac96d44440084abce55f3b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de70489720fe1a412be473636b6308f6cc1a22364397c7ed7057feaca667017a
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6d571519bcfae26bc7f78e6d50980dbc42bd6f78
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_13_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a001a0b58823c7c393ec2a0f269acc281f4cf3559c800657ccd627e3b3e152
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..66cfa837d57de9f3833a43348a78d737bb59936b
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:a2f616d3fa95c49df07df7208a85c11664e21670151f728511adf189d0f8b832
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dd6f690ca911e63bcb23b4468d02c66134b235aa
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:c0c3f13586fef85dc5fe0b0d5fba9f20da76d83e3ca6442ee6edc3840aed7efb
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..faf0ddbeafcacda9b1b8535106d80bcc3ffc7543
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6ed197d3b3681d5c0448d82a215a0f48de1dc74d77d38c9b7c19205844dc86
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7c60e07221c2ddff032c96b94e7a3c117733042f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_14_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92dea53d43047413caa22c9de0899ae44fd78c24de01cbedc359f9731469abf0
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..48dfb0a38b490cd8bcdadf112ebd396fa6224578
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e2cd03960ca9fc981bc512c896a2cecaffa905a6b74c8ff5ccb50931972df6f4
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b5042a2b50a5f89527635f4b56a48abd8097eb5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef23d0f5ba46010666f91f1e527cf7504aebbd0e31dc17757f5e2784e3b9dce
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..20a23326f03434e03aca3c80cdd9071a24189ae9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79201a76acc02f993044f00de1181a97cc8bfaabc4c17f634d4649668c338d6d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fdc170d1339e05887fe2bbd9e01dcdf69f3da3f4
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_15_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10dae3326a124794909e6c286a845d3ba32ce4ffffe643a8c8cb1997fcb73842
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6e0a4f01ee17b34768e210254f1be3e26641588d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d0397d7ab6a5d4340b0bd7ff10ddadf51b4192550e4388a26e66b2d452a750
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f50ab8bfafb0299167345303a0e216e30272efd6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5e35ea1cb617c23a1cdd436d66821b49dde017ed7c0b6bb5ae5da43cd27652
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d21eb6d7aaeb0785c98eb13251f5f0924598a25d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce707a8d722e95783bd427e93f45ade2a03eab98a908603b858853b05c01f502
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8fd5f8254d6e23f576e71c0d417356412f5b9569
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_16_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ab86b6010483ea95a4f84d98e46a358e3f3290226f155029dc8fc92f63c99f
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c0a01a1716d6923255d3e04678a68e13eb3a039f
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:be705594693e54e642db9a0c65fcc5a08dc66e4409f6afa2927c5c587a3f985f
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..070540a61e8dfed68e2534e8118fa99ada344047
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:c3f9d6e504b238cf031bdb1cc53a2169475a56f2750af1649b8cfd84a934fd50
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4b7dd67c7af2b0c0036e2bd3a82b85c03f443995
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d2f30ea8a552c5f64177873ebd24b55225ca86fe022d9fedcaaaa15735df78
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9e0cbce2e177a2c126987751f15a82c30b628563
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_17_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b70ffefd1f4831a26b21cf847c44212f6bad0536b0e82ed5d2a2e7205d558fb
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6d2feb57da7318cf95914c5762aac5e1c93ca054
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:c65d6231821ba7c3eadc381827da9f38a5c4e555a1d96c2485022249553cb33e
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c0bfd50daa86e013961ded329a59c168ed0480d5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552b9c100b2ef763c7d71f0c9a42d9b9b1c0807a7d78daffb8dd316c50792fad
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e72cc97b61062ff91f84bd392de462dedd24dd6d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2e02f4b4af635d1e0ff7a954232971a52ba57b74e2cb4537dbc11b5d4e78a38
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..26591e12b53f51003dd3602a49074c8fbed5c590
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_18_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a689083a2623635a058a5c415f03314022ee95f38ef7e5a6b991eb4bfb16b373
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6c712f1e19bc73282f0cdf316982b1ab105e0c50
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f2ca31c48538bf183d35f96a95104b26036490b08dfb4d6cf289080d804a7c
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7e0217f5cb00d8ffb1beb98998a7d105d109db3e
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:a410a6991605b774089417e3e7b5dd800c39daaf6dd5f5357e3495c92ea0d4b4
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cab17cb68b3f294e802267d65a0d260d728e81a7
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d9f867aef2df1454cab4713efd00ab50685178dfd624c0c67fb49d50dfc6c8
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..788ac47ba23dd9d2528bb49d933fe64f3c5e7097
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_19_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dce871b79625a1cfc489203a47fc4b26f89838df4f4c4d36732017e33a7514
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0e0cabaa9b3bda0512b9918b600a1c7c9565c661
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff1d56b425ba265721ef721346146ecc37484f5493ed6b3d5772859d719b492
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..34f3c8c21affb690a6a41b125a354ad8b69842c8
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d4f7db2e960dd4e961909f38e3444129b37589930a2e0fdc7320b53845d0ef0d
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6094595fb282cf7c4864413e5d1d571227f4f036
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a11c35e13540ce704380de1bfc852cfcb46907e07df5a06924bfa525daa8a1e
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3f6183c6a321b1fd19fbc60d8e5e2edb315cfa87
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_1_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2b59ffa67c55b33a59a89608db9da0be0ec34e0a204d1da72744b1bf65b975
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b1b77f628f13174c4c16446229dcccf6513d90ee
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099209373c3373a3e239de04f1e07d089e839f000521a3c1011bb75c813995b2
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..156ac66107f6a5f5eb5c81ca8844aa610a83e062
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b117a378963353042f6511954593c3bd61c4ab8707c2b5b70bb285bcc30b3312
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7c8d4154d0ad578554a0ea89422ff924ca74c772
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56e1a35e9090af821591818928460592341278188a3d8d3fa30b86e54c622cf
+size 208732322
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c657a4b075572d775cc2a043f21be727ad253ce0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_20_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89c929de295d688eb42f3798f514f8fd31f584f4fa26fef8e3d8a6e12c6a14f
+size 208732322
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a1cf23b0e93e0460c17330f6bf0687aeb180ee05
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7536b5a6756f3cd507df276c9878cdb70e1b219e01b164329e5ceafcc4b4fd13
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8801d7319db207f2a5f9666c462fdaf1cf7eed94
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:accaaf6883b8ee797cd0ecc4d251d8e3c94e9718e9936f689eff66db341ecf39
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ea602a1ee477c7302de679c8487b3b65edd75a50
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75ba5b053928dc4a7ac2fbaeeb282ad73902387e005441d3ac6a9524c3126cf
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0b94a5eea706a06d1e2798ccfebc52d56e04f22e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_21_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9eaaea2e7e78cfe39868baf9eb0201542939e5ecdb0c8017b643820ccdcd06
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..504ac5e9699e2f10fd021a6b13b153fc65b7eb55
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e32bd4e94b66b093019f1de57a81dd79b979a4447cefc300f6217e122c879eb3
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..70ec02e27846a1e5c84c0bf18a79bc1686d93a32
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458ee9b4f4cd17c1d139801fd8a3f66b592b8fafd954765a007d6d721de95092
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a1bbaba2b73cd5752bf90cf34345d0405bf6c82c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3bf8955199661e3be675c0aaf6da66ee6863cc8cf43569e38eadb28e3bdc2d2
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..659e2d7d0ff75c21b076d8bd07650ec83c2f435d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_22_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b889f51553e91c5de772face05d1339e07b81c321ae2c1de8111d05ccda1459
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a390e3d30cc5b7464ed9b40854f7f8de1d3095ba
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960fa78637ce52699dc54b5dd57b1eb813fbbf5da80f6761f13aaff7900b02af
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2cc034ad7b951a3537b7e50c4b0f3ff808ce5154
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d45987e9fe16aca34e310d06041476c510028fce81959cb7813ae8fe459cf157
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8984521b1b92788f21846bf6fef2ed4f5c6aa10d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d88b43b6b83c7a43d68db62e4a905a14132fc7764d24d815ed51f7f68420a01
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cfa458c2a286175c2db804c702e00e8b997862dc
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_23_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc90b5bbac5b47b24289b0dc36a4d685a26bfff2551d25ab41654e7eb8933472
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8752308b7b70cdc43abdd04f0a251bc1fa9262da
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d6e5587c8dca4d1a74b01c7e4db87c64d15d9710b591fbdc395ef42e393f03
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..426264aad1721dd62f4e55f95d6d933023a67a82
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b7626a64a7b64330d4dfeb48948eb3514a8246c3dad23f840865dca20550d382
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cf83ca080ca7fbd916579e109a97c2839d5b41a1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893defa274f38e80a7be60bc9fd21e2b7d52177592e34a3ee254dff825814171
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..101f43f8e02b08fe20967c25d452b0d15d2f2f2c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_24_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a229fbeba0751666d46b587a19ff2d743189317f299863d1c3fa1f0cfa02dd4a
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b19bbc7c393cddb81d62470c6bf17ecf3f8a7bd8
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3ecd81ce8c856f86fc2651b305a307fe1eecc5f03022e7a04c8fd887ab821a
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d76991dd3d40b75a9704094e09a6f29324c89440
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233bbf3c8c781812ad0e4c7a48560229ca8fee6e87b05983690f1d47b301c5a8
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..32abab4e532fdb856a57f2626535d2c42fdeb675
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5086ed77940dbc4175425feff895378039a2a426fefb8bac2e3c5c9f46a29919
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2bd4fc824dc86c3121880720c0ad96c1853ac674
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_25_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa7edd27fc75a2e8f3de26e3ace126f33c1c463ac3117d25fccd0b28663c84b
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8d62db3d4f5c1976b97be21a7b74cd9beacb83a6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4fd1caf552fe33e211b5918f7ca502aaf1c9806240a448d4b25e3627b56fe7
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a0a8543115f33721dfa8113d71c551bd9251bf62
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce7968af8d2748b72085807da08593ccb8234a100e63c8dd5202abf18c603d4
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..485cea425cbcd13bae5756903b1c3056f722dfea
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f21e8593a520f07c5b8582cc1b76788ee2f3d3a62b7b2687190bc57cdec00f
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..70022251334e09ecade509a37cdad23e81aa901a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_26_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb39f433c54b897e2281e45f3cf02a1965ca3992f4c4121ba23e7168aa34fe30
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5c21fabed541880e5afdeb311d53606fb9242cc9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc7498a1b4a913a58476e064dec74fb5ee54cb8126926db5824d6ea6b3035bc
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bae7fb92149cbcc4100838d990d8cb86d41aa106
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f6ca07b91013e6ed623958c45663b5ec2f1b9c81399ec3be91837931a51600
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..157bf0243d1b5180ef2460a682d3edffd5a59009
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8858b999543fb0da92469798b0b26557d660e99b64e71ce85f29ca64e3845087
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..47f21c3632ee0f1b2ec3682b84366b87b8336733
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_27_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75194e3b8e41450e9f8535d52899d1e0e03e05a46774b8dbd31713fb41c652a8
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..40bc58983ed34e56a18f31947363c10d1302fac1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ec6c2561f3f4c8090b1b7c46dc0727ed7816b6f97509f65a6472fcd29fd344
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6fda21ba467bbc27c3961a9a5a5a6b9999832d27
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7e8d61baa046a26ac943997fd1590cd42978c091961db142de8bb5241e836f
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bf8794b42f725a38d391f32e01713cab1c587737
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1713b315f0c75b3701fd9eca8c81508e07cef3181e5d429030bfecfd69b4235c
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..21fd18549633507de8f1263e4e41ffc21f1c34dd
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_28_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72b84a0a8f6cee1d56969581b7b3951fc47996dd31a379a6462be5d9f52e028
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..da733bba5b02a20f37792fe7a0af1dabf4b351cf
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a704c9dab7860343ec763a2b480dd7f3b84fa92b5aea37463c1240be8a64c6
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..68fc3f6d92d3a9c1b62675f48d07beee5f50cef2
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ea054bc361592458c35bbdf398ae47828e08c794712f04974dc082df095a4a66
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..82890695246a488a2f7ff414d1ffa64e1be34165
