Upload folder using huggingface_hub

#326
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-10000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 3.0243472144717263, "val/accuracy": 0.42463611421130953, "val/perplexity": 20.5805656298475, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.7515926005677405, "lambada/accuracy/total": 0.1686723602484472, "lambada/accuracy/openai_last_token": 0.7245729813664596, "lambada/perplexity": 23.734422729737634, "lambada/lm_loss": 3.5597748767998123, "lambada/lm_perplexity": 35.15528198461303, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.2966542372298784, "mean_loss": 2.887969907519733, "blimp/accuracy/passive_2": 0.897, "blimp/accuracy/determiner_noun_agreement_2": 0.967, "blimp/accuracy/ellipsis_n_bar_1": 0.728, "blimp/accuracy/tough_vs_raising_2": 0.861, "blimp/accuracy/tough_vs_raising_1": 0.528, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.869, "blimp/accuracy/principle_A_reconstruction": 0.409, "blimp/accuracy/wh_vs_that_with_gap": 0.363, "blimp/accuracy/principle_A_domain_2": 0.735, "blimp/accuracy/determiner_noun_agreement_1": 0.968, "blimp/accuracy/ellipsis_n_bar_2": 0.881, "blimp/accuracy/principle_A_domain_3": 0.481, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.85, "blimp/accuracy/animate_subject_trans": 0.865, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.73, "blimp/accuracy/distractor_agreement_relative_clause": 0.479, "blimp/accuracy/transitive": 0.804, "blimp/accuracy/sentential_subject_island": 0.331, "blimp/accuracy/adjunct_island": 0.672, "blimp/accuracy/intransitive": 0.692, "blimp/accuracy/existential_there_subject_raising": 0.848, "blimp/accuracy/irregular_past_participle_adjectives": 0.925, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.169, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.111, "blimp/accuracy/only_npi_scope": 0.659, "blimp/accuracy/superlative_quantifiers_2": 0.851, "blimp/accuracy/passive_1": 0.88, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.865, "blimp/accuracy/inchoative": 0.534, "blimp/accuracy/anaphor_gender_agreement": 0.934, "blimp/accuracy/principle_A_c_command": 0.541, "blimp/accuracy/only_npi_licensor_present": 0.635, "blimp/accuracy/expletive_it_object_raising": 0.742, "blimp/accuracy/left_branch_island_simple_question": 0.224, "blimp/accuracy/wh_questions_subject_gap": 0.902, "blimp/accuracy/existential_there_quantifiers_2": 0.406, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.886, "blimp/accuracy/sentential_negation_npi_scope": 0.391, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.82, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.943, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.868, "blimp/accuracy/principle_A_case_2": 0.929, "blimp/accuracy/distractor_agreement_relational_noun": 0.732, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.975, "blimp/accuracy/superlative_quantifiers_1": 0.69, "blimp/accuracy/wh_island": 0.778, "blimp/accuracy/principle_A_domain_1": 0.985, "blimp/accuracy/complex_NP_island": 0.582, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.934, "blimp/accuracy/irregular_past_participle_verbs": 0.779, "blimp/accuracy/drop_argument": 0.718, "blimp/accuracy/wh_questions_object_gap": 0.767, "blimp/accuracy/animate_subject_passive": 0.766, "blimp/accuracy/existential_there_quantifiers_1": 0.971, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.837, "blimp/accuracy/npi_present_2": 0.561, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.828, "blimp/accuracy/anaphor_number_agreement": 0.976, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.899, "blimp/accuracy/existential_there_object_raising": 0.751, "blimp/accuracy/matrix_question_npi_licensor_present": 0.118, "blimp/accuracy/npi_present_1": 