Commit
•
4fdcb9f
1
Parent(s):
f1295b6
Add files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- evaluation/agg.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json +1 -0
- evaluation/agg.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json +1 -0
- evaluation/agg.limited=3000.model=lm1-2b8-55b-nodups.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json +1 -0
- evaluation/agg.limited=3000.model=lm1-2b8-55b-nodups.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json +1 -0
- evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl +0 -0
- evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl +3 -0
- evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl +0 -0
- evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl +0 -0
- evaluation/merged.csv +5 -0
- evaluation/merged.json +1 -0
- evaluation/nodups-results_lm-eval_global_step52452_2023-01-21-08-16-27.csv +21 -0
- evaluation/nodups-results_lm-eval_global_step52452_2023-01-21-08-16-27.json +87 -0
- evaluation/slim.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json +133 -0
- evaluation/slim.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json +133 -0
- evaluation/slim.limited=3000.model=lm1-2b8-55b-nodups.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json +133 -0
- evaluation/slim.limited=3000.model=lm1-2b8-55b-nodups.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json +133 -0
- global_step52452/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +3 -0
- global_step52452/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl filter=lfs diff=lfs merge=lfs -text
|
evaluation/agg.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.28029328196894115, "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": 0.02480184024920872}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.06329690360390738, "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": 0.001387935330246365}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.31421418416573627, "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": 0.004791161650456045}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.09746309685284041, "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": 0.0016849621638654459}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.027137503163609716, "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": 0.0007651343564527364}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.1401257111559608, "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": 0.003241586954388128}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.04223874039871612, "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": 0.001058848391939766}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.05932466454492388, "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": 0.0012690344678080382}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.29457496075642914, "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": 0.004394633326456139}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.0915089018847029, "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": 0.00153588410518572}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.060080846441887166, "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": 0.0013314718589465604}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.29569333412156357, "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": 0.004414337835118563}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.09243599692729336, "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": 0.0016105636568568666}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-nodups/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
|
evaluation/agg.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.18474112904164633, "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": 0.002267407181269061}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.27650424470884233, "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": 0.0027689275938439025}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.20094467016617557, "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": 0.0019315648928512489}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.04427928011450033, "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": 0.0010900420762454247}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.06774300806074234, "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": 0.0015532556924402066}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.04775726799786922, "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": 0.0009924171917991007}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.1403989637840109, "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": 0.0017027888022148028}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.21498569513652452, "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": 0.002236435710308492}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.1533878305154272, "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": 0.001403955983191417}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.17171619714033193, "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": 0.0021119378832536255}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.2581270017082987, "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": 0.0026139033957512238}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.18704146707991842, "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": 0.0017997359690437693}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 2.3426766870517794, "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": 0.06168807200033554}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-nodups/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