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d66d680db9754edac2a43856d444a40015cf5346f623962976a50d422715e6
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e8f48ed1fec65e0e24acd6ae94857dbf03291b6f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_29_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d8e3bde827f6aac7acb643cf5fbb50a5d8540b0cd72147ca6c953ea53184cb
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..541a7666c15f45b595b324b7143b8e019ccfe938
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee2489c6b4b78e4ec8493de3d8da8678e064745600d4ce3381eb01c24308871
+size 208731415
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b014444649280a455193de68d9ed1350072f2333
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61aadd67f0abe4d778c87374c70153ba0df476b6365d5713c9e2a9595caa4b70
+size 208731415
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f97d788bc82edc478a85308c1a917dd59affad03
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95ffcf37c57912888f053c78624b588de89a7576c54c7be2836d8f9bb3607e2
+size 208732183
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..89d1c2e36ca8176caf306057fd05ed11d99f26eb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_2_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4b977973b98fda2437233f8abacb99ac0067cb1d88bf70f0adca3baca233d6
+size 208732183
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a747b26de4ca1ea4d78575c6eda142310ecdb48e
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:f1342037bd7220f06979bbef3e58b3716ed54499804608e3bc87dda99e77af8f
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..51bbef59bcbeab1b9cafe52b599ca75408411b90
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:cf6ab11a34e3c20a611051a2137c7619ac68d57231029414d4ed5b3115f942de
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ef3d9ad9198df93b9234a2bea66788da9c3fdb12
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86b8c5cf14eb18f4b3b6635daab33ab9076042e44543a1beb78f99b6bcccbb0
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6fffeb4b4e194b034c5131e2f4c98d0c04d8644c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_30_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad7c982334d030acb4b19325b6987c2490a17d6179a45b25e8f6743d8e244ff
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..902ea325366d046a3b400b15aa87951b14713beb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6625167df175b85fa1c3152c45ba9d895362672b4405d17ecef5a73481a8f767
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0022ab10f40a1cd56ce72f7b3b05e84c1f0b74dd
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b9c11cf915c3e1361663a8b857db19d181e143f7b9edfba0610d293bceb643
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8b55e07260b98c9e435911f7b7c4a84f00afa5ef
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84cdbf4e8789189b549f0f0794b783d6acecbf5e723a2b0b25cb33710cf7c6b6
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a711a63bbb5bbc3ea334bfdb30a054971a72002
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_31_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978f686529f758bd66795d7b4b2b92e7bdcb777b3359bd1ab5288e7ba079d511
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3d2c2db7e477db0613b83d72eda286d35d5eccb3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b264c83f9d0434786cd28faf2865959c834d890173fd4c3091f177bfcd6df8
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5bbb6397bbab22fd2d7b3c8aaea54e861d4aea17
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:c50cb409ec80c08be67727e85b36ac5f07dd3dcc4bb42056a5053a3395790266
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c88d19141016311cba76ffb50bb3cc9641278e38
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4e16e849e81602f4658d04c7e711e2b80d1408f60ca66724e92471a1010574
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eccfa2ecd8954d176bbbfbfdb89f77a09ad16014
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_32_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2865fd2cf388397fb5c4ddc1d22e9bcf08117446f2d1bee981b447b6039029fc
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b738f7d13513b30d2d00ee7603435b962f676fc
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87815d0e0de79dde145a32b0ba699b9241afe7fdc8fb72155379726c149d4307
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c85aade4827d665a2a6b9af07af6091683bf7dab
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e267592ae6c3690081bf1cdd8586dd2af621391fd652070ed03604923332f11d
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..be64ea7a2fee710c808a41d711d1a119bef91ffe
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d203a079c13442bdf802e7fe4f1469ffa6bf2d569ebb1608a55bae511fe0e186
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2463565310d7f68554622ec5fab40c479631d74b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_33_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879e659f1d57fc2ef8e53dc0a6e28d60a2e7dd599df70e48ebad0eeb0399bfd3
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1aa5635fcdab0533d0bd60b9da5b8f6b8240b8b6
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d00faa71bef9076be811126909c4a3f8bb10c180dd0a91925a42a856568c0bec
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7179eda5d6df81d6a5242be7843fad1de482451b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3e8b27c0c5a24fe3617dfc25ddb2381fc6aead72ff58787e7197d7edad42e5
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6d663c93213b7d24fd67d6cd53f02df74034689a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a50c8b9a4661826ff89b967b1369065479f380521ba9975bec640c9e2519d6
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f9b93516a518bfaa3a51f8395d4d090aa2b3883c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_34_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71123de67a0804161e91bbb7762a0fc1b02126a0622aef567e8d28710829d43a
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a5b79035935acdb4dc8c9d47caf90c01c46bef30
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fceeb648e7dbc9baf7950552f14c20612ed6fd85dc1406e0cc32ec44efab9d
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..64cce375fad2f06674321acef9d517bebed510d9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25187fe426d91e4b70891396264756051e7fb0bf2ebfa90214d9ed87aa9f3c3b
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f1eaab220f0f34a17bc7a045329c81c749aecbb5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c778a87dfa838c00a4a7d314f9cb7f7a3a4f5c76a8473fba19e03dcdc1a0a203
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f6cc00b1d45ca26e57f919ba3bdfac6188071f65
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_35_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef901c9c841403b0f4b516396d8d255e1dbe4103b88c892a8d41ab9f651c780
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b59ac4c33d8c1674eb22d8d0d150218456f2acc0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b6e6484f25c58321089f322992e223ab9c32ba571431a23505645cadc99793
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0fb0caa4f5a43371513a5e1cfcd68aac280b1585
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fe0c8304fa879787a7bee760b716f9829e16a1462c554e8e9655e476efad34
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cc5807efd96af780c502f133ee906e84cdf266c3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d67beb0e60722be3b4ee3f149bd8d64a9cd1d38158dc508a49d0a24cdcdf33
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..24f3f3f88339e1a6254ea2f8cab27cad5ee60b74
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_36_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0d35d69136270c9cfd01fdd0782f5a88c6678aeab90e308a4a4a5ff85c2639
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d8dfe8cea43549d548555edbf64a807a65ee2ef4
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286d7a7d563df7760dd639b636a598f0846aa849a08724e7bb6dc31ba60d1521
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e7ae5ed34f8e5232c3aa1439034d3a739ff0f326
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37afa2136278ff607ffe46a07469f5ab5cf88d7d8c457cae8e4f7ba583fa2e03
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..93482b45f74fa46316cba62d33f50e7a527fa198
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965566bcd8c930a7b04bb26d0c293116a626b85cb9df171b936a43819dfbf02d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b4ec504d0b781dc0ea1c46b0c7940a067fbe949e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_37_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a4217bf132b4851951ec9ac73293a8fd66ca7e62a13ebdd22e13a93efb19e3
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..229ecd07407c23fb448f51fbff720283ac4b5935
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ed73612690102195cda1bdfc5d15f85344fce0fced72142461a08631cbf6e6
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8582933ee1b019dec4cf16f18c42fc1936f38bd3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6d8904abb60f6ca12f4cb0ca3532018a97e71e67e6992e367f522473817400
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d0c4f3143324b60368d6d213c196d5b109774911
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d16901f787b6102c53c44b2ccb3a3c5541aac256fac2242f326d59f7cdb08a
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c6acf903e2593701ca38c70e5372abb1894991fa
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_38_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b5c61fe7543346c9cbb444417cb1ff9e2801004f0eb136d08e5a6c2a4fbedc
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5187d02db36c3b4026692976c768d1087acaa516
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:cc7fb5cdd9d8b8469791c536b49bcf7774f7cfa5b20ed631a0cb6b25b84b1cd3
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8e12d358d79c133ab5e0630b8d31ace0c0addaaf
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9b1f31d1a94561cbf03c8904098620cbf28e0ea722f39235d01e159cd186b4
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7f0790e0da555d6859c07bb9ac4e9d7b4a953107
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b1c24c894c8538f457e60eeb989396491adbc04ee6e3bc1060d2e3d3b33d71
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..adfe7144fbdab92df66346c0ee84249d6e24793e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_39_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308d3753720b52a9e07593682a2e0def850dca93fd3f506c4e0741aac3560c5b
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dfc99d9d63723df55154c3ff40750f5d2c0edabf
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ca4a65ad35a7e32a8f2a8ae23a4f415fb4da8170a7983048d8e8610c7483db42
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7f7d7115785aae924fc39837dd85d5e1aea97822
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2379831ddc91e040f16dcee202df53a046da1427ddd768a83982cf62483e1d46
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f4fe908f8035c29e153a6b72af969f9f92fe69eb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7dad19589c13ce338469ad644aa2f545c785a1c1ee880e2a2616b7b9d5cea6
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7cd750d653a3cb6efb51000e08538b58a9d0f793
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_3_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:033a8eab1230e61ba5c575d1e3c6702bf1e07be9b784b3055a518e24e1960344
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..64a67bb706ede0d17b9bb4f0d6bbaf3dfad9af28
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da671eb95c103780ebfbb567dddfffaf8ca156c04ff77cd82496b8840539895
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b525c0d2149bd5cb5c98bafc8fe27032a21dc462
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d1925d1a89a183822c99776f37d5773c6b9abdbb798f2d018cd7bf6fe5491aa1
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b81d9b4abf97a9f7a99f1c72e278df3b76c9e2dd
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d9b7c7de4aa6929601a768c4420fa58c60fc58726528f679e571941275aa19
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3adf33844a750a4dd25d4e33228ea5cf71305b48
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_40_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a148a8154ddce810babe2d34ead237ab21cc07c9f23242324bb64c50e45ccca6
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..349a4d34b39c13255a4e0b6fce351b43b1891a9f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2886b06cb1bf9436aeaad96f341b5776903b20228ccbd98cc6e3a51898356207
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e4348b004966b9eb5d13407ab35b3cf4a23d39ee
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d43d3bec5d29aa7662b66e6feb6cf22a9398ce5805dc647128e347d5eda2ac
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..73706c547f4bf179f5faf430ee72887fb51cb191
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f101046f240ad61064d15f2fc6a5821ca35dfa37e718049683d7739cb33b49d
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..10c3170af510a61b724f1849de3373d4a90ea402
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_41_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b513acb9e768b024b2abaa6780aaafc86bfb44ff69210f834e5e11f177c3cd
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f03457c36407ffca51bd876503e6e9026de0682
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ba6b7f0913c0e05d5f68ae8127510de9ac4208716d78593d64422673416030a3
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..21cef05d7b869f50e0d225c9674c4f1dc1f09040
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d02b313bce9d0b19e2f27a9db62043ea85eaa02b5463a84f1981fe21bba704e
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2bc0220b00aa62abab610c46519f55d60ba188e9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764bf058581b3bcd17cab074f3ad93739ffd09b9202af61bad3c3b1712973f0c
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7e99babd8c05de739580eb393489a27c01290fc6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_42_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aef16cf734fe6966ee42e38b1bc26f32d092aba358338566db2d82e81827c69
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bb56e4e373239c0761c83b645c0948b03446b2b6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87999eb0191531045a2b857e9501ec637c2da5cbab191c882664e418734632ec
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..da584257cb977d90442364c9f18f84b4ebc99b01
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c4a4922cc87ebe2dba6b1cbd4a0d3afc4846aca2f9657e91cc256d3a21b3c4
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bc5e603635614518af79f93cc81496e0d508a808
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8336c02998b9ea0b1d5ee92966ba6e3a55cf67187da1e04dc73d14609620f866
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3db829b6ea2972f9ee127693e08f79543a3074a6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_43_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d745a98e76b16b8f3e04e77039e9651a979118113e549c91045ee788c24e84f9
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c38953b551ec7f2db7354244246d77773e74b006
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b66495383ccd56acf6151f04f3639ad452f093e88c30a6917270f78c319e93
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..85b91fda0fca6736a47ab9b42e455fffcbb992d6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f393978e5cedc83b400c2eac1b3f3610433fa2fde81be2390388bba34f531e