0.532, "blimp/accuracy/wh_vs_that_no_gap": 0.975, "blimp/accuracy/left_branch_island_echo_question": 0.565, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.984, "blimp/accuracy/causative": 0.608, "blimp/accuracy/group_average": 0.7236417910447761, "blimp/accuracy/seq_average": 0.7236417910447761, "cbt/accuracy/NE": 0.6991185897435898, "cbt/accuracy/V": 0.86, "cbt/accuracy/CN": 0.7368, "cbt/accuracy/P": 0.84, "cbt/accuracy/group_average": 0.7839796474358974, "cbt/accuracy/seq_average": 0.7840136054421769, "hellaswag/accuracy/val": 0.2740489942242581, "hellaswag/accuracy/group_average": 0.2740489942242581, "hellaswag/accuracy/seq_average": 0.2740489942242581, "piqa/accuracy/val": 0.5636561479869423, "piqa/accuracy/group_average": 0.5636561479869423, "piqa/accuracy/seq_average": 0.5636561479869423, "ai2arc/accuracy/ARC-Easy": 0.31331923890063423, "ai2arc/accuracy/ARC-Challenge": 0.20085836909871244, "ai2arc/accuracy/group_average": 0.2570888039996733, "ai2arc/accuracy/seq_average": 0.2762039660056657, "race/accuracy/test/high": 0.2524299599771298, "race/accuracy/test/middle": 0.32590529247910865, "race/accuracy/group_average": 0.2891676262281192, "race/accuracy/seq_average": 0.2738143494122416, "siqa/accuracy/dev": 0.35670419651995905, "siqa/accuracy/group_average": 0.35670419651995905, "siqa/accuracy/seq_average": 0.35670419651995905, "commonsenseqa/accuracy/dev_rand_split": 0.22932022932022933, "commonsenseqa/accuracy/group_average": 0.22932022932022933, "commonsenseqa/accuracy/seq_average": 0.22932022932022933}
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-100000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.6106809585813493, "val/accuracy": 0.4798719618055556, "val/perplexity": 13.608314395893634, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.7588478230541535, "lambada/accuracy/total": 0.24883540372670807, "lambada/accuracy/openai_last_token": 0.7618400621118012, "lambada/perplexity": 11.91786262717185, "lambada/lm_loss": 3.1709826891164785, "lambada/lm_perplexity": 23.83089121114353, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.36435368276613184, "mean_loss": 2.6847643908177514, "blimp/accuracy/passive_2": 0.928, "blimp/accuracy/determiner_noun_agreement_2": 0.99, "blimp/accuracy/ellipsis_n_bar_1": 0.813, "blimp/accuracy/tough_vs_raising_2": 0.876, "blimp/accuracy/tough_vs_raising_1": 0.602, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.918, "blimp/accuracy/principle_A_reconstruction": 0.379, "blimp/accuracy/wh_vs_that_with_gap": 0.517, "blimp/accuracy/principle_A_domain_2": 0.826, "blimp/accuracy/determiner_noun_agreement_1": 0.984, "blimp/accuracy/ellipsis_n_bar_2": 0.902, "blimp/accuracy/principle_A_domain_3": 0.559, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.907, "blimp/accuracy/animate_subject_trans": 0.899, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.878, "blimp/accuracy/distractor_agreement_relative_clause": 0.686, "blimp/accuracy/transitive": 0.877, "blimp/accuracy/sentential_subject_island": 0.303, "blimp/accuracy/adjunct_island": 0.818, "blimp/accuracy/intransitive": 0.806, "blimp/accuracy/existential_there_subject_raising": 0.865, "blimp/accuracy/irregular_past_participle_adjectives": 0.93, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.281, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.294, "blimp/accuracy/only_npi_scope": 0.726, "blimp/accuracy/superlative_quantifiers_2": 0.857, "blimp/accuracy/passive_1": 0.915, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.922, "blimp/accuracy/inchoative": 0.625, "blimp/accuracy/anaphor_gender_agreement": 0.957, "blimp/accuracy/principle_A_c_command": 0.584, "blimp/accuracy/only_npi_licensor_present": 0.649, "blimp/accuracy/expletive_it_object_raising": 