|
evaluation/agg.limited=3000.model=lm1-2b8-55b-nodups.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 6.208120134028529, "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": 0.1090255908153869}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.31731355835055003, "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": 0.004099274504817032}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.3324854292034225, "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": 0.0036680738174009278}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.2919082916343828, "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": 0.003144827416065499}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.1359171818938097, "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": 0.0024425949074616932}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.13681320433598393, "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": 0.0021042970297826253}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.12033860836317081, "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": 0.0018255484904436405}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.24305871613826696, "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": 0.00324135869732354}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.2577033439038558, "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": 0.0029570712013500815}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.22283049594155988, "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": 0.0023764897834232346}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.2640833510596156, "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": 0.00363828067497133}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.273011704389814, "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": 0.0031687493131647084}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2404191146065513, "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": 0.002734721442980669}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-nodups/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
|
evaluation/agg.limited=3000.model=lm1-2b8-55b-nodups.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.11158867971698037, "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": 0.0016342679910338715}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.27563712740580626, "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": 0.003703133787971269}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.1568899973617697, "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": 0.002189141052983194}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.018936864961514067, "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": 0.000818057289793505}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.04792744421310345, "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": 0.0020733476414230333}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.026811270052396363, "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": 0.0011483653848396338}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.09051718542621195, "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": 0.0012785710611048916}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.22518909744083276, "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": 0.0030139050451273614}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.12746226399797717, "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": 0.0017205425134826698}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.08996878492074459, "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": 0.0013092110765833764}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.22428273464986798, "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": 0.0031314258481570214}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.12677328059989124, "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": 0.0017734421929659534}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.9955908989230836, "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": 0.07407336954067296}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-nodups/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
|
evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3b5c89a24483406f8cb7dfcd91df292385e66a61722a94a5d34c3ea27cb42a6
|
3 |
+
size 13234336
|
evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
evaluation/examples.limited=3000.model=lm1-2b8-55b-nodups.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
evaluation/merged.csv
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
dataset,prompt,metric,value
|
2 |
+
e2e_nlg_cleaned,generate_text_restaurant,rouge2_fmeasure,0.12033860836317081
|
3 |
+
gem_xsum,article_DOC_summary,rouge2_fmeasure,0.026811270052396363
|
4 |
+
web_nlg_en,PALM_prompt,rouge2_fmeasure,0.04223874039871612
|
5 |
+
wiki_lingua_en,tldr_en,rouge2_fmeasure,0.04775726799786922
|