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6a1cb5c69457c802debe010722e60371178850f9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55ee63aca50652d043ff6dbbd6bbab1de5d6432217e38dfbde8d87fd8f8a286
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ec4b58ab1f7afd39ebea06380372cc87686819b4
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_44_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed72c1c2f70240382ef0ba19cba896ea0fea3239a1eefecf78d5d5e61754c82
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c98235da93fdfbf09b31970a313a7f8e5813319a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8628b152db1eae812e0594cf07cb15ad5c678465507ba0ab33bd39e4dfc768
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b01c13cb702a8a4fe13f31e7066e52f4b30baa32
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:fb7290cf80f9278ac0f59dca9216f070b5f424cdf7e0754c5946eba88caca7a1
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3ccfc768f88b31e731dfa5c42aeea4f38a92c11c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3665da8d17afb3805a28abc3ac82988ea9408730da8486dda4ad8f07bfa40a
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..37597a4ad3a5e674943555310e54bccbf4e04627
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_45_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f1f1907f530e2232b283226e608b5a1c0d0edef6c2e01ea32ab099dfb5967c
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b6486dffe494444973f16ee197068370ba16e8f3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5678b534855b37d06a4a3cd75e597d31fcbaec39263c6cd04544f050ecee0b
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2efabe659df9c7f6e97080c1647a271b7f945c1b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97babf93dd397fe62839185f75ad93d8e23fc4bea639a501e1313ed5807c32b9
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..49f6f00d142d272831f86cc942c33ff2a2a02788
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3111d603435255d7631aa574718a8d48e10857bccaacd53a1e035e2653ebf5
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9379c3dc004e26d8360587496fd3e8afaf636a5e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_46_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc7506d674584321d196c1bab2c4a5325dca3f6cdade029823e8374eaa9996e
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..31aedf6101d04aa4717162cc261a25ef42758a01
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6acbfc70e74067038b9fae18ca3fc50a80404562bdac26a0ccacbd246d3df60e
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5da8cdba36376342b5b15638aa52a1229a9458f0
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b35bc7594987a2825ae28b1775cbd9e4aee37b7ca791300b8c07edc74e964514
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a2c5a3ecb51a7e042708bc8d65a65818589135b3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb78b5b47a41d83198978e6b7d2c983855e9936c21ed444315ba6c96fef190f0
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3b8d6886528d107f587975cbfc94645a1e78a46b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_47_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d9dd0c502bc41e36d1e620398f9af1c6816232dc7e6ddf6d9510fbc9d51385d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..afecf5e39b057d75f89fb8342e6f0000c66fd44a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8511189adddab9fb9de133570466a03ad1b53aaeb55a93193178d8d26be27cf2
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b25eced298ba2076a81a71517df37be8c2f8e4c
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d97bb135f99a7e8b54a50bb0aaf36adf630fc02c13cf272554ec50e2e98efcd0
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0d25c0486688f1b70d9434876e7db77f64e69210
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69827ea2358cf429debd05b9c9e29b62453ed60f60f2ae30a4810014268cb347
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6c834e260455fc0d8fd6ce1133cd0f278f2e40a4
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_48_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d70c05792ff2b4637d926b09526c84f6a7018b432898c66a54c0556f86ff0d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f43181641736f7685f3efc40803cf54157a311cf
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:c99369338d74a2986db2feeecb6040e8aa1ab71ede97e0c87327345c3c5deecd
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..93d1380cddd784a1c40ef042f57cb22942c08c4c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94fc77cafa802e74afd79cd9a4e66ecba91e1e4b4fc31f6656ffe035a2fd2a50
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dff20e3fe720321f4f8898ada6975a55dcb374c9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802905227a155159138b23631f5a50b5fae5d0dd14b1a2e32cd4d702cca7eb65
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..343f4896863729a9d6a9fa0b9554510cddf9ad2f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_49_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9316794e360b35a1828ec0a362dbef2e58305a78d6035ba5d0a0844bd4acb7
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4ef9e88fbd158369adace61800454f5cd26cb095
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:c63cf78d063d26482929d6906fd9cbc4fa9bf2c617c4f5d7e9d10d14b0b43db1
+size 208731415
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aad03dc31d67576f7a9fdf05c68dd74a66f10c4b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3581b43740557ad4bf7b41dd0092863783b3e43ca2b263db5c86226822853b
+size 208731415
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b3cc56f7610c04977909ae7e04c5fe50d6f72ed0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314a7c7418fe902dc6345e38ba1b44ac67b77e9899b332db0bfef1ae3a2aaf63
+size 208732183
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..81c1a66607941086d8f6a30f32dacf27ebd2fbbf
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_4_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:302d9932481b6dbd43c504de989bd93bd3e007f301d84bb43c31f760bd816af3
+size 208732183
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4f4f306a936689a431eccf67b74a5d6b0873e0af
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0261e657d1035d3604a92940d60f48d7f3ea2628054964e3601cfcc1a044d07f
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..06f408f2e5c9e936e8d01ced5e405254a8059f38
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d7fc2524ea1e60038b3bf8764dc23ad7f0a364e6531c348b763927387f4b454c
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f9f3b818a9eaf0f9b83db30160309821a5f0b3d1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a08409808cd0dc8dc808b6669e202aa0767b2265f167c75ae7c6966218e4eb
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7939f82fa09a53eda1d99b6a3e2848f4420a3ba8
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_50_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325a885102b45830d776bf6f699817657a5c11d1c98b0d0027d2c85837115432
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..daf1b7cdb3f68ed19608dbaa83d270d02c851e11
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a9af2d7fc13174f9f059862a4d1ff57847ea8e4a71579fb7f8c3b817d65ef1
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6f3b3440f2234bcc97bde35d99510e0eb8092630
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7156a41714c73f49f39be6307eb78ddadcac2a04f2964368700cd9ab584210d6
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6a7f6ee74d8670ebb55bff83687ae1337f964730
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54ddf1a13a17d508fd9e11176015509581d7f8034303af521dac3fda448bfaf
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7982f8719be67c671dd92b02818fd8d08e969468
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_51_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233b4c2962210e9ab61719e004306563842689750b9b2722d006a1ec225a446d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..78c5d012c6c572d84894577e5c749152d6a28ca3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646c230d5dedf211fcf376074c520f086938efec9084299a33e4eb88034e0b9b
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ea6867aedf2476d676a1fc0815227a301e909f3d
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:afc03b015612f8fa7437c7b8539655f80fad0720df59b1ca84b788a4cf4e782e
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..249de0415e5a75b33d00c55608ec479c648489b0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fd148c50889427bdc5efc16e8aedcecab2448a839b648708afc41c6043fcbb
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..564052ce85ac12b84de12782a120385e96bba6d8
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_52_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ec1e97029376568e54bd72818aa64be63ca0b8976a147561050db18350e5c4
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4df4ad71e48cdcc4d375c0e262d255b8452e4d81
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e418bb50f6e20dfdc50ecfd68f6c37f9fd7395306dd8aedc2079af8caab0f9b
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d8a243ff51bd4f9ba488538c9455821122190765
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ee12ec86a895e3b10f939148ace83edd5fe12d2ec49dc03f786adf1911656908
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a4329b60f8d49f5106d9cf98e5864feb1e2342dc
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38353274ba5743fc3a311e8cb7c614bdad94aa8761b803be64de0deb3fdb7ff0
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..39eca0b3bb45d1166b291c0123f7f0305d05f59c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_53_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7cc855b716496848d308c88e097301f37b1657999773ee667c74db2a3a0c7f
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..165c3d62c9fed570eab9be1a1a4ffbe07610f8fb
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e303685f1be872c75f531949caa677bebbf1329cd84f62b3a85dd98e9dde85aa
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7e57ad71d9ee3c1d283dac49168fdf0f6355f543
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611353caddbdc313d532d080f0b9b7aa3fb032ac0fb9634c099f905c94c0b69f
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..244287542486072f4b2482a745d1553aada55c94
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed2ed9b48c802be102d4c7ac5115e2a3fad8538f2a752b4522873ae9a8b7e7b
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..03af69ebec32386ce55f5ba0361104cbe57d7ce0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_54_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f661110ae6dd916ac7f80a16324953cbc5febeb1ea3ef59bfc49b40e7db2ae97
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dabe40ad97b7bbcb554a9ae192292d41e2d6ad49
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b05ffb5f14b56c0dab85fc362e17b9c4fb7945f8e6c7e1ee559a483f80776b17
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ca48dbf5d876d42461bf113b2a90f8390f25c182
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ef9055dd8c4834d8c5c7d77730c346f183d84a263b0f8580f1fd3a610cd8e5bd
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3b7ead32bbd86662274657bd357d884c48010710
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc2c7e1589d987de217f495547915674918525664feff9ab8f7062070d2f9ff
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..af242215eac721e89128de3aec4f9f382a1fb77b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_55_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15f5c6d2554fe19c6825537f15f9aa722235a21d4527a76eb6e0071cc540778
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..375b9fc21f53028d364924a5b8679b77081391e3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9437a4e5c39d60b9128b4d9d4e925fcbce22633111d3800f78a9cd27a90362
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..807e557db930e75bef7bcec579efad91e07cdfea
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801bdf643e8aad1498a849e5ba155f69aa555da459ad7122c6eeb2fabc1b1bf9
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9570c09a97bf6fd83c505119b9456800503bf12b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09300454a229ef46a25def94a54e7c779f5ecc94519ed863e87b3e4ad47db402
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..893105d0e356ad6cfdf4d034cddef30e0de15efe
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_56_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4832f4fa7e1c88dafd7cecd84b079125c56853d590f6c085795bc64e3a769a6e
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e18cb859d7bbd70a157ae3becad3956f349d0bba
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e0b995405f5a1deddb355baa505e40271932dbc3ea8cf3177cbf89511e5059d9
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..42ead7cf8da3a8ebba2818dffdd26c391109c226
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d850a3ea25c7788e9d26c61b63ac509383c85d24061f82bf98933069e342154
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..227729a86e1f1a29b3b13a1785884d31f3030e59
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7906a9a7805cfe189d09e547f772307ffe938f0aa0b7b8539d7914f3a74409c5
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..edf47d309b6f1107458586be90abd12ddf6bb24a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_57_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c130cb3c95b81fc43a23e16e176ed8bceb5de5c5aca71efaa70616aa1be76e5
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6b3125c52ce897c86d5d8c8c0384100ce9acdc71
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d992572d6c0d6c5fd9e734c7bbecb7bda0825c0f02dcb2df5f22864a8b12e187
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c415094b6637b5d45fc61e4cea3efaec202c5c76
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6082479ac93886ab93c0062fb9c81327d3d4a494e8bfaf0e7ac7398231bb910c
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..72b6cad6217daffa0d4cfb244ab2ca145df546c5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fdc3128e9133bfc4e3818b75727301684f6c21a6078d57855653147f6127feb
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..821f4dee70a3c3fc438f8caebb6282f8f72f2ce7
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_58_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867c527be116abbd13af82a185b31046e134f943d8a11bd493af13baac0df2a5
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3e5f0408b1886b0d9a80715b22291d03ca1772ce
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b45f6c0c71a6e99638be88a50878011d37d6b2559239ac46ce6a10a5cf671f3
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fee784ee8df6296712561030f69e071ca360e524
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cbd4657239d89f4e1e25d45a946332b40c011abf0b707de1ec86d501383cae3
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..492bcb30aecf606566e70a0c8412e42bfc1d3827
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dd758c9c532181e083352b58a4fdfff330f10f1a5261241500da097c85a93c
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..972f5f6ca8176f1715c6c4fa32fdf9e3e9df8790
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_59_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f68a8e1124e8eaa5002b45ca7c28e2b4d383ff7ad2b5add20d1cb8abeddbe8
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..91dbf2ba0d93bef59716ab5d04ff37e50d5754e3
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:dc3e3d99226fb8b03efc178c783794ae320da06ee232de854c19292883f133b0
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f4719912690d11ce836e1c4cd948e0a1981178ab
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ded6d612dbd65a952591a21b0084045e167716456093f01a2b002884b327ac1d