0.759, "blimp/accuracy/left_branch_island_simple_question": 0.397, "blimp/accuracy/wh_questions_subject_gap": 0.92, "blimp/accuracy/existential_there_quantifiers_2": 0.5, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.937, "blimp/accuracy/sentential_negation_npi_scope": 0.602, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.839, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.882, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.909, "blimp/accuracy/principle_A_case_2": 0.954, "blimp/accuracy/distractor_agreement_relational_noun": 0.868, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.979, "blimp/accuracy/superlative_quantifiers_1": 0.678, "blimp/accuracy/wh_island": 0.814, "blimp/accuracy/principle_A_domain_1": 0.986, "blimp/accuracy/complex_NP_island": 0.555, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.982, "blimp/accuracy/irregular_past_participle_verbs": 0.904, "blimp/accuracy/drop_argument": 0.768, "blimp/accuracy/wh_questions_object_gap": 0.779, "blimp/accuracy/animate_subject_passive": 0.794, "blimp/accuracy/existential_there_quantifiers_1": 0.98, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.867, "blimp/accuracy/npi_present_2": 0.61, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.917, "blimp/accuracy/anaphor_number_agreement": 0.988, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.947, "blimp/accuracy/existential_there_object_raising": 0.795, "blimp/accuracy/matrix_question_npi_licensor_present": 0.256, "blimp/accuracy/npi_present_1": 0.54, "blimp/accuracy/wh_vs_that_no_gap": 0.966, "blimp/accuracy/left_branch_island_echo_question": 0.405, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.967, "blimp/accuracy/causative": 0.696, "blimp/accuracy/group_average": 0.7733283582089552, "blimp/accuracy/seq_average": 0.7733283582089552, "cbt/accuracy/NE": 0.7644230769230769, "cbt/accuracy/V": 0.9072, "cbt/accuracy/CN": 0.8244, "cbt/accuracy/P": 0.8824, "cbt/accuracy/group_average": 0.8446057692307692, "cbt/accuracy/seq_average": 0.8446378551420568, "hellaswag/accuracy/val": 0.2922724556861183, "hellaswag/accuracy/group_average": 0.2922724556861183, "hellaswag/accuracy/seq_average": 0.2922724556861183, "piqa/accuracy/val": 0.588139281828074, "piqa/accuracy/group_average": 0.588139281828074, "piqa/accuracy/seq_average": 0.588139281828074, "ai2arc/accuracy/ARC-Easy": 0.32727272727272727, "ai2arc/accuracy/ARC-Challenge": 0.21802575107296138, "ai2arc/accuracy/group_average": 0.27264923917284434, "ai2arc/accuracy/seq_average": 0.29121813031161475, "race/accuracy/test/high": 0.27358490566037735, "race/accuracy/test/middle": 0.34401114206128136, "race/accuracy/group_average": 0.30879802386082933, "race/accuracy/seq_average": 0.2940818808269153, "siqa/accuracy/dev": 0.36284544524053225, "siqa/accuracy/group_average": 0.36284544524053225, "siqa/accuracy/seq_average": 0.36284544524053225, "commonsenseqa/accuracy/dev_rand_split": 0.25225225225225223, "commonsenseqa/accuracy/group_average": 0.25225225225225223, "commonsenseqa/accuracy/seq_average": 0.25225225225225223}
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-20000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.8785952613467263, "val/accuracy": 0.44216192336309523, "val/perplexity": 17.789266349639295, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.6511734672214673, "lambada/accuracy/total": 0.19778726708074534, "lambada/accuracy/openai_last_token": 0.7373835403726708, "lambada/perplexity": 17.69416913577623, "lambada/lm_loss": 3.405469522620225, "lambada/lm_perplexity": 30.128438386842557, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3199745952219203, "mean_loss": 2.7648843642840966, "blimp/accuracy/passive_2": 0.88, "blimp/accuracy/determiner_noun_agreement_2": 0.965, "blimp/accuracy/ellipsis_n_bar_1": 