evaluation/merged.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"GEM/web_nlg_en": {"PALM_prompt": {"bleu": 0.28029328196894115, "bleu_stderr": 0.02480184024920872, "rouge1_fmeasure": 0.09746309685284041, "rouge1_fmeasure_stderr": 0.0016849621638654459, "rouge1_precision": 0.06329690360390738, "rouge1_precision_stderr": 0.001387935330246365, "rouge1_recall": 0.31421418416573627, "rouge1_recall_stderr": 0.004791161650456045, "rouge2_fmeasure": 0.04223874039871612, "rouge2_fmeasure_stderr": 0.001058848391939766, "rouge2_precision": 0.027137503163609716, "rouge2_precision_stderr": 0.0007651343564527364, "rouge2_recall": 0.1401257111559608, "rouge2_recall_stderr": 0.003241586954388128, "rougeL_fmeasure": 0.0915089018847029, "rougeL_fmeasure_stderr": 0.00153588410518572, "rougeL_precision": 0.05932466454492388, "rougeL_precision_stderr": 0.0012690344678080382, "rougeL_recall": 0.29457496075642914, "rougeL_recall_stderr": 0.004394633326456139, "rougeLsum_fmeasure": 0.09243599692729336, "rougeLsum_fmeasure_stderr": 0.0016105636568568666, "rougeLsum_precision": 0.060080846441887166, "rougeLsum_precision_stderr": 0.0013314718589465604, "rougeLsum_recall": 0.29569333412156357, "rougeLsum_recall_stderr": 0.004414337835118563}}, "GEM/wiki_lingua_en": {"tldr_en": {"bleu": 2.3426766870517794, "bleu_stderr": 0.06168807200033554, "rouge1_fmeasure": 0.20094467016617557, "rouge1_fmeasure_stderr": 0.0019315648928512489, "rouge1_precision": 0.18474112904164633, "rouge1_precision_stderr": 0.002267407181269061, "rouge1_recall": 0.27650424470884233, "rouge1_recall_stderr": 0.0027689275938439025, "rouge2_fmeasure": 0.04775726799786922, "rouge2_fmeasure_stderr": 0.0009924171917991007, "rouge2_precision": 0.04427928011450033, "rouge2_precision_stderr": 0.0010900420762454247, "rouge2_recall": 0.06774300806074234, "rouge2_recall_stderr": 0.0015532556924402066, "rougeL_fmeasure": 0.1533878305154272, "rougeL_fmeasure_stderr": 0.001403955983191417, "rougeL_precision": 0.1403989637840109, "rougeL_precision_stderr": 0.0017027888022148028, "rougeL_recall": 0.21498569513652452, "rougeL_recall_stderr": 0.002236435710308492, "rougeLsum_fmeasure": 0.18704146707991842, "rougeLsum_fmeasure_stderr": 0.0017997359690437693, "rougeLsum_precision": 0.17171619714033193, "rougeLsum_precision_stderr": 0.0021119378832536255, "rougeLsum_recall": 0.2581270017082987, "rougeLsum_recall_stderr": 0.0026139033957512238}}, "e2e_nlg_cleaned": {"generate_text_restaurant": {"bleu": 6.208120134028529, "bleu_stderr": 0.1090255908153869, "rouge1_fmeasure": 0.2919082916343828, "rouge1_fmeasure_stderr": 0.003144827416065499, "rouge1_precision": 0.31731355835055003, "rouge1_precision_stderr": 0.004099274504817032, "rouge1_recall": 0.3324854292034225, "rouge1_recall_stderr": 0.0036680738174009278, "rouge2_fmeasure": 0.12033860836317081, "rouge2_fmeasure_stderr": 0.0018255484904436405, "rouge2_precision": 0.1359171818938097, "rouge2_precision_stderr": 0.0024425949074616932, "rouge2_recall": 0.13681320433598393, "rouge2_recall_stderr": 0.0021042970297826253, "rougeL_fmeasure": 0.22283049594155988, "rougeL_fmeasure_stderr": 0.0023764897834232346, "rougeL_precision": 0.24305871613826696, "rougeL_precision_stderr": 0.00324135869732354, "rougeL_recall": 0.2577033439038558, "rougeL_recall_stderr": 0.0029570712013500815, "rougeLsum_fmeasure": 0.2404191146065513, "rougeLsum_fmeasure_stderr": 0.002734721442980669, "rougeLsum_precision": 0.2640833510596156, "rougeLsum_precision_stderr": 0.00363828067497133, "rougeLsum_recall": 0.273011704389814, "rougeLsum_recall_stderr": 0.0031687493131647084}}, "gem_xsum": {"article_DOC_summary": {"bleu": 0.9955908989230836, "bleu_stderr": 0.07407336954067296, "rouge1_fmeasure": 0.1568899973617697, "rouge1_fmeasure_stderr": 0.002189141052983194, "rouge1_precision": 0.11158867971698037, "rouge1_precision_stderr": 0.0016342679910338715, "rouge1_recall": 0.27563712740580626, "rouge1_recall_stderr": 0.003703133787971269, "rouge2_fmeasure": 0.026811270052396363, "rouge2_fmeasure_stderr": 0.0011483653848396338, "rouge2_precision": 0.018936864961514067, "rouge2_precision_stderr": 0.000818057289793505, "rouge2_recall": 0.04792744421310345, "rouge2_recall_stderr": 0.0020733476414230333, "rougeL_fmeasure": 0.12746226399797717, "rougeL_fmeasure_stderr": 0.0017205425134826698, "rougeL_precision": 0.09051718542621195, "rougeL_precision_stderr": 0.0012785710611048916, "rougeL_recall": 0.22518909744083276, "rougeL_recall_stderr": 0.0030139050451273614, "rougeLsum_fmeasure": 0.12677328059989124, "rougeLsum_fmeasure_stderr": 0.0017734421929659534, "rougeLsum_precision": 0.08996878492074459, "rougeLsum_precision_stderr": 0.0013092110765833764, "rougeLsum_recall": 0.22428273464986798, "rougeLsum_recall_stderr": 0.0031314258481570214}}}
|
evaluation/nodups-results_lm-eval_global_step52452_2023-01-21-08-16-27.csv
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
task,metric,value,err,version
|
2 |
+
anli_r1,acc,0.332,0.014899597242811483,0
|
3 |
+
anli_r2,acc,0.337,0.014955087918653607,0
|
4 |
+
anli_r3,acc,0.3516666666666667,0.013789711695404792,0
|
5 |
+
arc_challenge,acc,0.24829351535836178,0.012624912868089762,0
|
6 |
+
arc_challenge,acc_norm,0.2713310580204778,0.012993807727545796,0
|
7 |
+
arc_easy,acc,0.5589225589225589,0.010188293221040569,0
|
8 |
+
arc_easy,acc_norm,0.494949494949495,0.010259260102565853,0
|
9 |
+
boolq,acc,0.5425076452599389,0.00871339478784262,1
|
10 |
+
cb,acc,0.30357142857142855,0.06199938655510753,1