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d15abd8b177126a0585ac60b46c9aa5bd5d6d7e1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de3df34c3e773525b11c3c639219fbf87dc493d78c83acb387a663245525fa45
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..abcf3ed2f9d272670bff2864dc4ba4b58406057d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_5_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63a662be4a7b7d7869e9f9211b94a78112e0f3e3a9c0d9ea574e96a95f59bda
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7a76b37ecbd48c57dd28a11e1ee4f96f4cea3ac3
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b40e17f6fc01c9f0ff307795b3d91dbe900b28acaf1669e816fbee8cb85ec739
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..834d9d0f89971e421918715009ae50ee33eb006a
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:a7b7df7526853b3c23db6600f9a2564cd1bfe776d3eb762ab237d483976c95b1
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9e541a72f6ba188b301f85c4fcb2818798717539
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1113040171eb73fa7a007655b56932028062212369748da8c7e4dcac7763797e
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6826cb3ffe12b41b44710232a5820a852eb06dcb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_60_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce81355552304eccc83731bdd80a6677eef82a44ca4ae12cd5d090dcceb13644
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9241e57e0599695fd2eef7f868f012aad87ef8ec
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:d8125d9f4aab5350707726a62fc92d9e09b60554249f40f324d1e10acfdca443
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0e2b452ccb1510c7d941f637ac3eba83be1e7fce
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4108a0e6fd9368c1aca10f5766a520e10601a3d8f2ccca734d2a0fee06638444
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ccd87f255dca22264771fed862e9631e2bf3a1fa
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c66a00427161258139773250ccb0a5210bc7d1c6bf86b205a24b630c8d2b57
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cf48f0b23f493cf77f534ba83c9f343f17879b07
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_61_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28a798b452b55fe4bf252f992bb537ea91b09cd6badeb4c93c5bbb10980a77d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..62bd613837551aee9fedf82998fa9ddb0c17f374
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e26492a03be8fe87b9345cc9a53e4c024320c4a63e6f79ac6cc5c10b4f638ef
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..73c7fea3038aecf06dc5af00856f198586fa12d1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5051fe14c4caaa7b5bc611552f91b58cd6b80c74b9dc966b95327b60e3308305
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..688d082f1ec56792108c75b5694a1f387ef4156c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a9468144e26818af3bbc0091cacf361e30e25f26a70c6366b362e2d687110c
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c3dc10edd2f7e97bb465a12d00618e1e6bbefd17
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_62_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b18f85d3cc0cf8e59e7972713f286a79d97f2377d0d99bcdb681ea6b8f16971
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e6cf4926876b4d019b0df069bf1aaa521cba472f
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:f04fee4cb926576aca77e8ceb151717ea1543791b14afb186774b8d516bde6fb
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b413517a172e9b83a7f3afaa5d52bd2d66f8ab00
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ac5f26d02d1622809260c89742a5ef4240b21dab4c3ebb78476931a9fc1a710a
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f1a8f585680e853be9429fd4d19d92ffcddbc1a4
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0734aced74afab8d699271cfb6a56b49fd779ac4d5ec64e89e5af4fd17d6acf
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0dd4431369ccfe5091e6d362bd4a05e69b4bff31
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_63_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ceb567d27f9488da174658749ee424e278ddcc13bd6611a3ebdca42c5ec9f74
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e950eebd4d0cbf4bfbe68ead328cceeaa46ee99f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5035bcc465936c8ed728f90cc2f04c71eb28427f0c9a53a775faed4b926b654b
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..26b6fb08ce7f3fa61666b33ebee68d266b6314e1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd8598af79997ce75a6371a10ec7a0c5a867cb5227310fd85509c16fd833c15
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c4bf1a4e722b2714619c5146c32741f2945ed037
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcf66852dcde936c95c2d1fedb4fed2a32d8f68a16c3250a26ab4bb47c52188
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c02509c5f1228829b7f87186529fc10e5e60cde2
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_64_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7154437a1be5cf9489c4fff78a47e2f9f40a9ba91c62597150f4c6a9cba07d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eb926e39d1670aa3dc4cadabc40337a088d4bfbd
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:caa539cfd79e15f50e48ecdcd084f4fac2a6a8350564d3cdfd8cdabb3f32787f
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..da365f9b497bf8a5dea5620824418752dea5fae8
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ad40bcbdc6c4be3537ad7ad30d19c52bf1d3ad6b853328c72f52f077fe26b3fd
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3693ec8eb8973dc4c8e8164234ae1ff9ec4cbbb0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fbb6cc4a9c6733ed4ef3892ba516be398d6021c2edb96a513f957316e4be5f6
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..13d7a1cc9eec92dec71cadff2a1fd9a7c27cbd94
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_65_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9691cf6ecec6d215791d3b050648fbde46360bbb6049041b87d23ca7d4f6979a
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9ff7c8f85a27f3ab49962067d614d1acd75bc185
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027eb7a06f72d5b87e3878d33c44054d7b8d913d454d5e8f1719302c7833f942
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..61c9c94aa2aab45e731267ec34485b273c48af15
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b2c525f2f8511260b24acd500e0537c0ad34beaa914b158c1223a1a9b49883
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..61f1e104e085c90859ed9f38331232012cfdec09
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbf1e6119915a96ae416ae0496ff521a4108e245e66471063dfe76bace70d53
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4bac4636dc67d7c3cb511d9bba09fd1bd18bc7d1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_66_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d4ceccaa2e9e52e085d5394b1c07f9eeef6faf896978f6d2f5f456ec340c56
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..952110bcb6f3ac48018cb6b0a6625975210e50de
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2878abbdb7bd3e8c0bfb35165565f6ae19f5bd3358cc79392f1eec7e9c6e1d
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e1c3df22ac01b175b91798403b6bc1118b709a32
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afe0852c895b7506c4ddd9f61b7bebe38087bc1c2945a1427bbe38d77a4124a
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3de805528b248de9d70cd54366429487893c5163
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0d111cbc9af136cb395e977aea5b404bd4b7b19932cb1995f332a4f508fb10
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f29060978bcd31135109e24585a8ff45853a8ed7
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_67_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0cfadf8e8792f6c95367b59f121d09ef33b6024f30710d50da46472f5404c7
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1d932ca819ec8932f96fc07b2e553019d7e42ee8
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:bc134ba5dfde6f4107e14edcd679e8d28a3cc5f03bf29c7c8ac795f4c2b9ae1d
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f95171f767fc9dcdd19217fb2cd8806493127d70
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1095645e8843d08e7d09e6513c09ad8ca0abf73587905f84807f45514c644c97
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d2590ff96b9b23c74dae8fa7274b28f9b03324e0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d055d9916f19715b5e4dd46546e89b605acc0f3ec8e90a5346123e3f733a56
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8664d01192bb94ad21bd8144fc68f13405ed7821
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_68_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a94e29f3f7f33704d49a5d3591537fc27d744eeafd3b7e2f6ef5e84eb0cbb7
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f4201412d369100880eeb6909450a7ac67e7af58
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a623cd349fb0363f076d1b831f19b6dc4f5d7d09d21cf6e76fa96e0a9646331
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5a081220a65224190790199896476eae8fdee388
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d7389b959bc46ff06d13a7826a3e54b02321bfb3ebc8d852e0091e89e351ab
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9bba6d2c0ad5fa311569dd2b111a8aa082a0fdff
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef2178441abaa4504843f052008ebd25a9c230a986df95af630382aff5ff668
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..47dbe6e0be4764c160f029fb2a722bf19ffa234e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_69_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3a561213c879d4d8ff3ec150f6759804d897b0123074a558e545da2717b9e1
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aa3da4a78f1e991e580736866f5d34fad81711a9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d32f2cff9d8049bec381827b88865b9e84360019a65c43e47b3ac1022807fb7
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2577229a7e3f1bc11ff6d43b949e03640c0b78f9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9582bb583a15ab2f6b0f55ca1f02092551610b5bacd026889b7d9108e204573f
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c06bcbd55ac391c798cea78dcd1cc0c47528e9db
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3a566c282066a91d7782ab35710370654372ddee121aa4f09c1bb6578a4103
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d4e76a44012676f690e0d52b90257423f5a6e882
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_6_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e8fa515de7734c5604c884c2455c43662d45396dbb4b39bc282f894fcff46b
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a89002c12d00e4d6f19da97c5d6a57fab5b78bc6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e0d091c6788f0bf3603560ccb266325797c6b7acaee1bb1c73ff25a2e19639
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..30503f3a4bebf29a0ce1e1bb3afe09801186c767
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b322e9acd3065f8e5f0c9874dbe43c9052db41e8505e0f99d5b44faa8f10164f
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..58eda35852d41c410789e455aa0f4487ae4dcf53
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0e42dd0dd5f3b2948fee2c8532beb6619c75b9059565f471b38bd0ae2087ca
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1ca5eea2319c2104cff4fc89451607ccd702fc59
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_70_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f52bb0d7277a5e957a18205b8395ef68170c57954ffa379e88f784fc9ca818
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..27696c715c8b857ddcd9baebed7680028d9b45ad
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610456952ba1870e6d57c7e2473949805af5f3510f296fa5c4a500064dc037be
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0cabf2d95e9ca144d0fba213d23d6757408d4d70
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097bc737cee72446f17303da88c87ab4d6d5032e6413211ab49c53d4b5fc2b74
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b03ad9b20633f765d3dfc0b5946eb27274bb6d3b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f733273bd5c2b7e4bc0778ac0b54fca025e20bf2c38701729df2d6bfd1105f
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..506590c3d1a632205768a00899ddcd9cafa57ee6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_71_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194f7ba87ee62980e84c500a0e6bb7154ad1fb70b143c2a17b18535fe4d6fed6
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dc4d9ae469c6b20073275fa2d00c267ae3c40018
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:cbec2a50248998b6a8061c8abbe722d710603de9fb1e9963d98d276347caf90e
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..44b87b8449749cd0b7a1bb054fee75cfc4f2af37
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:bbf542005e8ddfe0d219643d9a528945fdcd446b75364958d42d15f2c45d11bd
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e96d647dcebd265895e3a021c5a7ce8812392107
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766038565a43ddd85dc0bf2e6d90f8b505bd80d8c05229cd41145f2abd79aa0d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..867d409d8defdbbc283db8747e830419a9ed4f8d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_72_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198ca15c982ed2d42d9df160924d1483bf22e02ee43d9ae2f90b7dd765a55b99
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..997c609b4762578f9ac38c0c3b61280689a71521
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e4e5bebd3baf7b925a5944584094c9ab9620db020b4364302470aa427c95a8
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..389e8c23da94c3a521a4517c17dcd429ba585397
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e7730b9281c73f8f2d469be55dcd8ece19254fd1b1c1c1bd9ca8c6866ddbe4
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cc2c97deefb5b6c16ccbe80d85e53a77a7a24c8f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c41d1b4e48ca6be8b22752e442f3d29f343005b8ee8d81dd407672d33d48d90
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5ffa1b8f003ab7e00df36f855406127d935e81ba
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_73_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5191f7ef1067e786ab30224e52774af00fe5cfcc089f60ec01dd7d6b680ed769
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..28ebac7a271aa79a01a3b1730837bf157573ea9e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3045a0053d255873025f77fcfb7667bdb7fc942ae6d059b5f361e0c7e971c8
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..341fb761c8d1cb82118c9e5553a7bc7882f1bbb1
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:da5cf7fd837335a9748bebc0c6695ef88f6999f50c671e2bc638dc14c320240b
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f388d003fbc35cebaba7f4b44c6784ed6d9de843
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2127afc0eb77ea18cdd24c2b57631545a0f67428803f9ed4a057ca39ff40cd
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ecac9d27ebc8aa90581e359ece6b3446a08279ef
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_74_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8360dc809eb71e50586aa587aa3566c3331ae2800e962328c943799f4698b97a
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..503da93eaf37029eae026d7532dac74fb96f97d6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e921ec94c85fe5030682c99926c3da39b0e0a8bbe2121681058fcd5d540589
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c7f3f662393ac8eee91f74baadf920cdc702de52
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04533987c235297e0748b85784d051205213e56cdd52277329e09d1e94e94e4b