0.789, "blimp/accuracy/tough_vs_raising_2": 0.881, "blimp/accuracy/tough_vs_raising_1": 0.584, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.918, "blimp/accuracy/principle_A_reconstruction": 0.398, "blimp/accuracy/wh_vs_that_with_gap": 0.47, "blimp/accuracy/principle_A_domain_2": 0.784, "blimp/accuracy/determiner_noun_agreement_1": 0.977, "blimp/accuracy/ellipsis_n_bar_2": 0.882, "blimp/accuracy/principle_A_domain_3": 0.547, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.884, "blimp/accuracy/animate_subject_trans": 0.861, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.831, "blimp/accuracy/distractor_agreement_relative_clause": 0.615, "blimp/accuracy/transitive": 0.844, "blimp/accuracy/sentential_subject_island": 0.395, "blimp/accuracy/adjunct_island": 0.725, "blimp/accuracy/intransitive": 0.737, "blimp/accuracy/existential_there_subject_raising": 0.836, "blimp/accuracy/irregular_past_participle_adjectives": 0.911, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.224, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.117, "blimp/accuracy/only_npi_scope": 0.677, "blimp/accuracy/superlative_quantifiers_2": 0.846, "blimp/accuracy/passive_1": 0.888, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.905, "blimp/accuracy/inchoative": 0.569, "blimp/accuracy/anaphor_gender_agreement": 0.892, "blimp/accuracy/principle_A_c_command": 0.552, "blimp/accuracy/only_npi_licensor_present": 0.708, "blimp/accuracy/expletive_it_object_raising": 0.723, "blimp/accuracy/left_branch_island_simple_question": 0.328, "blimp/accuracy/wh_questions_subject_gap": 0.919, "blimp/accuracy/existential_there_quantifiers_2": 0.42, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.896, "blimp/accuracy/sentential_negation_npi_scope": 0.425, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.773, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.924, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.9, "blimp/accuracy/principle_A_case_2": 0.953, "blimp/accuracy/distractor_agreement_relational_noun": 0.866, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.947, "blimp/accuracy/superlative_quantifiers_1": 0.77, "blimp/accuracy/wh_island": 0.832, "blimp/accuracy/principle_A_domain_1": 0.994, "blimp/accuracy/complex_NP_island": 0.541, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.937, "blimp/accuracy/irregular_past_participle_verbs": 0.864, "blimp/accuracy/drop_argument": 0.758, "blimp/accuracy/wh_questions_object_gap": 0.79, "blimp/accuracy/animate_subject_passive": 0.782, "blimp/accuracy/existential_there_quantifiers_1": 0.992, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.879, "blimp/accuracy/npi_present_2": 0.557, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.889, "blimp/accuracy/anaphor_number_agreement": 0.974, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.923, "blimp/accuracy/existential_there_object_raising": 0.733, "blimp/accuracy/matrix_question_npi_licensor_present": 0.229, "blimp/accuracy/npi_present_1": 0.549, "blimp/accuracy/wh_vs_that_no_gap": 0.966, "blimp/accuracy/left_branch_island_echo_question": 0.385, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.992, "blimp/accuracy/causative": 0.669, "blimp/accuracy/group_average": 0.7488208955223878, "blimp/accuracy/seq_average": 0.7488208955223881, "cbt/accuracy/NE": 0.7059294871794872, "cbt/accuracy/V": 0.8816, "cbt/accuracy/CN": 0.7692, "cbt/accuracy/P": 0.8632, "cbt/accuracy/group_average": 0.8049823717948719, "cbt/accuracy/seq_average": 0.8050220088035214, "hellaswag/accuracy/val": 0.28141804421429994, "hellaswag/accuracy/group_average": 0.28141804421429994, "hellaswag/accuracy/seq_average": 0.28141804421429994, "piqa/accuracy/val": 0.558215451577802, "piqa/accuracy/group_average": 