|
11 |
+
cb,f1,0.2584656084656085,,1
|
12 |
+
copa,acc,0.79,0.040936018074033256,0
|
13 |
+
hellaswag,acc,0.4444333798048198,0.004958872288442143,0
|
14 |
+
hellaswag,acc_norm,0.5771758613821948,0.00492998369279507,0
|
15 |
+
piqa,acc,0.7464635473340587,0.010150090834551791,0
|
16 |
+
piqa,acc_norm,0.7540805223068553,0.01004733186562518,0
|
17 |
+
rte,acc,0.5306859205776173,0.030039730592197812,0
|
18 |
+
sciq,acc,0.816,0.012259457340938577,0
|
19 |
+
sciq,acc_norm,0.734,0.01397996564514515,0
|
20 |
+
storycloze_2016,acc,0.7156600748262961,0.01043161412866525,0
|
21 |
+
winogrande,acc,0.5722178374112076,0.013905134013839953,0
|
evaluation/nodups-results_lm-eval_global_step52452_2023-01-21-08-16-27.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"anli_r1": {
|
4 |
+
"acc": 0.332,
|
5 |
+
"acc_stderr": 0.014899597242811483
|
6 |
+
},
|
7 |
+
"anli_r2": {
|
8 |
+
"acc": 0.337,
|
9 |
+
"acc_stderr": 0.014955087918653607
|
10 |
+
},
|
11 |
+
"anli_r3": {
|
12 |
+
"acc": 0.3516666666666667,
|
13 |
+
"acc_stderr": 0.013789711695404792
|
14 |
+
},
|
15 |
+
"cb": {
|
16 |
+
"acc": 0.30357142857142855,
|
17 |
+
"acc_stderr": 0.06199938655510753,
|
18 |
+
"f1": 0.2584656084656085
|
19 |
+
},
|
20 |
+
"copa": {
|
21 |
+
"acc": 0.79,
|
22 |
+
"acc_stderr": 0.040936018074033256
|
23 |
+
},
|
24 |
+
"hellaswag": {
|
25 |
+
"acc": 0.4444333798048198,
|
26 |
+
"acc_stderr": 0.004958872288442143,
|
27 |
+
"acc_norm": 0.5771758613821948,
|
28 |
+
"acc_norm_stderr": 0.00492998369279507
|
29 |
+
},
|
30 |
+
"rte": {
|
31 |
+
"acc": 0.5306859205776173,
|
32 |
+
"acc_stderr": 0.030039730592197812
|
33 |
+
},
|
34 |
+
"winogrande": {
|
35 |
+
"acc": 0.5722178374112076,
|
36 |
+
"acc_stderr": 0.013905134013839953
|
37 |
+
},
|
38 |
+
"storycloze_2016": {
|
39 |
+
"acc": 0.7156600748262961,
|
40 |
+
"acc_stderr": 0.01043161412866525
|
41 |
+
},
|
42 |
+
"boolq": {
|
43 |
+
"acc": 0.5425076452599389,
|
44 |
+
"acc_stderr": 0.00871339478784262
|
45 |
+
},
|
46 |
+
"arc_easy": {
|
47 |
+
"acc": 0.5589225589225589,
|
48 |
+
"acc_stderr": 0.010188293221040569,
|
49 |
+
"acc_norm": 0.494949494949495,
|
50 |
+
"acc_norm_stderr": 0.010259260102565853
|
51 |
+
},
|
52 |
+
"arc_challenge": {
|
53 |
+
"acc": 0.24829351535836178,
|
54 |
+
"acc_stderr": 0.012624912868089762,
|
55 |
+
"acc_norm": 0.2713310580204778,
|
56 |
+
"acc_norm_stderr": 0.012993807727545796
|
57 |
+
},
|
58 |
+
"sciq": {
|
59 |
+
"acc": 0.816,
|
60 |
+
"acc_stderr": 0.012259457340938577,
|
61 |
+
"acc_norm": 0.734,
|
62 |
+
"acc_norm_stderr": 0.01397996564514515
|
63 |
+
},
|
64 |
+
"piqa": {
|
65 |
+
"acc": 0.7464635473340587,
|
66 |
+
"acc_stderr": 0.010150090834551791,
|
67 |
+
"acc_norm": 0.7540805223068553,
|
68 |
+
"acc_norm_stderr": 0.01004733186562518
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"versions": {
|
72 |
+
"anli_r1": 0,
|
73 |
+
"anli_r2": 0,
|
74 |
+
"anli_r3": 0,
|
75 |
+
"cb": 1,
|
76 |
+
"copa": 0,
|
77 |
+
"hellaswag": 0,
|
78 |
+
"rte": 0,
|
79 |
+
"winogrande": 0,
|
80 |
+
"storycloze_2016": 0,
|
81 |
+
"boolq": 1,
|
82 |
+
"arc_easy": 0,
|
83 |
+
"arc_challenge": 0,
|
84 |
+
"sciq": 0,
|
85 |
+
"piqa": 0
|
86 |
+
}
|
87 |
+
}
|
evaluation/slim.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": [
|
3 |
+
{
|
4 |
+
"task_name": "GEM/web_nlg_en",
|
5 |
+
"prompt_name": "PALM_prompt",
|
6 |
+
"bleu": 0.28029328196894115,
|
7 |
+
"dataset_path": "GEM/web_nlg",
|
8 |
+
"dataset_name": "en",
|
9 |
+
"subset": null,
|
10 |
+
"bleu_stderr": 0.02480184024920872
|
11 |
+
},
|
12 |
+
{
|
13 |
+
"task_name": "GEM/web_nlg_en",
|
14 |
+
"prompt_name": "PALM_prompt",
|
15 |
+
"rouge1_precision": 0.06329690360390738,
|
16 |
+
"dataset_path": "GEM/web_nlg",
|
17 |
+
"dataset_name": "en",
|
18 |
+
"subset": null,
|
19 |
+
"rouge1_precision_stderr": 0.001387935330246365
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"task_name": "GEM/web_nlg_en",
|
23 |
+
"prompt_name": "PALM_prompt",
|
24 |
+
"rouge1_recall": 0.31421418416573627,
|
25 |
+
"dataset_path": "GEM/web_nlg",
|
26 |
+
"dataset_name": "en",
|
27 |
+
"subset": null,
|
28 |
+
"rouge1_recall_stderr": 0.004791161650456045
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"task_name": "GEM/web_nlg_en",
|
32 |
+
"prompt_name": "PALM_prompt",
|
33 |
+
"rouge1_fmeasure": 0.09746309685284041,
|
34 |
+
"dataset_path": "GEM/web_nlg",
|
35 |
+
"dataset_name": "en",
|
36 |
+
"subset": null,
|
37 |
+
"rouge1_fmeasure_stderr": 0.0016849621638654459
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"task_name": "GEM/web_nlg_en",
|
41 |
+
"prompt_name": "PALM_prompt",
|
42 |
+
"rouge2_precision": 0.027137503163609716,
|
43 |
+
"dataset_path": "GEM/web_nlg",
|
44 |
+
"dataset_name": "en",
|
45 |
+
"subset": null,
|
46 |
+
"rouge2_precision_stderr": 0.0007651343564527364
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"task_name": "GEM/web_nlg_en",
|
50 |
+
"prompt_name": "PALM_prompt",
|
51 |
+
"rouge2_recall": 0.1401257111559608,
|
52 |
+
"dataset_path": "GEM/web_nlg",
|
53 |
+
"dataset_name": "en",
|
54 |
+
"subset": null,
|
55 |
+
"rouge2_recall_stderr": 0.003241586954388128
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"task_name": "GEM/web_nlg_en",
|
59 |
+
"prompt_name": "PALM_prompt",
|
60 |
+
"rouge2_fmeasure": 0.04223874039871612,
|
61 |
+
"dataset_path": "GEM/web_nlg",
|
62 |
+
"dataset_name": "en",
|
63 |
+
"subset": null,
|
64 |
+
"rouge2_fmeasure_stderr": 0.001058848391939766