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..07690fb31b550f7b651db443606646d6e1a8496f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b183254e7073175a58519bd0eb93b3d6bb520dfa021e5b9bdb0c1311fa95758
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..86bd569ffd39578e51967e423d8ef35344648c94
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_75_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5000074dff5e788aa4176ea8f81e3fb51ddce8e2da0c62fe14a3a61ceced3541
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..376c536ecb41aa6b6e8f2cfaf6816f0d37617ec0
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:c961159017d761edae5891fd19bcaa5302625def0634da65eec3c4c02ed61401
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..805b1a779f68b7aea478098b6c88713bd1062fb4
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fb8dcb3bf889d681ba41167d97e41e5bfb42e11f9c7155b5fa78fa88fbba5f
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e64647fe9c722e021edde26cec97fc04b2e09076
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e58b2435be1654f30937987067af3eed68c552292b846948d401879b1b35e66
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fa5a74924d7ad69564563ed770718d2879053d72
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_76_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd13c86b904721b3541c31bf385150bc8451a5199d80a98d1ffa6e6809285bd
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..deea2bbce2134ca6a6d0957061cf50c69d7e94ff
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2370455fedb4323ccd35bc718436ebde776da9f2ce18fbad99d011a54da338e2
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5eeb2f03a0deae6130429b1876216d7c517cbdad
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f9343475179a7532eaaf938caea89363b43243a008a3c4cdaf2391813fe941
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..985e7cbfaf10ae03825dc37f7704de0bb634cbb3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b632419ab45c19166a0f498937961dc3dce75ce23c18df9c20f301cf9793e26b
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..74b8109b5f99691cbd03556ee784e276113038b5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_77_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f3ef5dc6401a1eea09f25f7f4b5701a91142b69166d64ce26a360a687a0d72
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..249505432900ace194abc886cda2646d5711d279
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320ab1a266a680bdc85c6867d7ecc454f1482188f9643c18e9ce0286622424b0
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2416c493f4478dd7beb069bcae0d3bc044398abb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a6bdbdd4b1b8467f312866e46f93e60d83a78e1e5a01b440db651e72cd9b8d
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d97ed9ca86464c7fd2e5fd62ff5f9b111affc2f8
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8441832d17c79147aa49e3f5184bb98690ae7cc27b046fe771b881b839ac3f41
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..274067f8199414b2c599024d17019be3fcecac04
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_78_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c380e53e5626aeb3eb3b51631a4b62aaf1bf3286692a07256f1332ed03dfa041
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1f15b8c474f62f139847423beb872480907a0c25
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c39cea3868e10c2fbbe47860d3340902ffc76dd9eb5ea9dd903f8425e8e5e12
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..476c912b751c436d9a47723694e638d4f679b25e
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e1cab27842010044642e983bca6bbc7895a1033d32f887a6feb0e1f338ea1e53
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f7f6435d976a1ed04da948e7d602b32ed7af5889
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696542eed471d66401f7aa970f7761cbe8ab1c0ac62dedb45029ec1f6e78a99b
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bf5884f224509125a2adec8e8734c51dbccfa4fb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_79_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fe75696d329a3faf79978bf20bf94e691db3a7d0e63a23b5af2234917fc7eb
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b9090ee81ec74e32074acec19214c72431ee8c86
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dcf94d5d419aa83e29d767eb4e18fc2830c3d1914ec9db30c321d5eaca8191
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e2d8ddd0d9e223bba01a47f61b0e8c43c9029180
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d4b3eb51f2780c0fa4a03a8a37b8ffe81df4abf7433f4b7d9bcf86bd72ac17
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9901e4f0dfc054ed9274351c1e75dc8f4dcc81d1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581c951d21231963559ed0e02711d2be14874833cae7ec31d994525141d83890
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5a31fbdd22250e5dc39662f2e2a601e33fe49af9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_7_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f017833c30c5c0df4b2e92e23342472580173a2db287b85f4d785dab012e27eb
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c3611647cbd7f5987fab1ac110096c9ba55bf90e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618131781010e2eea0219564461170b3a77d4ffe9a03b0ad32ca5d9e65e2204b
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..84b5dcbdb6ada914e06cdd885c23a0ed7cfb76fc
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d59fcb5efd8b6db00133fed3cf60f083e512df287f27a8c08a53751369d154
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e7830dc23bb0a7af16905b3f01853060dbe26119
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2238d21d7ba5c9c045fc746a9ffe3296e47221d038ff244b6666d96c8d71e6
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..59b854f5b693cf7be6ba31f02c4695d3b1f36eb5
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_80_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f88ca16d66f46fd72399b20a0e11d40248d4e3af8b8ce2cca8aae827ad82740
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..714ddf46c7df81200196b5a59683591555cb1039
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f99e9d276365d39f58ddced13dc6f2ac20978b4e55fa5e6d08e701388d41870
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..862e20b87cfb1120f7a5775b37a8bd2449b6cabb
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7d0ad39a5b41d522da31e4db51ce50b770bfaf7c6b92afbb371b8754ef69a3
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a7641f3c765a1e976f56faff2d9db8d755c8e6fe
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceec0dc828c85e7bedc290337b638055cb7efb05a1270f8addba8d71c279d5af
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..786db56f846b8a43e54a7c634628701af907c2a8
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_81_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1831fbbaafd9917ef35ed8f2c6eaa8b18d2a14fcc4c454508d6d3006089c944e
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0cf405a88de5619d75c4cb3437a6119fd3b08cb7
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6944c4af3696d9457b7464099fd007ddf79e290a4ccddd1af64f463313cc12fa
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9e8bc31c1a11e15c6c9a8faebb1d1b22478c7cf6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c3e904750523265770d171be91c01a6b512c03d6f9e8d22b8660820043aee0
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..221faaeda20d0c16f23b181cf7c0fb5f6cdfc44d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ddc5d8cc60ad3bd53cc825ea452b293e3cbfaf0b6358595fee0f65e0eaebfb4
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..54cd2cbe7b380e693dcd522955df5447e6ed3163
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_82_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440655a0a3831e70c3ffaba9fb48dd2c14cf2c2260cc315c512a7f25b0ad0e9e
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e324a6ab70c2a8db901e77c47406e0ff35838d54
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2adc0ac51954b509c09b6def179ec46164d4fcf9a1cf36575ab02f98122bdf2d
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cfa28520fc9a526afbc2494b26bc03a405c1d27d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b8e0769c01163ed0bab48f6d9ae37ea075b3e82e21c97de947cafb85f63598
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aa6ce7b73ad275ec409b374a7596bbdf6b31693f
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40094900ec1cbec0327392ed86b91ecce994c240e9c8d2133c0dcee5ec5350c5
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..568bddeaf9cdf3e7419acfcaf75e924648862107
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_83_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af7f280b5ff2d5070b124207bf614be7c8e1ffea134d37219e823925f2b3f92f
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..74c2d40e8b8bbe0fb0741815f82f54058a1a2151
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b1f8804480f70c59b289c3bd9f570f515a7d45a1b92379659c7bd4a7ed41b265
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b065ff0b067a92f366c72805f20616d4bb0b569a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63979e5d2e82c6274f467d8387b9c61e6730c0280af28c29bad7831708748903
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4e91b33d9596306b555af478ec4a7fcb0ec8e478
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e314a8ca001a0332ce165321823df579250f1b95993af9a55c925496a2baf7
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d12d104db1b7a140b739be94c5e768b185b848c7
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_84_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2d8761cc2db2a95703b9deb95ec1831ce0c564bec5493e39e7fb84cf99d281
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a0fb782b59e7ffc3a5aa4f098986293f047f4556
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5daaeb09a46e345d0cda64fdf72e4aa5640c08772fefbe63c73fb6b6d1a220
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3854c7145d8f98ce4545d5f55c230a19c8daaf48
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a57cde62f7f9a2eaae0802b67bc0fed81b13a0a9acd5c5173ea6d29fa2eb892
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7e07c4c7281d21a6b80360282573aefd1366644e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d8f32ca767b8672e2441a11f1cceffecfaac4b54d2212e4f38e9a63cc16953
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..90574b250eb6700e875d7905fb9cd7dcb9105258
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_85_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5793859d3408007ed28fbd1bab79729fd1d95d6440534abe78b4e0d9f8f4812
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b82bab8fac0b9330cc097207c222cafddd240c23
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:f868e5d4ae3192e80b277ff193b944181ad6f4ccc23304dd418e70ac22b89cf6
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cd0dd90d8e029296b6c59953129b5f6adccfe608
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ccaa0edbd6fc6a397bc956d6ba78400a40b7ffcfde9062d9ccf9bccd49814eeb
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..07a69d7d4cc9a14f4e4820879505fb141078eeb6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42679d6ae6eec01f319de76a4c8043d55adcd566434d2804cc4a0db7dd6e306d
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1aa08f1866f7bfe06651c88a95e024430f956163
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_86_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949d92c9bb9b34a3edd35b9b0245ea6c28e8ab3d6d6583716f02ba45953aa35d
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..345e6d1dad5d3c99d23cb08eaeb85107be1d49f1
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac11c5af0d297b806a97d0650742f0d05c5478592352eabbd35f8caf132a392
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..952e97227cac7df5c1bda83741f08dcd9a3d27c2
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f049089938d188bb9a43b0b204460a6220df1877715241dbb559e8ca1c72f62
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c859636ddf8cbf6f8eed9273efb5bb221c6e0725
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b90d27ac165aeda66f93560cadd9fc01ebf573812cf8afae88b3cbe60f0b20
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e910f3122d9bc7c47e0d83cb100c230a43071d65
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_87_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c76392665ffc90d73b1665890177953f54b9285cf8be3249d04cc8b046799e
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8ec802fe53773b9a9116914a89d7de82ad8ff03d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec4407f0a42c7f6fcda9be8922ac8b6206a728d89d2b706c2993caea4a84648
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3f28d672693f06d5c33ea14bbc562c61bfecb0c5
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:beae344f6e3f8f24ac2c1c29b996fa3a64e70c70fb5ca8fc0bbca93c6a4385a2
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f47809c75a94fe8808033252d4656f71bae4041
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f847dd6488c3744576ef19dbe210f12171e3464ac95914fb772b6479a09ae1
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e6689af5bf6d5ce32347896c99661dbfda999aab
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_88_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315277f670517f62ed213ca468f4af7fca755d7fabb4e09221038a5a29c8fc02
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a32d0f1badd3c64cf4db64875f37d916e43795c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ceb121ffa57608fe954100007f58481f9b9fb62fd36d468eb47199d2086e0e
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..89966d5ef807c42654cdadfea25d2c80e3e87339
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ede7700e00f7f4982c05f7a20f71d1b962b807b8c2fb96c77699ae4a212416c9
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a0310e0eec336ecfa7ae37adc1c6950f26ce2a9a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b78e6c896b5fe4c857b09b7338ebc699550ec15c06797f01da08b8c2b8145d0
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c3c86337d67fde60f06f2ae011d6dded23a1ec29
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_89_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de97ddbfa348a93133917d58954ba63808980a823333bcc4d15fd8d72b7790e8
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ee8c96d1fb60ef90739d5c2addaf396b46f5f413
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ba17790b4562af9cd6464e6120484652d8dbe9057665cc9c7a2a82ba57b9d1
+size 208731479
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ff9096d6145b81384c87d3f5373a90f458c1aef3
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e500f4554953a329599decd8c1722e137e3d01a6f1896c87d3d3c2ed113360b
+size 208731479
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..978259d3c69c0e5c03d8378ae3211e1cef8db8ea
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2decb7b775c549c2c67e65a7297c38da9934716d37f89690b85a4ddac2639408
+size 208732247
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4ead2016cf0c0f46d0d31e89d84ee77807dc6e03
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_8_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627b480cb36e7a21df0d12952d9435ca3fe6790d196cfbfd0aaf574812cbfcd6
+size 208732247
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8df94f017dc0a7dcda37697efe23b0b655b8025d
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fbe50d3a7b5f9847d8c415a8da390abbbf278f6384983b1b63922711c19b5a8
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e62b824718f7cfa139077d688a2b95cad49370b8
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ed549dc5a488205662aba34516ca2d52289b3dcc6c95e0be164228e993788ebb