0.558215451577802, "piqa/accuracy/seq_average": 0.558215451577802, "ai2arc/accuracy/ARC-Easy": 0.32346723044397463, "ai2arc/accuracy/ARC-Challenge": 0.1965665236051502, "ai2arc/accuracy/group_average": 0.26001687702456244, "ai2arc/accuracy/seq_average": 0.28158640226628895, "race/accuracy/test/high": 0.25614636935391655, "race/accuracy/test/middle": 0.334958217270195, "race/accuracy/group_average": 0.2955522933120558, "race/accuracy/seq_average": 0.27908390758005674, "siqa/accuracy/dev": 0.3587512794268168, "siqa/accuracy/group_average": 0.3587512794268168, "siqa/accuracy/seq_average": 0.3587512794268168, "commonsenseqa/accuracy/dev_rand_split": 0.23423423423423423, "commonsenseqa/accuracy/group_average": 0.23423423423423423, "commonsenseqa/accuracy/seq_average": 0.23423423423423423}
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-30000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.8043317037915427, "val/accuracy": 0.45220365978422616, "val/perplexity": 16.516034613735588, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.739962939149845, "lambada/accuracy/total": 0.21739130434782608, "lambada/accuracy/openai_last_token": 0.7443711180124224, "lambada/perplexity": 16.174147105304424, "lambada/lm_loss": 3.359235142644027, "lambada/lm_perplexity": 28.767179673615498, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3347974820660261, "mean_loss": 2.772147321470694, "blimp/accuracy/passive_2": 0.897, "blimp/accuracy/determiner_noun_agreement_2": 0.982, "blimp/accuracy/ellipsis_n_bar_1": 0.806, "blimp/accuracy/tough_vs_raising_2": 0.864, "blimp/accuracy/tough_vs_raising_1": 0.613, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.905, "blimp/accuracy/principle_A_reconstruction": 0.553, "blimp/accuracy/wh_vs_that_with_gap": 0.548, "blimp/accuracy/principle_A_domain_2": 0.803, "blimp/accuracy/determiner_noun_agreement_1": 0.981, "blimp/accuracy/ellipsis_n_bar_2": 0.879, "blimp/accuracy/principle_A_domain_3": 0.543, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.906, "blimp/accuracy/animate_subject_trans": 0.881, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.869, "blimp/accuracy/distractor_agreement_relative_clause": 0.639, "blimp/accuracy/transitive": 0.837, "blimp/accuracy/sentential_subject_island": 0.343, "blimp/accuracy/adjunct_island": 0.777, "blimp/accuracy/intransitive": 0.775, "blimp/accuracy/existential_there_subject_raising": 0.874, "blimp/accuracy/irregular_past_participle_adjectives": 0.893, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.2, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.253, "blimp/accuracy/only_npi_scope": 0.779, "blimp/accuracy/superlative_quantifiers_2": 0.806, "blimp/accuracy/passive_1": 0.885, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.904, "blimp/accuracy/inchoative": 0.624, "blimp/accuracy/anaphor_gender_agreement": 0.946, "blimp/accuracy/principle_A_c_command": 0.551, "blimp/accuracy/only_npi_licensor_present": 0.502, "blimp/accuracy/expletive_it_object_raising": 0.778, "blimp/accuracy/left_branch_island_simple_question": 0.283, "blimp/accuracy/wh_questions_subject_gap": 0.913, "blimp/accuracy/existential_there_quantifiers_2": 0.299, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.924, "blimp/accuracy/sentential_negation_npi_scope": 0.55, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.828, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.878, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.898, "blimp/accuracy/principle_A_case_2": 0.931, "blimp/accuracy/distractor_agreement_relational_noun": 0.804, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.972, "blimp/accuracy/superlative_quantifiers_1": 0.662, "blimp/accuracy/wh_island": 0.799, "blimp/accuracy/principle_A_domain_1": 0.977, "blimp/accuracy/complex_NP_island": 