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"task_name": "GEM/web_nlg_en",
|
68 |
+
"prompt_name": "PALM_prompt",
|
69 |
+
"rougeL_precision": 0.05932466454492388,
|
70 |
+
"dataset_path": "GEM/web_nlg",
|
71 |
+
"dataset_name": "en",
|
72 |
+
"subset": null,
|
73 |
+
"rougeL_precision_stderr": 0.0012690344678080382
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"task_name": "GEM/web_nlg_en",
|
77 |
+
"prompt_name": "PALM_prompt",
|
78 |
+
"rougeL_recall": 0.29457496075642914,
|
79 |
+
"dataset_path": "GEM/web_nlg",
|
80 |
+
"dataset_name": "en",
|
81 |
+
"subset": null,
|
82 |
+
"rougeL_recall_stderr": 0.004394633326456139
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"task_name": "GEM/web_nlg_en",
|
86 |
+
"prompt_name": "PALM_prompt",
|
87 |
+
"rougeL_fmeasure": 0.0915089018847029,
|
88 |
+
"dataset_path": "GEM/web_nlg",
|
89 |
+
"dataset_name": "en",
|
90 |
+
"subset": null,
|
91 |
+
"rougeL_fmeasure_stderr": 0.00153588410518572
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"task_name": "GEM/web_nlg_en",
|
95 |
+
"prompt_name": "PALM_prompt",
|
96 |
+
"rougeLsum_precision": 0.060080846441887166,
|
97 |
+
"dataset_path": "GEM/web_nlg",
|
98 |
+
"dataset_name": "en",
|
99 |
+
"subset": null,
|
100 |
+
"rougeLsum_precision_stderr": 0.0013314718589465604
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"task_name": "GEM/web_nlg_en",
|
104 |
+
"prompt_name": "PALM_prompt",
|
105 |
+
"rougeLsum_recall": 0.29569333412156357,
|
106 |
+
"dataset_path": "GEM/web_nlg",
|
107 |
+
"dataset_name": "en",
|
108 |
+
"subset": null,
|
109 |
+
"rougeLsum_recall_stderr": 0.004414337835118563
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"task_name": "GEM/web_nlg_en",
|
113 |
+
"prompt_name": "PALM_prompt",
|
114 |
+
"rougeLsum_fmeasure": 0.09243599692729336,
|
115 |
+
"dataset_path": "GEM/web_nlg",
|
116 |
+
"dataset_name": "en",
|
117 |
+
"subset": null,
|
118 |
+
"rougeLsum_fmeasure_stderr": 0.0016105636568568666
|
119 |
+
}
|
120 |
+
],
|
121 |
+
"config": {
|
122 |
+
"model": "hf-causal",
|
123 |
+
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-nodups/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
|
124 |
+
"task_args": "",
|
125 |
+
"num_fewshot": 1,
|
126 |
+
"batch_size": 16,
|
127 |
+
"device": "cuda",
|
128 |
+
"use_cache": false,
|
129 |
+
"limit": 3000,
|
130 |
+
"bootstrap_iters": 10,
|
131 |
+
"seed": 1234
|
132 |
+
}
|
133 |
+
}
|
evaluation/slim.limited=3000.model=lm1-2b8-55b-nodups.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": [
|
3 |
+
{
|
4 |
+
"task_name": "GEM/wiki_lingua_en",
|
5 |
+
"prompt_name": "tldr_en",
|
6 |
+
"rouge1_precision": 0.18474112904164633,
|
7 |
+
"dataset_path": "GEM/wiki_lingua",
|
8 |
+
"dataset_name": "en",
|
9 |
+
"subset": null,
|
10 |
+
"rouge1_precision_stderr": 0.002267407181269061
|
11 |
+
},
|
12 |
+
{
|
13 |
+
"task_name": "GEM/wiki_lingua_en",
|
14 |
+
"prompt_name": "tldr_en",
|
15 |
+
"rouge1_recall": 0.27650424470884233,
|
16 |
+
"dataset_path": "GEM/wiki_lingua",
|
17 |
+
"dataset_name": "en",
|
18 |
+
"subset": null,
|
19 |
+
"rouge1_recall_stderr": 0.0027689275938439025
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"task_name": "GEM/wiki_lingua_en",
|
23 |
+
"prompt_name": "tldr_en",
|
24 |
+
"rouge1_fmeasure": 0.20094467016617557,
|
25 |
+
"dataset_path": "GEM/wiki_lingua",
|
26 |
+
"dataset_name": "en",
|
27 |
+
"subset": null,
|
28 |
+
"rouge1_fmeasure_stderr": 0.0019315648928512489
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"task_name": "GEM/wiki_lingua_en",
|
32 |
+
"prompt_name": "tldr_en",
|
33 |
+
"rouge2_precision": 0.04427928011450033,
|
34 |
+
"dataset_path": "GEM/wiki_lingua",
|
35 |
+
"dataset_name": "en",
|
36 |
+
"subset": null,
|
37 |
+
"rouge2_precision_stderr": 0.0010900420762454247
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"task_name": "GEM/wiki_lingua_en",
|
41 |
+
"prompt_name": "tldr_en",
|
42 |
+
"rouge2_recall": 0.06774300806074234,
|
43 |
+
"dataset_path": "GEM/wiki_lingua",
|
44 |
+
"dataset_name": "en",
|
45 |
+
"subset": null,
|
46 |
+
"rouge2_recall_stderr": 0.0015532556924402066
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"task_name": "GEM/wiki_lingua_en",
|
50 |
+
"prompt_name": "tldr_en",
|
51 |
+
"rouge2_fmeasure": 0.04775726799786922,
|
52 |
+
"dataset_path": "GEM/wiki_lingua",
|
53 |
+
"dataset_name": "en",
|
54 |
+
"subset": null,
|
55 |
+
"rouge2_fmeasure_stderr": 0.0009924171917991007
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"task_name": "GEM/wiki_lingua_en",
|
59 |
+
"prompt_name": "tldr_en",
|
60 |
+
"rougeL_precision": 0.1403989637840109,
|
61 |
+
"dataset_path": "GEM/wiki_lingua",
|
62 |
+
"dataset_name": "en",
|
63 |
+
"subset": null,
|
64 |
+
"rougeL_precision_stderr": 0.0017027888022148028
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"task_name": "GEM/wiki_lingua_en",
|
68 |
+
"prompt_name": "tldr_en",
|
69 |
+
"rougeL_recall": 0.21498569513652452,
|
70 |
+
"dataset_path": "GEM/wiki_lingua",
|
71 |
+
"dataset_name": "en",
|
72 |
+
"subset": null,
|
73 |
+
"rougeL_recall_stderr": 0.002236435710308492
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"task_name": "GEM/wiki_lingua_en",
|
77 |
+
"prompt_name": "tldr_en",
|
78 |
+
"rougeL_fmeasure": 0.1533878305154272,
|
79 |
+
"dataset_path": "GEM/wiki_lingua",
|
80 |
+
"dataset_name": "en",
|
81 |
+
"subset": null,
|
82 |
+