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fe815e9e3c55b749eb4f487a855646c09c12c9ce
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c660652098492d796d8704e77871c2bc2da762d49ed2a93e4dfaace0d037e174
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f0ad846b0e2ab2bf18cdb9965ad4797ed9961b07
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_90_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b19f6e0510c9f76e13e8acbc9d5d1f85534da85842319c2f944c88e9ce5e08
+size 208732066
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5467bb2c476fe5e5bf31b044af468691c6cc0309
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f6ac75576b73985439547162bd9b1e2c37e1b81f43e234e46c4bdde05620bc
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a5e358aca03da27f1936abcf90c5ee69b63fe89a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8948c13fe833d836fa4654ab8eb59f553c893de48e139ba20d41af20ea0ba91a
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..369bea2ce057a24fc2d46d7108cffb3085079390
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecdd9456b29ed6fe9da1e70779e4275b4155761e57a12ae5abf8a7cf81c971f
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..adcdc2a285e411b310e3de736b863b37606d899a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_91_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64272b9e02b3aaab87affafd3515ebb42f774e7da2526774a91e36f6cb01205d
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fbb7c8f7d909e1e8c3d6d16f0b920bb8283a4403
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:cdcef74c7f7bf08a5c19a3ec789c15436a147d3f2569cd59b4ca2a58b9d94c97
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..70e471249c5c02fd9acabfeab0fc959d95c04bfa
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:ccb4fdd3b2038f7d381e901c63f4eacc56bcf4f2958a172d667212b13fdc137d
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..18b083e2bc200c7e3844dbe693623d9c322fd401
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b257bd15276a66c0aa35d6a1923ed50d837f41526f7a2c17e55b1ba75903c1
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e596752dd69b5734f6ae0792897bde5b06b5510b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_92_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aaff836ff551f30350eb82030e9278c9ebc2c933c84cb6dcb739c59acb8a3a8
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2a338438da80f1083af35f07201c2af060b69e5f
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:a1e863712b6ca8a8db76eb223f7336ef8da80612bdbd55ad2c2b3265d85aa621
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..787101d815da7f007df42977c83fa10346ae1bfe
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:bea90deec5f4331b1d20b9e70d5e044e15b677ab570ed9334b61cb708d2046df
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9eb18efbf850aeced7694a8cbab06a86097a3d56
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c95cf0d5adfd2be7df13924d900ad5e49474e2e490fc974ccf6bcf322b7db1be
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a48c4e30fa1bb346a495f71d6f083aae1ded87db
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_93_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023c7eb8718040a71e005e094fb999be842f34373576460a0e35cde388cf2ee2
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f20ad1ee7530394eab3f06d3230311a76f3dd460
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e112700b1dfb594cdabd504232c6cc218dde3597c287295001ae98d30e4b76
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..64e497e56430a40f13dab83075cdecc4a7eba4af
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:db1d339be91a0367ae715bff4402243a7f7cf4144aa701838218c43c1f71fd75
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5fa0d6adf39befa66ad73f9a89188d0addf12bb6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa0c563d27b19f107e9d1f8723ee785f66c36551bad1277ca1a870bd19943c9
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3fc9b295d46fd5aca7d45984a09479bae0a4b478
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_94_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7c6f98787f471b4df57af6119ca2aa23c5c26a5b6223a3506c88fed27fe009
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2cb59739281bb5c576dea861bc562844b404a759
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acf19a1aaab6ab588e3257b0466832ca94f97a33164aebee9a8f4a4f24f8bae
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..359f9b10440433552773209c37c87f939aa4cfa0
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:c17e8a3cc43b7ff87caf4666558a960c2715c940a3e0b4aaa733dfca7ad52364
+size 208731490
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8aa5d791137842750b7a58241c734d8da09ccf8c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8adbe8d01db44cded2fca665a7befe264b870f30aba79de35b3d543d3659f347
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..605939585e028a9048a4129829263d255fe2037b
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_95_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70a3c8e47ef5174dd30d0c528f8ffe284ef33b923378c1f2014403206648d82
+size 208732258
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e9be94b1e1dfb4ea1f4a7b908b347ed340f52ee9
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f8e8e0a19cd28e8c1aaf239111542bbc5c5497edd441982fd9d78cafd3c43b
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8d86aeae051731919e4bf71a67db0264d3957617
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:e01aed83876c7175c1329607f4c14cfe918e62f09085ab8b8e25afd2dd7d69ef
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f2b8c5120a8611ce56468fd5444a02d665e08b5a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9479c37672bac950e01fcebd3ceccbcdcc40e6c90842ab46b4b52b5f40063c3a
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ba46cbbfce3fbdbfda1a6a3e1ccab7f81d438d21
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_96_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1d8a153177481d76cf0980438dda989b00e157afcd220c407ac6b08b4d8a3b
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c333fd31d8c18de21ef5c985b3376eebbfbd0606
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2da12130a452c91b1a37fdee83e09d0539bf72b0c17a20cf2e3bd8cf732b2d
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5e08a236078b4894b5091315bb23e5eeb84f124e
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a46ba9e94e4b3b8c2972c82af6b7ad5e476841cffea5cbb9839f22b27d0d6f
+size 208731298
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..924167b0998468b1518fcaf6558654ad4a10ead0
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a9f5cb1d3714bfb5d7b01b174af2b06ccfebac7f586a3e0099b2c411799e29
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6a929e4bb7b90f09837277b306e1eaad51a35b3a
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_97_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc373e4c97be9f0cec6efee4bc1e832f733d16e41dbdd55a41785646571e1a4
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..43bd358fe79434d55935606700179e7935ff6b0c
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:b7325b57f2c287d3bd3dbcbedac822f7505d5c65ece92a1e9dac5ad2ea61e2e5
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..309d07572c5c028f5d3885942285f8c2f8cee06f
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:cc672bdb7800317575bb380f14202724559d12cb709339b3feeb5f5b78ba197e
+size 208731426
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..be003fa54e564a72abdbf4dfa10a37789a982013
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c401e688108c6a40cfbbe083cb3fb8ef1194b8b1f8b942add109c2663e87588
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..95aa1c68f2292450f2d38fb33432d75c60dbc042
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_98_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad1720a6287cc29a4f27dedb97a966ed328b6f40389d521cc06f77622eacd2d
+size 208732194
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7b795ff65fe793f282c3805586c2acd540cfb0c6
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aaf3074ec2d861a8fdd015e512eee3ad14bd57aa76d0465d0cfdcdb3c2296c2
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0ee8b3a1942c944acc331bf16cd6fd7104371207
--- /dev/null
+++ b/8b7178b178b/global_step84877/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:a94c99680a9f2e5011c0589e801f280c4a40293ec4d83cb3b45a57fb28dc96ca
+size 208731362
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ea9b4857ad7771fc9dd5d05cc13b12aa15f0b9ef
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee1d899e1b03c6f643000b0faca951a89e9d7bf9f490031d7670e1e528cbd11
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..07a2c94d9fe4f1108a4d5e47f3ce8abc65534a10
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_99_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0a05ef7db3bd2f739142f903330bb1b403395bc2696911ec880653e5b5f3d7
+size 208732130
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0359875fa1693bd1d4341ecf48cff37dd306232c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6f34741925728cffabf9ad47b6af094d94fa5c53af38e96f7362f65f79cb1b
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..88417c76dd1dbbe2bef85089895bc8d374c8c924
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bac3dad12505834ea0a122e468d6211e448da2c72af228351a303e81eb4160
+size 208731351
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_02_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_02_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..db1f7f17877cac968598abdbba14cfd285855375
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_02_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3097da161adfad75c21a5f0f6c86f4ef410ba759772e381df2c2093bf22d1da1
+size 208732119
diff --git a/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_03_optim_states.pt b/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_03_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b3c9b1364f070742ea2240c5e22f99cb678802c
--- /dev/null
+++ b/8b7178b178b/global_step84877/bf16_zero_pp_rank_9_mp_rank_03_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ee83b40e7b5f56e2d3be232ca4d0b0c9ccf2c7a7ef254c551481f795042bc2
+size 208732119
diff --git a/8b7178b178b/global_step84877/layer_01-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_01-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..518c0ad0f32c26e9d713f5ddeeb7ad3016766c74
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_01-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f92e60d97c3304218cdc0c5e5f907992c43f32767f8d627ff600942fbb44ce
+size 223347971
diff --git a/8b7178b178b/global_step84877/layer_01-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_01-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..19669db59e85f75726dc15687271b9c8c2c0b37b
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_01-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f9530e80cf3fc2b2b1085a66ef9940aac749f5fac827ac16406491dab1b7a6
+size 223347971
diff --git a/8b7178b178b/global_step84877/layer_03-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_03-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..24db0bbbd657d27ceaa669ccdad43fbeb5d431b9
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_03-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba7971ba5e6c47bfde43da781429b3c80b97d6ec97d56f1cbb155bee30dce45
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_03-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_03-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d34dd2a0549deeb084a29b2350e6fba73bb0a388
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_03-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0405b617ddde4a63ecc3918a60cbea98a727636dcbe6dff687559c72fd0e8601
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_04-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_04-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8af8d72cb7f1f2d05d287d42d9468e24ffcbbc0a
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_04-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf077202ea5283805e532638ed604671a2e89ebfe7ca056c55ed6bd8ce6424cf
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_04-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_04-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d7f615b0a55e0e2a035a6de8224f3877f842f8f1
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_04-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb92134ef8f2d723256ff9a5109baaf10598763ec4fc17f168aeea18165eb731
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_05-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_05-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a1fd032e517f0aa797fe042f41267edc7c1f0450
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_05-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6dcfb5efa17d0c043deffefeb8022188903f45caa7fac2903b29cdb882da55b
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_05-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_05-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6ffa2c0e02ba46e601368ef64316a3bf84a0f38b
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_05-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cf16b18a6ec676f722e747beefe3baf4403f16a05383db455a8d8637f59f50
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_06-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_06-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..017ccc7c073ba5fb722818cc091bcb34578c4b53
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_06-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d537b767b52c8bf8c28016a68187fd22731a382e226821ee5665301dbdbc817c
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_06-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_06-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a030c56d9fc323cda2dfda1006d0d24d8dc1f263
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_06-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b79f6d5cfed772a4a938f3f2b80628f9ab05a653ebdd1ca11ea2e44a79917a
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_07-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_07-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b4d4936a4e0c07e8efac422dd231a6ce0144b081
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_07-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e422a7c554e26e953356d5ab30604dd851aea805a51a404b3a87510e9556a2b
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_07-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_07-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ac7959c9352ff09cebe18e64693537f40de63347
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_07-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ccaf1082771c36ab58aa336d3fd8dc5dbc738b2f4b566c90be8c749b21ba0a
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_08-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_08-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c2fb46255a69dd56983cd153c18561d56ccbe211
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_08-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa1e4c334eac7778147e844581e4a50fb79d8e6d8b935240d96fd4ecfd24878
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_08-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_08-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a5fdb01347eb04a3636d07ae6c81d0da982db8fb