0.525, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.968, "blimp/accuracy/irregular_past_participle_verbs": 0.828, "blimp/accuracy/drop_argument": 0.785, "blimp/accuracy/wh_questions_object_gap": 0.733, "blimp/accuracy/animate_subject_passive": 0.817, "blimp/accuracy/existential_there_quantifiers_1": 0.968, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.87, "blimp/accuracy/npi_present_2": 0.571, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.909, "blimp/accuracy/anaphor_number_agreement": 0.974, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.928, "blimp/accuracy/existential_there_object_raising": 0.769, "blimp/accuracy/matrix_question_npi_licensor_present": 0.269, "blimp/accuracy/npi_present_1": 0.535, "blimp/accuracy/wh_vs_that_no_gap": 0.95, "blimp/accuracy/left_branch_island_echo_question": 0.368, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.974, "blimp/accuracy/causative": 0.65, "blimp/accuracy/group_average": 0.7538059701492534, "blimp/accuracy/seq_average": 0.7538059701492538, "cbt/accuracy/NE": 0.7379807692307693, "cbt/accuracy/V": 0.8888, "cbt/accuracy/CN": 0.7948, "cbt/accuracy/P": 0.8696, "cbt/accuracy/group_average": 0.8227951923076924, "cbt/accuracy/seq_average": 0.822829131652661, "hellaswag/accuracy/val": 0.2810197171878112, "hellaswag/accuracy/group_average": 0.2810197171878112, "hellaswag/accuracy/seq_average": 0.2810197171878112, "piqa/accuracy/val": 0.5761697497279652, "piqa/accuracy/group_average": 0.5761697497279652, "piqa/accuracy/seq_average": 0.5761697497279652, "ai2arc/accuracy/ARC-Easy": 0.3150105708245243, "ai2arc/accuracy/ARC-Challenge": 0.20772532188841203, "ai2arc/accuracy/group_average": 0.2613679463564682, "ai2arc/accuracy/seq_average": 0.27960339943342777, "race/accuracy/test/high": 0.25986277873070324, "race/accuracy/test/middle": 0.32381615598885793, "race/accuracy/group_average": 0.2918394673597806, "race/accuracy/seq_average": 0.27847588163761655, "siqa/accuracy/dev": 0.35977482088024565, "siqa/accuracy/group_average": 0.35977482088024565, "siqa/accuracy/seq_average": 0.35977482088024565, "commonsenseqa/accuracy/dev_rand_split": 0.23095823095823095, "commonsenseqa/accuracy/group_average": 0.23095823095823095, "commonsenseqa/accuracy/seq_average": 0.23095823095823095}
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-40000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.7547452411954363, "val/accuracy": 0.45854937841021826, "val/perplexity": 15.717036339337263, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.645799340668672, "lambada/accuracy/total": 0.21622670807453417, "lambada/accuracy/openai_last_token": 0.749805900621118, "lambada/perplexity": 15.202837121146974, "lambada/lm_loss": 3.2904543949781258, "lambada/lm_perplexity": 26.855063689949507, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3373880432423762, "mean_loss": 2.7002722909320545, "blimp/accuracy/passive_2": 0.89, "blimp/accuracy/determiner_noun_agreement_2": 0.979, "blimp/accuracy/ellipsis_n_bar_1": 0.823, "blimp/accuracy/tough_vs_raising_2": 0.861, "blimp/accuracy/tough_vs_raising_1": 0.6, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.916, "blimp/accuracy/principle_A_reconstruction": 0.409, "blimp/accuracy/wh_vs_that_with_gap": 0.506, "blimp/accuracy/principle_A_domain_2": 0.766, "blimp/accuracy/determiner_noun_agreement_1": 0.982, "blimp/accuracy/ellipsis_n_bar_2": 0.891, "blimp/accuracy/principle_A_domain_3": 0.534, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.931, "blimp/accuracy/animate_subject_trans": 0.886, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.878, "blimp/accuracy/distractor_agreement_relative_clause": 0.671, "blimp/accuracy/transitive": 0.848, "blimp/accuracy/sentential_subject_island": 