"rougeL_fmeasure_stderr": 0.001403955983191417
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"task_name": "GEM/wiki_lingua_en",
|
86 |
+
"prompt_name": "tldr_en",
|
87 |
+
"rougeLsum_precision": 0.17171619714033193,
|
88 |
+
"dataset_path": "GEM/wiki_lingua",
|
89 |
+
"dataset_name": "en",
|
90 |
+
"subset": null,
|
91 |
+
"rougeLsum_precision_stderr": 0.0021119378832536255
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"task_name": "GEM/wiki_lingua_en",
|
95 |
+
"prompt_name": "tldr_en",
|
96 |
+
"rougeLsum_recall": 0.2581270017082987,
|
97 |
+
"dataset_path": "GEM/wiki_lingua",
|
98 |
+
"dataset_name": "en",
|
99 |
+
"subset": null,
|
100 |
+
"rougeLsum_recall_stderr": 0.0026139033957512238
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"task_name": "GEM/wiki_lingua_en",
|
104 |
+
"prompt_name": "tldr_en",
|
105 |
+
"rougeLsum_fmeasure": 0.18704146707991842,
|
106 |
+
"dataset_path": "GEM/wiki_lingua",
|
107 |
+
"dataset_name": "en",
|
108 |
+
"subset": null,
|
109 |
+
"rougeLsum_fmeasure_stderr": 0.0017997359690437693
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"task_name": "GEM/wiki_lingua_en",
|
113 |
+
"prompt_name": "tldr_en",
|
114 |
+
"bleu": 2.3426766870517794,
|
115 |
+
"dataset_path": "GEM/wiki_lingua",
|
116 |
+
"dataset_name": "en",
|
117 |
+
"subset": null,
|
118 |
+
"bleu_stderr": 0.06168807200033554
|
119 |
+
}
|
120 |
+
],
|
121 |
+
"config": {
|
122 |
+
"model": "hf-causal",
|
123 |
+
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-nodups/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
|
124 |
+
"task_args": "",
|
125 |
+
"num_fewshot": 1,
|
126 |
+
"batch_size": 16,
|
127 |
+
"device": "cuda",
|
128 |
+
"use_cache": false,
|
129 |
+
"limit": 3000,
|
130 |
+
"bootstrap_iters": 10,
|
131 |
+
"seed": 1234
|
132 |
+
}
|
133 |
+
}
|
evaluation/slim.limited=3000.model=lm1-2b8-55b-nodups.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": [
|
3 |
+
{
|
4 |
+
"task_name": "e2e_nlg_cleaned",
|
5 |
+
"prompt_name": "generate_text_restaurant",
|
6 |
+
"bleu": 6.208120134028529,
|
7 |
+
"dataset_path": "e2e_nlg_cleaned",
|
8 |
+
"dataset_name": null,
|
9 |
+
"subset": null,
|
10 |
+
"bleu_stderr": 0.1090255908153869
|
11 |
+
},
|
12 |
+
{
|
13 |
+
"task_name": "e2e_nlg_cleaned",
|
14 |
+
"prompt_name": "generate_text_restaurant",
|
15 |
+
"rouge1_precision": 0.31731355835055003,
|
16 |
+
"dataset_path": "e2e_nlg_cleaned",
|
17 |
+
"dataset_name": null,
|
18 |
+
"subset": null,
|
19 |
+
"rouge1_precision_stderr": 0.004099274504817032
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"task_name": "e2e_nlg_cleaned",
|
23 |
+
"prompt_name": "generate_text_restaurant",
|
24 |
+
"rouge1_recall": 0.3324854292034225,
|
25 |
+
"dataset_path": "e2e_nlg_cleaned",
|
26 |
+
"dataset_name": null,
|
27 |
+
"subset": null,
|
28 |
+
"rouge1_recall_stderr": 0.0036680738174009278
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"task_name": "e2e_nlg_cleaned",
|
32 |
+
"prompt_name": "generate_text_restaurant",
|
33 |
+
"rouge1_fmeasure": 0.2919082916343828,
|
34 |
+
"dataset_path": "e2e_nlg_cleaned",
|
35 |
+
"dataset_name": null,
|
36 |
+
"subset": null,
|
37 |
+
"rouge1_fmeasure_stderr": 0.003144827416065499
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"task_name": "e2e_nlg_cleaned",
|
41 |
+
"prompt_name": "generate_text_restaurant",
|
42 |
+
"rouge2_precision": 0.1359171818938097,
|
43 |
+
"dataset_path": "e2e_nlg_cleaned",
|
44 |
+
"dataset_name": null,
|
45 |
+
"subset": null,
|
46 |
+
"rouge2_precision_stderr": 0.0024425949074616932
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"task_name": "e2e_nlg_cleaned",
|
50 |
+
"prompt_name": "generate_text_restaurant",
|
51 |
+
"rouge2_recall": 0.13681320433598393,
|
52 |
+
"dataset_path": "e2e_nlg_cleaned",
|
53 |
+
"dataset_name": null,
|
54 |
+
"subset": null,
|
55 |
+
"rouge2_recall_stderr": 0.0021042970297826253
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"task_name": "e2e_nlg_cleaned",
|
59 |
+
"prompt_name": "generate_text_restaurant",
|
60 |
+
"rouge2_fmeasure": 0.12033860836317081,
|
61 |
+
"dataset_path": "e2e_nlg_cleaned",
|
62 |
+
"dataset_name": null,
|
63 |
+
"subset": null,
|
64 |
+
"rouge2_fmeasure_stderr": 0.0018255484904436405
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"task_name": "e2e_nlg_cleaned",
|
68 |
+
"prompt_name": "generate_text_restaurant",
|
69 |
+
"rougeL_precision": 0.24305871613826696,
|
70 |
+
"dataset_path": "e2e_nlg_cleaned",
|
71 |
+
"dataset_name": null,
|
72 |
+
"subset": null,
|
73 |
+
"rougeL_precision_stderr": 0.00324135869732354
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"task_name": "e2e_nlg_cleaned",
|
77 |
+
"prompt_name": "generate_text_restaurant",
|
78 |
+
"rougeL_recall": 0.2577033439038558,
|
79 |
+
"dataset_path": "e2e_nlg_cleaned",
|
80 |
+
"dataset_name": null,
|
81 |
+
"subset": null,
|
82 |
+
"rougeL_recall_stderr": 0.0029570712013500815
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"task_name": "e2e_nlg_cleaned",
|
86 |
+
"prompt_name": "generate_text_restaurant",
|
87 |
+
"rougeL_fmeasure": 0.22283049594155988,
|
88 |
+
"dataset_path": "e2e_nlg_cleaned",
|
89 |
+
"dataset_name": null,
|
90 |
+
"subset": null,
|
91 |
+
"rougeL_fmeasure_stderr": 0.0023764897834232346
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"task_name": "e2e_nlg_cleaned",
|
95 |
+
"prompt_name": "generate_text_restaurant",
|
96 |
+
"rougeLsum_precision": 0.2640833510596156,
