Upload folder using huggingface_hub

#4339
Pretrain_language_model/save/slimpajama_competesmoe_no_attmoe_660M_standardlb_down_flip/export/result-model-140000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.417517877394153, "val/accuracy": 0.5032575053553427, "val/perplexity": 11.217980327100483, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.217075892857143, "lambada/accuracy/total": 0.3223990683229814, "lambada/accuracy/openai_last_token": 0.7895962732919255, "lambada/perplexity": 8.033157605216047, "lambada/lm_loss": 2.9931819562798707, "lambada/lm_perplexity": 19.94905864044293, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.41282828683916206, "mean_loss": 2.317296885125648, "blimp/accuracy/passive_2": 0.893, "blimp/accuracy/determiner_noun_agreement_2": 0.984, "blimp/accuracy/ellipsis_n_bar_1": 0.866, "blimp/accuracy/tough_vs_raising_2": 0.908, "blimp/accuracy/tough_vs_raising_1": 0.591, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.906, "blimp/accuracy/principle_A_reconstruction": 0.498, "blimp/accuracy/wh_vs_that_with_gap": 0.516, "blimp/accuracy/principle_A_domain_2": 0.871, "blimp/accuracy/determiner_noun_agreement_1": 0.988, "blimp/accuracy/ellipsis_n_bar_2": 0.906, "blimp/accuracy/principle_A_domain_3": 0.601, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.922, "blimp/accuracy/animate_subject_trans": 0.917, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.913, "blimp/accuracy/distractor_agreement_relative_clause": 0.652, "blimp/accuracy/transitive": 0.896, "blimp/accuracy/sentential_subject_island": 0.352, "blimp/accuracy/adjunct_island": 0.899, "blimp/accuracy/intransitive": 0.77, "blimp/accuracy/existential_there_subject_raising": 0.883, "blimp/accuracy/irregular_past_participle_adjectives": 0.894, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.595, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.343, "blimp/accuracy/only_npi_scope": 0.794, "blimp/accuracy/superlative_quantifiers_2": 0.71, "blimp/accuracy/passive_1": 0.879, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.931, "blimp/accuracy/inchoative": 0.613, "blimp/accuracy/anaphor_gender_agreement": 0.979, "blimp/accuracy/principle_A_c_command": 0.618, "blimp/accuracy/only_npi_licensor_present": 0.736, "blimp/accuracy/expletive_it_object_raising": 0.752, "blimp/accuracy/left_branch_island_simple_question": 0.665, "blimp/accuracy/wh_questions_subject_gap": 0.947, "blimp/accuracy/existential_there_quantifiers_2": 0.465, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.952, "blimp/accuracy/sentential_negation_npi_scope": 0.695, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.825, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.911, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.901, "blimp/accuracy/principle_A_case_2": 0.921, "blimp/accuracy/distractor_agreement_relational_noun": 0.843, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.978, "blimp/accuracy/superlative_quantifiers_1": 0.673, "blimp/accuracy/wh_island": 0.704, "blimp/accuracy/principle_A_domain_1": 0.994, "blimp/accuracy/complex_NP_island": 0.64, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.971, "blimp/accuracy/irregular_past_participle_verbs": 0.92, "blimp/accuracy/drop_argument": 0.749, "blimp/accuracy/wh_questions_object_gap": 0.874, "blimp/accuracy/animate_subject_passive": 0.804, "blimp/accuracy/existential_there_quantifiers_1": 0.986, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.915, "blimp/accuracy/npi_present_2": 0.562, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.95, "blimp/accuracy/anaphor_number_agreement": 0.985, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.962, "blimp/accuracy/existential_there_object_raising": 0.836, "blimp/accuracy/matrix_question_npi_licensor_present": 0.324, "blimp/accuracy/npi_present_1": 0.536, "blimp/accuracy/wh_vs_that_no_gap": 