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_08-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ffa09224df2ce9ffe2f2e5de5bfef011ab06ef48c9cbfa7f8630d0ee524ad2f
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_09-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_09-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..57abfc0ca3aac683a375dda7d5992db2b50db885
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_09-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae63f90197a006ae7c0405555e5d7af85f1448d9e1bef16ba3cd6774a1a296fd
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_09-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_09-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..163bac31d63256848504920e17aee26035c0de10
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_09-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05166b3a8fa7d1cdabbe769c2ecb686e1a8f4f46a6b059dc3220275a37b733db
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_10-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_10-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8618f59f02fe5d85e6079ce442fa7a7c0269390c
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_10-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4566f30fcd68e8bb1fe8a5257f4e7c1720e314d8f295ff7bd0544599491a93
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_10-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_10-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4f7107c7e5ccd155a6d24ba2c1272eb8e0201033
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_10-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccfc66aa0d8b17ad4e7b769e5000b9abc54c2b6e9883ee0101af79c7ba0a1e5
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_11-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_11-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c6437e302d5443fc08720e9c14bbb51a9eccdeef
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_11-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922deb4d2d655786dce280a1a6628712155a666c878449e05058ca79b5d99d84
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_11-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_11-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..019a66722d2b720a2e3c6054a55608cb24234ad0
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_11-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7416504418e36806a39ae2cfe7a3627a590d954871bb34caac31da59b9ad5a
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_12-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_12-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e6cea09566b946d18dbccaf77f5e569d8549edbb
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_12-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7766ec1fc4d7826107ba8a1f503b9082c012fbbc5e0423e624162377b0484d1
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_12-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_12-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..93b2a5b4395f5c50ebbcbdb6bb1c27d339f2a1df
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_12-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d84dfc9c78189fb9b861548387bb80061dd528ceb32c4cc70f106b67438954
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_13-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_13-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..395a54526c85f746523494e707f728ae1a789c40
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_13-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd61197d0ae9a6421cb3a17543e1b48cad23e1e524c53b3920194ccb13d5596
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_13-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_13-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f4e4f7660a622ad0a6e6484ae000175e7a98938
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_13-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3e42e745b0591d54027f005bbc4d5f2c0cc54a3fcd8006dbd7ac5f91146445
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_14-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_14-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8974eb97971c71d5d78b8bde3eb9d0ffad0032b6
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_14-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75dc41735f3ebfb3a25330d21f7ed4aafa2a8d48efe632baa66a1ddd52ec15e4
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_14-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_14-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e40038b8f97e87a56d1726d85f4bef60c098e156
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_14-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726b143fe2dd01c3781aaac9f7ee4ffea1677d5b37bae0959c6b0772a3297a34
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_15-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_15-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a2d8ab19e2a823814d4f0b2b4d43b32f1cd0997f
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_15-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0b4a4c4165584715d8e6efc26cfdad64bf2b23c7fd66db4f1d737eacf75444
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_15-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_15-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6cffdf394ca29049f1b7cd3fca2b761f1d249581
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_15-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dce6eff349e89ae878d8df7d0641fb087ddf743496b3e6e77f3bb157db4c41a
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_16-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_16-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f58da934da7d907d68f93468e0230d14a51bd68c
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_16-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b727332e8a33e38e1a4abf5de2c2925309e67e244e3b321ce68ea80fb01c3573
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_16-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_16-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..206fc9c17fba073d0c8433c86cf08ddeb98a563f
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_16-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:388ac206208c05ca3bc245c60b91c818348ccda026c8937446728d88ac3026aa
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_17-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_17-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d49a91d5fe846d5d833722116d6f9882d3299018
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_17-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48ebf6f50c7a3a48aa0acf9d4973005f53b9bc4b29a8e4ade4333006e732ef3
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_17-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_17-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7c72202314c3d240a6c181e3f56752fd1dd0fb5c
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_17-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314c430d4393c11132ee353cecba11fed1f36fb6afd830902b0b99c20cb6fe21
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_18-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_18-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..470014422ebcb63d7d04cd4312531ee4ed234b03
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_18-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2015e7da95dd51f8e479da87ecdb31e135a3f24822f059da1c8c98f0a3dcd8
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_18-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_18-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..94cac8100d203c914f41ee6b9abc0d23259c174b
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_18-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f196a982316bda1f45aa1e8b27a488ed23a40d1df6b04d3ee31e35a0b519d1
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_19-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_19-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aaa6055aa4c45ca2f716ff8bcec5d5a4a366fa4f
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_19-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5111e15262154fb7bc5eff74f76e51f7bd63cd807941ba31755d1a7bdb593cb5
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_19-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_19-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f47ef25be2dc7c7ded296829cae0827571aa0227
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_19-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf786152826ce548a43c9ea78473d6f90140ac086ad33e82e565df02968a3da
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_20-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_20-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2a18991db755f06743da9e9a562b0f581d71851d
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_20-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0022e2f0102a103165bf2ebbb0d63187d975ffc4b6ffc40c7f7e8e07782ed8
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_20-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_20-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a9e2300d3f9d9aca278d4298b50a59fdddb75c83
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_20-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4e9a5353ab084cc2e96b0773b4c21ec28c5d17d62094115ca594d144ab20c6
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_21-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_21-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d66a220baeb2f5690856bbe3bf39fb14e48f0e5a
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_21-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f542c93ced257e635b5901bfb1571862f1945cc003e38be31c04a18dd4081aa
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_21-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_21-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ac18c4a4c579ad282ae1a3776207acb4dfdb6c7b
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_21-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c49d14238435f464e58c6f2a67e0b2bb69b0bb9a344746d3b08685e8fff5716
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_22-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_22-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ac13ad3611845309a7f5b924a982d5cb19eb193e
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_22-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6cc1c8a05bdfad3373b082cdc7720470cf2999f64f6b5f48b237fb95f3f51e6
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_22-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_22-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..85d94b97ae113a3029bf44763fc9bb513173ce1e
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_22-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0259c119a018c97ffb861455b2ad3c8d68899a89c210a9321d3f1c859c0afbea
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_23-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_23-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d3f9b92b02e8e2217844f6c4beb77fd6dc0a8557
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_23-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f393cca54f99637c2bbd5c27a8cb6b8154734a5b3c3a58f498890f7a7a3aecb
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_23-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_23-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ccaebab64747a73ba42d48db55ccad6226523b60
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_23-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87003b2bb04c9c998e48028f58cf9df68c6f26cfd88bf44173713c257ab76f0b
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_24-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_24-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6d15ec9be1256b1b485c67f4abb68dceb5a746e3
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_24-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0969833f535f9280e41e46b41f677678e6f4f25aecea526cf635bb1bacdc06ac
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_24-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_24-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b7e0ef5c9f3acc0e99956f638806ec77a6bc4f4e
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_24-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c14b06e071e1ea279723a84c4ced6cdc5a5b602dd3d52d666c60342854d9bf
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_25-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_25-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7c44fd50afa7ef53cbd3ffd1abf18f2a5e58a27b
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_25-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1720fb03afc980b89f6a58bc37ae424d59ca36a5fb65ef79bf06481a372460fc
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_25-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_25-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c5ec439e92ee33322492a72151ffdb107b18b59a
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_25-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a209a2a3c2c29855858ef8265857c03f1397ae6e73eca3ee1ef0babb2ed4731
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_26-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_26-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..936e5842ea2229852a47301f71917551c35960ea
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_26-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0eb526b7de8aa1fddf50981dd3a0aa9837ef2ae9ee690b68910657bcb58971
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_26-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_26-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9472c938e7f84a088801de3e6cfd7b5b5e273083
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_26-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5957fc1c6355c3a2109fda822a14220b026e3cf382103eeee02b4b0f7f651c85
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_27-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_27-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..027662268d99cbde3fffcc90b4ecd5367a88fa71
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_27-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c42be1306c0963db9ae225812614f0ac145609643537ae9788263f4dab762c
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_27-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_27-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..accb96b7a2959ee7d0b548e3e27c6a529bc2888b
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_27-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661b72e246881bdcdc11fc0dd6fc19f2e9f83d09a086353da825925e32871813
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_28-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_28-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c111747abb42d7f481634cc2906d04ac1b9018d1
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_28-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f92184072349c7a64aae9257b894a5e40f7c88d54ab91cd6fb0b75644480972
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_28-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_28-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..795f3f161233d30311376e8a12bfb44a2c4d0833
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_28-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7374477802b84b1fe10a77d74f0b2bf34436b95b22cca205d48d7038c32967d1