|
97 |
+
"dataset_path": "e2e_nlg_cleaned",
|
98 |
+
"dataset_name": null,
|
99 |
+
"subset": null,
|
100 |
+
"rougeLsum_precision_stderr": 0.00363828067497133
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"task_name": "e2e_nlg_cleaned",
|
104 |
+
"prompt_name": "generate_text_restaurant",
|
105 |
+
"rougeLsum_recall": 0.273011704389814,
|
106 |
+
"dataset_path": "e2e_nlg_cleaned",
|
107 |
+
"dataset_name": null,
|
108 |
+
"subset": null,
|
109 |
+
"rougeLsum_recall_stderr": 0.0031687493131647084
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"task_name": "e2e_nlg_cleaned",
|
113 |
+
"prompt_name": "generate_text_restaurant",
|
114 |
+
"rougeLsum_fmeasure": 0.2404191146065513,
|
115 |
+
"dataset_path": "e2e_nlg_cleaned",
|
116 |
+
"dataset_name": null,
|
117 |
+
"subset": null,
|
118 |
+
"rougeLsum_fmeasure_stderr": 0.002734721442980669
|
119 |
+
}
|
120 |
+
],
|
121 |
+
"config": {
|
122 |
+
"model": "hf-causal",
|
123 |
+
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-nodups/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
|
124 |
+
"task_args": "",
|
125 |
+
"num_fewshot": 1,
|
126 |
+
"batch_size": 16,
|
127 |
+
"device": "cuda",
|
128 |
+
"use_cache": false,
|
129 |
+
"limit": 3000,
|
130 |
+
"bootstrap_iters": 10,
|
131 |
+
"seed": 1234
|
132 |
+
}
|
133 |
+
}
|
evaluation/slim.limited=3000.model=lm1-2b8-55b-nodups.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-20T22:42:14.json
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": [
|
3 |
+
{
|
4 |
+
"task_name": "gem_xsum",
|
5 |
+
"prompt_name": "article_DOC_summary",
|
6 |
+
"rouge1_precision": 0.11158867971698037,
|
7 |
+
"dataset_path": "GEM/xsum",
|
8 |
+
"dataset_name": null,
|
9 |
+
"subset": "",
|
10 |
+
"rouge1_precision_stderr": 0.0016342679910338715
|
11 |
+
},
|
12 |
+
{
|
13 |
+
"task_name": "gem_xsum",
|
14 |
+
"prompt_name": "article_DOC_summary",
|
15 |
+
"rouge1_recall": 0.27563712740580626,
|
16 |
+
"dataset_path": "GEM/xsum",
|
17 |
+
"dataset_name": null,
|
18 |
+
"subset": "",
|
19 |
+
"rouge1_recall_stderr": 0.003703133787971269
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"task_name": "gem_xsum",
|
23 |
+
"prompt_name": "article_DOC_summary",
|
24 |
+
"rouge1_fmeasure": 0.1568899973617697,
|
25 |
+
"dataset_path": "GEM/xsum",
|
26 |
+
"dataset_name": null,
|
27 |
+
"subset": "",
|
28 |
+
"rouge1_fmeasure_stderr": 0.002189141052983194
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"task_name": "gem_xsum",
|
32 |
+
"prompt_name": "article_DOC_summary",
|
33 |
+
"rouge2_precision": 0.018936864961514067,
|
34 |
+
"dataset_path": "GEM/xsum",
|
35 |
+
"dataset_name": null,
|
36 |
+
"subset": "",
|
37 |
+
"rouge2_precision_stderr": 0.000818057289793505
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"task_name": "gem_xsum",
|
41 |
+
"prompt_name": "article_DOC_summary",
|
42 |
+
"rouge2_recall": 0.04792744421310345,
|
43 |
+
"dataset_path": "GEM/xsum",
|
44 |
+
"dataset_name": null,
|
45 |
+
"subset": "",
|
46 |
+
"rouge2_recall_stderr": 0.0020733476414230333
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"task_name": "gem_xsum",
|
50 |
+
"prompt_name": "article_DOC_summary",
|
51 |
+
"rouge2_fmeasure": 0.026811270052396363,
|
52 |
+
"dataset_path": "GEM/xsum",
|
53 |
+
"dataset_name": null,
|
54 |
+
"subset": "",
|
55 |
+
"rouge2_fmeasure_stderr": 0.0011483653848396338
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"task_name": "gem_xsum",
|
59 |
+
"prompt_name": "article_DOC_summary",
|
60 |
+
"rougeL_precision": 0.09051718542621195,
|
61 |
+
"dataset_path": "GEM/xsum",
|
62 |
+
"dataset_name": null,
|
63 |
+
"subset": "",
|
64 |
+
"rougeL_precision_stderr": 0.0012785710611048916
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"task_name": "gem_xsum",
|
68 |
+
"prompt_name": "article_DOC_summary",
|
69 |
+
"rougeL_recall": 0.22518909744083276,
|
70 |
+
"dataset_path": "GEM/xsum",
|
71 |
+
"dataset_name": null,
|
72 |
+
"subset": "",
|
73 |
+
"rougeL_recall_stderr": 0.0030139050451273614
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"task_name": "gem_xsum",
|
77 |
+
"prompt_name": "article_DOC_summary",
|
78 |
+
"rougeL_fmeasure": 0.12746226399797717,
|
79 |
+
"dataset_path": "GEM/xsum",
|
80 |
+
"dataset_name": null,
|
81 |
+
"subset": "",
|
82 |
+
"rougeL_fmeasure_stderr": 0.0017205425134826698
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"task_name": "gem_xsum",
|
86 |
+
"prompt_name": "article_DOC_summary",
|
87 |
+
"rougeLsum_precision": 0.08996878492074459,
|
88 |
+
"dataset_path": "GEM/xsum",
|
89 |
+
"dataset_name": null,
|
90 |
+
"subset": "",
|
91 |
+
"rougeLsum_precision_stderr": 0.0013092110765833764
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"task_name": "gem_xsum",
|
95 |
+
"prompt_name": "article_DOC_summary",
|
96 |
+
"rougeLsum_recall": 0.22428273464986798,
|
97 |
+
"dataset_path": "GEM/xsum",
|
98 |
+
"dataset_name": null,
|
99 |
+
"subset": "",
|
100 |
+
"rougeLsum_recall_stderr": 0.0031314258481570214
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"task_name": "gem_xsum",
|
104 |
+
"prompt_name": "article_DOC_summary",
|
105 |
+
"rougeLsum_fmeasure": 0.12677328059989124,
|
106 |
+
"dataset_path": "GEM/xsum",
|
107 |
+
"dataset_name": null,
|
108 |
+
"subset": "",
|
109 |
+
"rougeLsum_fmeasure_stderr": 0.0017734421929659534
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"task_name": "gem_xsum",