0.982, "blimp/accuracy/left_branch_island_echo_question": 0.511, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.974, "blimp/accuracy/causative": 0.754, "blimp/accuracy/group_average": 0.7952985074626865, "blimp/accuracy/seq_average": 0.7952985074626866, "cbt/accuracy/NE": 0.8024839743589743, "cbt/accuracy/V": 0.9336, "cbt/accuracy/CN": 0.8684, "cbt/accuracy/P": 0.9088, "cbt/accuracy/group_average": 0.8783209935897436, "cbt/accuracy/seq_average": 0.8783513405362144, "hellaswag/accuracy/val": 0.34106751643098987, "hellaswag/accuracy/group_average": 0.34106751643098987, "hellaswag/accuracy/seq_average": 0.34106751643098987, "piqa/accuracy/val": 0.6213275299238302, "piqa/accuracy/group_average": 0.6213275299238302, "piqa/accuracy/seq_average": 0.6213275299238302, "ai2arc/accuracy/ARC-Easy": 0.3627906976744186, "ai2arc/accuracy/ARC-Challenge": 0.2429184549356223, "ai2arc/accuracy/group_average": 0.30285457630502044, "ai2arc/accuracy/seq_average": 0.32322946175637396, "mmlu/accuracy/MMLU": 0.2615659635323561, "mmlu/accuracy/group_average": 0.2615659635323561, "mmlu/accuracy/seq_average": 0.2615659635323561, "openbookqa/accuracy/test": 0.272, "openbookqa/accuracy/group_average": 0.272, "openbookqa/accuracy/seq_average": 0.272, "race/accuracy/test/high": 0.2815894797026873, "race/accuracy/test/middle": 0.33774373259052926, "race/accuracy/group_average": 0.30966660614660824, "race/accuracy/seq_average": 0.2979327117957033, "siqa/accuracy/dev": 0.3669396110542477, "siqa/accuracy/group_average": 0.3669396110542477, "siqa/accuracy/seq_average": 0.3669396110542477, "winogrande/accuracy/dev": 0.516179952644041, "winogrande/accuracy/group_average": 0.516179952644041, "winogrande/accuracy/seq_average": 0.516179952644041, "commonsenseqa/accuracy/dev_rand_split": 0.2620802620802621, "commonsenseqa/accuracy/group_average": 0.2620802620802621, "commonsenseqa/accuracy/seq_average": 0.2620802620802621}
Pretrain_language_model/save/slimpajama_competesmoe_no_attmoe_660M_standardlb_down_flip/export/result-model-160000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.3996148878528225, "val/accuracy": 0.5050472136466734, "val/perplexity": 11.018932038843184, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.2831644567643634, "lambada/accuracy/total": 0.3295807453416149, "lambada/accuracy/openai_last_token": 0.7864906832298136, "lambada/perplexity": 7.955993307328318, "lambada/lm_loss": 2.97131455822052, "lambada/lm_perplexity": 19.51755970818759, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.41731397949414417, "mean_loss": 2.341389672308593, "blimp/accuracy/passive_2": 0.903, "blimp/accuracy/determiner_noun_agreement_2": 0.981, "blimp/accuracy/ellipsis_n_bar_1": 0.855, "blimp/accuracy/tough_vs_raising_2": 0.872, "blimp/accuracy/tough_vs_raising_1": 0.581, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.915, "blimp/accuracy/principle_A_reconstruction": 0.318, "blimp/accuracy/wh_vs_that_with_gap": 0.469, "blimp/accuracy/principle_A_domain_2": 0.886, "blimp/accuracy/determiner_noun_agreement_1": 0.991, "blimp/accuracy/ellipsis_n_bar_2": 0.899, "blimp/accuracy/principle_A_domain_3": 0.608, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.929, "blimp/accuracy/animate_subject_trans": 0.903, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.91, "blimp/accuracy/distractor_agreement_relative_clause": 0.704, "blimp/accuracy/transitive": 0.888, "blimp/accuracy/sentential_subject_island": 0.318, "blimp/accuracy/adjunct_island": 0.885, "blimp/accuracy/intransitive": 0.769, "blimp/accuracy/existential_there_subject_raising": 0.878, "blimp/accuracy/irregular_past_participle_adjectives": 0.958, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.717, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.355, "blimp/accuracy/only_npi_scope": 