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_29-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_29-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..08fb47a36be4fd2c63570f985701d019bd3d5684
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_29-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ade43c20af5517d684f1109c47e19d36ba17d9a69cff5899e7ed424a0fc6255
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_29-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_29-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..12cb906d3de459f6198486540534d9448277169d
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_29-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df86e6ec3027ba6d1557696120337c9f049164a840acd3eda69d8ba3733daa4d
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_30-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_30-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c7c309e2ddab4b9231eb2d1efe4066b2d3a69706
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_30-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc54edcdcf2f1eec52d4c155f14a12a0a7ebaf1fd1ea3a8b3196df32cb8e310
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_30-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_30-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c1b9b7aa6c1f2eafa2abc025aa6445506e22c147
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_30-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6d01ad0a2ae028c6a3ef958b27b70f5d9272fbdaafad63566359b1a6621136
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_31-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_31-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1bd1081be80cc2c932104dcaceb87ad388c3bedf
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_31-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8328c5cf8964aac565b6c2c4acbd7bce7526f968d253212239abb047a716914c
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_31-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_31-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e9a79590f0980741825dc0a1ff459eeb873f7647
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_31-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea3e1642370a2d83930fd0f1ab2a0d1aedb50ab8bcee001877c8d912863b1ef
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_32-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_32-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d3e7d3a33f85c5edee5df0f58cd2641056e6fa75
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_32-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75f2618695afd140750f9f7f569134a8302c03098e48fc44f685787bb81e5a0
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_32-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_32-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c1cbe937de6bf922076ee74accf7427cba4d1cfb
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_32-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37cafd118cf5336cfcc053a609c551969221b49adf4666d77519ff4750e4443
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_33-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_33-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..57a0c4288eeb20e8a4daf001129d6a267aeaeff7
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_33-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d837f5983c8b61e173cbc26c5b2ff4398ec3db849c46384ad88e918b19686b6
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_33-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_33-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0dd5b153027d52805ecbdce4d4e35a82d2b5de10
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_33-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a876f69f3cd1879471a9b1955256334576980916a32f1d58ba116a4aaaa04d9e
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_34-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_34-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..189ef6aa91e4de9c4a441bdd08470d6c312ecef0
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_34-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c1eecb05ec6be91e44a44258e93e6bcb005870c096771129a2bfc29a93da7c
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_34-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_34-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7720ef0c3bb8326a99dcc02ceff53ffdf08f7d9a
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_34-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2541755c2fbbebdf55a71a9ac67742690c777249129da6bed77809c43c364c5a
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_35-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_35-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a1f9084a99c093a212420dd9edc6b4fd60a5cb2
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_35-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6dfc50befe6918e8cdff35b877c000229412525cc130967e590a57262a7c1d
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_35-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_35-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..facdc20d75b81e171389ee6fccaac94266894056
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_35-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b6357ed2006924e1cd3faab295e87a8291b50b2fb660ba0421dc37a92778fd
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_36-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_36-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1b149665f02d41dc781eeb85af18331df71f3638
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_36-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a001876283b78dbcdc68fffb02615b124c90667bf5dc57b42fa49be02bed77
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_36-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_36-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..56bde16b921bb1891c3f5cd185f45299dcabde48
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_36-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6a7736d9be58d0c3deac121a3a7409ba152d045253ddce1a1293e58addaee7
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_37-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_37-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b672e578b8f781ce7b56c54957888d77024ec10f
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_37-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd66723f6ffb3f22a07ca65a09f6eaf40e06bb133790ac1fe0214028f81cb258
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_37-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_37-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d72663233845e0d89fc462d02d3c6108465d41a1
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_37-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369a6fa83776ecc2c5770fab9ecf2b58c2ea1218b51c0c2aae8e2cfc018a01d7
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_38-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_38-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5aca9c97b57149b1ab5365b03d95df5ecab610a7
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_38-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3681a8c23bcac40713e80924784694a1a922d6282db9c00c48bf1c49c9d9644
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_38-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_38-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..96c6196474f0e505ada01d53e3dbe72e997da48f
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_38-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c94ee38fd40f58ca1c723d63e12caf8d02e079e18461fd8206987a597d2de1
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_39-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_39-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e66f1f2e2527285770a33316169dac8cfb57abcd
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_39-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2077c57ec881dd4604002b51a1ee96d2860fce880f6f661b418f8d02dc82fc06
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_39-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_39-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0c88a7e9fd85a0b7e4b88fe22050ea7b70e6d869
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_39-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcbd9472112c39ce41f6f7ec48e44ed59b4ed59031875f856b7ebe29ed46c41
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_40-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_40-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..414f5613169b5b382ca80be5be2104b600594819
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_40-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa490b832d31d5ca2b1656a1ea7abd7ac9ba8a58572c336f30a02decb737385
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_40-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_40-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b3785902e16dfc4588c74b68b176e04809533a3
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_40-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55325827feefb8566578afd8b2cef172d40a2f80e5a214a8115ad22ea9f3356c
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_41-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_41-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e37654c969e850b21c0d4edb33b44adcc323ed04
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_41-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5ad2b5b011f033d1cd9e21c688444e9d91afffe1943931254ddfdf98578e93
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_41-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_41-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..02abed4caa5da1578d0879552bb232ae4af68be3
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_41-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d486d751326d3fecd7b5a684550aa6a4756f3d3d37282cd18a6fa55ef9405bd2
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_42-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_42-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d02ebb8345bd2b80d773eedf269facb1944e6d2e
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_42-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08e016a108ed82660a959309d3d61b1f4e0afbed7c96d459577069578f412ce
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_42-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_42-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..549c3f61d1cc26b6336f6cf158922c5991131ed1
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_42-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212e86a464278441820645b04491dabff5bfc18c113840a6d25bde69fbebbaca
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_43-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_43-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b1139ab795421e6a3f6fa3c49704c3876c8ed442
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_43-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263b8758a82704fbbcd2bdd2e15da7e85a4549645f8d659df15315b6e45d1f6e
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_43-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_43-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..97d053a7270aad73922c23d4d1520bcb916bcdcf
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_43-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079f104d717103b3b5d2d24e0116bc6460fe31f0111717a6d8361980e04614bd
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_44-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_44-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2f421397c02c6fa6428ee4beafc3f15bdf89d659
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_44-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756074b057f9982624850936615c28025b79e17bad5294437681e8de84c3099f
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_44-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_44-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c57a4a0c0dd8cfc23feaeba8af5efb194286bcdc
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_44-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5023b1c39cb771cd4cf57f99a9394030ebef9983fd8fee2a767bd32bda97a6f5
+size 201408771
diff --git a/8b7178b178b/global_step84877/layer_46-model_00-model_states.pt b/8b7178b178b/global_step84877/layer_46-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7881eabf754fb5488bdc1966285ab5c67b172225
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_46-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082835f0fefe03a4bbd23fccf6d626c15919f111e951902fee6410f809e52615
+size 17603
diff --git a/8b7178b178b/global_step84877/layer_46-model_01-model_states.pt b/8b7178b178b/global_step84877/layer_46-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9cb39cee5e461ca0e2aa73460917edb3b6f6689d
--- /dev/null
+++ b/8b7178b178b/global_step84877/layer_46-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1e96e85eac9d8bee59358f0192a627080b0769477bb3f0655f97276356fd26
+size 17603
diff --git a/8b7178b178b/global_step84877/mp_rank_00_model_states.pt b/8b7178b178b/global_step84877/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b7f6d2f6ec08023a181c6c74344a55050a910791
--- /dev/null
+++ b/8b7178b178b/global_step84877/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1c50773a01280815880333b477ce806e28d1c2d56975c30a8a6da6e9ad9272
+size 39923
diff --git a/8b7178b178b/global_step84877/mp_rank_01_model_states.pt b/8b7178b178b/global_step84877/mp_rank_01_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0148943fcfec2728bd59a379d1f128912c0169df
--- /dev/null
+++ b/8b7178b178b/global_step84877/mp_rank_01_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e42289287a3cf2c60214e5297173110b3849d3cd63a25e965696790e71b35e
+size 39923
diff --git a/8b7178b178b/global_step84877/mp_rank_02_model_states.pt b/8b7178b178b/global_step84877/mp_rank_02_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8e70793f9b1c08785a57db434a4d71eeb2356621
--- /dev/null
+++ b/8b7178b178b/global_step84877/mp_rank_02_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b24f420986dfabc2f5cdfeba437c6570632af5e7934ef0671d030ca03eee382
+size 40051
diff --git a/8b7178b178b/global_step84877/mp_rank_03_model_states.pt b/8b7178b178b/global_step84877/mp_rank_03_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..12092ef956564e50c683ad4ee9b4f8b6b78a8237
--- /dev/null
+++ b/8b7178b178b/global_step84877/mp_rank_03_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62744ad9263ddaa846e0ec14e5e9a4ae7632b70f525480d9c37ccbd3dca2ec24
+size 40051
diff --git a/8b7178b178b/transformers/config.json b/8b7178b178b/transformers/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..eadf3eb13cecae9db1c34cde4f4d373a9d0fe00f
--- /dev/null
+++ b/8b7178b178b/transformers/config.json
@@ -0,0 +1 @@
+{"vocab_size": 50432, "n_positions": 2048, "n_embd": 4096, "n_layer": 42, "n_head": 32, "n_inner": 16384, "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/8b7178b178b/transformers/pytorch_model.bin b/8b7178b178b/transformers/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..21dc5d18a6501aebb073cfdffa6750f6e4e6cfdb
--- /dev/null
+++ b/8b7178b178b/transformers/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4697193e4ff52349e05cbd0da534c5ea54ffe6bf3354648b3115fe7aa0ca0b8
+size 17698351197