|
113 |
+
"prompt_name": "article_DOC_summary",
|
114 |
+
"bleu": 0.9955908989230836,
|
115 |
+
"dataset_path": "GEM/xsum",
|
116 |
+
"dataset_name": null,
|
117 |
+
"subset": "",
|
118 |
+
"bleu_stderr": 0.07407336954067296
|
119 |
+
}
|
120 |
+
],
|
121 |
+
"config": {
|
122 |
+
"model": "hf-causal",
|
123 |
+
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-2b8-55b-nodups/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
|
124 |
+
"task_args": "",
|
125 |
+
"num_fewshot": 1,
|
126 |
+
"batch_size": 16,
|
127 |
+
"device": "cuda",
|
128 |
+
"use_cache": false,
|
129 |
+
"limit": 3000,
|
130 |
+
"bootstrap_iters": 10,
|
131 |
+
"seed": 1234
|
132 |
+
}
|
133 |
+
}
|
global_step52452/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:787116bd311bfa10becf061add157a86a22ebcb37dfc57ac4fda19cb6d5196fc
|
3 |
+
size 131677719
|
global_step52452/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2089d9c2671e959a6dba04afdd5c45f6c37ed54be6442a6287e47bf8c6b29ea
|
3 |
+
size 131677805
|
global_step52452/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8abe5ff3e2089debb15c65dc88a67581df74f3dc0e02a3b30592e1e7ee53de3c
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:781929a0838babbf60d761170db1965c53b569521c6a2eb27556eb7b3caa1760
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:357a6ff0b0f8409dd714f52a1978324d2c989d9f40a769e69aa484e30e106552
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37658f2eb228beafca97dac455f92fb3989b7d0cf13ec8f6a586c992b3692565
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8a4ddb32524c30af9e104a7d0ccc02114a66c244a762b8231c2625ab21d1b18
|
3 |
+
size 131677677
|
global_step52452/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec70007672a52b1a57eaa6711017a634117fe5ed75c79aad3f5c6f23a0e1fea5
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a323c42be41ea31dbc2b65a5bbf594881f61af678e8f537f3715274044fceb28
|
3 |
+
size 131677805
|
global_step52452/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a55966272b34082785f3d378c1d72619cfca55e9e6232b80d7dedaed06678bfc
|
3 |
+
size 131677869
|
global_step52452/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1a1c8973a86b9b7a95d53b3db3af1035c2cbeb9faac6c295d6208a0f38ceff4
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b8b1383322c010532195b3a2b2cd28bc65191e2db742efb9f78082a661acc5c
|
3 |
+
size 131677794
|
global_step52452/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa9dcce6be45faf0f8e6b203dbb1fc863afa5c25841aa8741c7cc60f61d2d43c
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:012e31e784d79a20394930d5ae9dc689fb27e1a7d53b8d6dc809ca977ebab1ed
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba7f6d9bdce9a69e6a1063033e15e583d4c580a2ad1e2f75659cf341fe2fede
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6d39ad86c06d9bb38599cfd068c08fa964a65f1a13c46c0aa14b8dc36021cf4
|
3 |
+
size 131677805
|
global_step52452/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ba760f5574164e26e192865b53eaf83fc38d68bad2f031b1979fcbf16c57a46
|
3 |
+
size 131677677
|
global_step52452/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7335ac5095060cdab6f8cb6e3cc8a2b8416220db52f11e9c9fd6b4d95c0bae63
|
3 |
+
size 131677805
|
global_step52452/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be644e89f90da6a0e6e46ce6cf19f14fb91f85193474f60f7e9604d12ede8a05
|
3 |
+
size 131677805
|
global_step52452/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc0cb2a9185b948b519d3bb34c92b41999895478e484ee37de609b2722b914a
|
3 |
+
size 131677677
|
global_step52452/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3939cee12fedf69c4aa80c70c55f40816e1175014c1b50574bfea1c827cc95ff
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c3fd12c301faae6f1716254e6214f0c4655a0c13a3bb1877ca84bc2cfd3c0ba
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f4fc619cbf68753e50c9ee9e0947fca5aaf5ea6a42667bd20810cd14c717b91
|
3 |
+
size 131677730
|
global_step52452/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:629755caf57159ff657af603f6b7861e7d6315a267ab5cb33f19e0235e9e0dc0
|
3 |
+
size 131677677
|
global_step52452/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97784dd0e50d8c08a935cd6f7dae5155242c9fce55b9b756b3f00ecf8213bc18
|
3 |
+
size 131677805
|
global_step52452/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bd148ee37d89504738ab45dfa8ee365e162e16d3f8cfc9d34c8fb92a53d7cd9
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a741dbc6d3478edb4398a40c73818a2a8fefb2b478c753e64546472b1f7f97c9
|
3 |
+
size 131677869
|
global_step52452/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:095d9e21140105edff7bf7ed24fda024c5bda12ce195b3f915fd86e2bf006204
|
3 |
+
size 131677805
|
global_step52452/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fae89dd4d6f84072d796daa837481320c355e4964eddad25525d8c230f01a755
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc3a60294562d0c1b5b876527b6547e5195afadc6625fd95f7a420e6d9ca58eb
|
3 |
+
size 131677805
|
global_step52452/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45085f64177a1e90eb6158db3b46179ebdf1551ca0eb17af8d13cd06a1d1c9f9
|
3 |
+
size 131677677
|
global_step52452/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba5262fe9f5dd52bd35da5a016166122c29b4ddbf963bdc30965902e0d756040
|
3 |
+
size 131677741
|
global_step52452/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9346378b9adf56f95bb8c134371955cae3a83fe45b4c2119076677ce64b9dd9d
|
3 |
+
size 131677677
|