0.717, "blimp/accuracy/superlative_quantifiers_2": 0.753, "blimp/accuracy/passive_1": 0.901, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.93, "blimp/accuracy/inchoative": 0.625, "blimp/accuracy/anaphor_gender_agreement": 0.962, "blimp/accuracy/principle_A_c_command": 0.623, "blimp/accuracy/only_npi_licensor_present": 0.639, "blimp/accuracy/expletive_it_object_raising": 0.765, "blimp/accuracy/left_branch_island_simple_question": 0.784, "blimp/accuracy/wh_questions_subject_gap": 0.917, "blimp/accuracy/existential_there_quantifiers_2": 0.39, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.948, "blimp/accuracy/sentential_negation_npi_scope": 0.714, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.82, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.879, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.912, "blimp/accuracy/principle_A_case_2": 0.93, "blimp/accuracy/distractor_agreement_relational_noun": 0.852, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.975, "blimp/accuracy/superlative_quantifiers_1": 0.731, "blimp/accuracy/wh_island": 0.78, "blimp/accuracy/principle_A_domain_1": 0.995, "blimp/accuracy/complex_NP_island": 0.641, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.972, "blimp/accuracy/irregular_past_participle_verbs": 0.906, "blimp/accuracy/drop_argument": 0.73, "blimp/accuracy/wh_questions_object_gap": 0.819, "blimp/accuracy/animate_subject_passive": 0.779, "blimp/accuracy/existential_there_quantifiers_1": 0.979, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.905, "blimp/accuracy/npi_present_2": 0.54, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.977, "blimp/accuracy/anaphor_number_agreement": 0.994, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.961, "blimp/accuracy/existential_there_object_raising": 0.855, "blimp/accuracy/matrix_question_npi_licensor_present": 0.327, "blimp/accuracy/npi_present_1": 0.458, "blimp/accuracy/wh_vs_that_no_gap": 0.971, "blimp/accuracy/left_branch_island_echo_question": 0.491, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.958, "blimp/accuracy/causative": 0.752, "blimp/accuracy/group_average": 0.7917761194029849, "blimp/accuracy/seq_average": 0.7917761194029851, "cbt/accuracy/NE": 0.8044871794871795, "cbt/accuracy/V": 0.9324, "cbt/accuracy/CN": 0.8732, "cbt/accuracy/P": 0.9092, "cbt/accuracy/group_average": 0.879821794871795, "cbt/accuracy/seq_average": 0.8798519407763106, "hellaswag/accuracy/val": 0.34007169886476796, "hellaswag/accuracy/group_average": 0.34007169886476796, "hellaswag/accuracy/seq_average": 0.34007169886476796, "piqa/accuracy/val": 0.6137105549510338, "piqa/accuracy/group_average": 0.6137105549510338, "piqa/accuracy/seq_average": 0.6137105549510338, "ai2arc/accuracy/ARC-Easy": 0.36321353065539114, "ai2arc/accuracy/ARC-Challenge": 0.22832618025751072, "ai2arc/accuracy/group_average": 0.29576985545645096, "ai2arc/accuracy/seq_average": 0.31869688385269124, "mmlu/accuracy/MMLU": 0.2653557382910261, "mmlu/accuracy/group_average": 0.2653557382910261, "mmlu/accuracy/seq_average": 0.2653557382910261, "openbookqa/accuracy/test": 0.276, "openbookqa/accuracy/group_average": 0.276, "openbookqa/accuracy/seq_average": 0.276, "race/accuracy/test/high": 0.2830188679245283, "race/accuracy/test/middle": 0.36002785515320335, "race/accuracy/group_average": 0.32152336153886585, "race/accuracy/seq_average": 0.30543169841913254, "siqa/accuracy/dev": 0.36898669396110545, "siqa/accuracy/group_average": 0.36898669396110545, "siqa/accuracy/seq_average": 0.36898669396110545, "winogrande/accuracy/dev": 0.4956590370955012, "winogrande/accuracy/group_average": 0.4956590370955012, "winogrande/accuracy/seq_average": 0.4956590370955012, "commonsenseqa/accuracy/dev_rand_split": 0.26371826371826373, "commonsenseqa/accuracy/group_average": 0.26371826371826373, "commonsenseqa/accuracy/seq_average": 0.26371826371826373}