0.314, "blimp/accuracy/adjunct_island": 0.844, "blimp/accuracy/intransitive": 0.789, "blimp/accuracy/existential_there_subject_raising": 0.873, "blimp/accuracy/irregular_past_participle_adjectives": 0.889, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.228, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.228, "blimp/accuracy/only_npi_scope": 0.721, "blimp/accuracy/superlative_quantifiers_2": 0.882, "blimp/accuracy/passive_1": 0.89, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.88, "blimp/accuracy/inchoative": 0.597, "blimp/accuracy/anaphor_gender_agreement": 0.951, "blimp/accuracy/principle_A_c_command": 0.557, "blimp/accuracy/only_npi_licensor_present": 0.762, "blimp/accuracy/expletive_it_object_raising": 0.764, "blimp/accuracy/left_branch_island_simple_question": 0.351, "blimp/accuracy/wh_questions_subject_gap": 0.925, "blimp/accuracy/existential_there_quantifiers_2": 0.347, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.921, "blimp/accuracy/sentential_negation_npi_scope": 0.518, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.792, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.891, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.907, "blimp/accuracy/principle_A_case_2": 0.958, "blimp/accuracy/distractor_agreement_relational_noun": 0.886, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.982, "blimp/accuracy/superlative_quantifiers_1": 0.738, "blimp/accuracy/wh_island": 0.72, "blimp/accuracy/principle_A_domain_1": 0.988, "blimp/accuracy/complex_NP_island": 0.543, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.965, "blimp/accuracy/irregular_past_participle_verbs": 0.88, "blimp/accuracy/drop_argument": 0.763, "blimp/accuracy/wh_questions_object_gap": 0.77, "blimp/accuracy/animate_subject_passive": 0.801, "blimp/accuracy/existential_there_quantifiers_1": 0.971, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.879, "blimp/accuracy/npi_present_2": 0.536, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.901, "blimp/accuracy/anaphor_number_agreement": 0.983, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.943, "blimp/accuracy/existential_there_object_raising": 0.778, "blimp/accuracy/matrix_question_npi_licensor_present": 0.223, "blimp/accuracy/npi_present_1": 0.461, "blimp/accuracy/wh_vs_that_no_gap": 0.977, "blimp/accuracy/left_branch_island_echo_question": 0.367, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.982, "blimp/accuracy/causative": 0.649, "blimp/accuracy/group_average": 0.7587462686567163, "blimp/accuracy/seq_average": 0.7587462686567165, "cbt/accuracy/NE": 0.7435897435897436, "cbt/accuracy/V": 0.8964, "cbt/accuracy/CN": 0.802, "cbt/accuracy/P": 0.8688, "cbt/accuracy/group_average": 0.8276974358974358, "cbt/accuracy/seq_average": 0.8277310924369747, "hellaswag/accuracy/val": 0.2862975502887871, "hellaswag/accuracy/group_average": 0.2862975502887871, "hellaswag/accuracy/seq_average": 0.2862975502887871, "piqa/accuracy/val": 0.573449401523395, "piqa/accuracy/group_average": 0.573449401523395, "piqa/accuracy/seq_average": 0.573449401523395, "ai2arc/accuracy/ARC-Easy": 0.3226215644820296, "ai2arc/accuracy/ARC-Challenge": 0.20515021459227467, "ai2arc/accuracy/group_average": 0.26388588953715214, "ai2arc/accuracy/seq_average": 0.28385269121813034, "race/accuracy/test/high": 0.2667238421955403, "race/accuracy/test/middle": 0.33774373259052926, "race/accuracy/group_average": 0.30223378739303475, "race/accuracy/seq_average": 0.287393595460073, "siqa/accuracy/dev": 0.36745138178096215, "siqa/accuracy/group_average": 0.36745138178096215, "siqa/accuracy/seq_average": 0.36745138178096215, "commonsenseqa/accuracy/dev_rand_split": 0.24078624078624078, "commonsenseqa/accuracy/group_average": 0.24078624078624078, "commonsenseqa/accuracy/seq_average": 0.24078624078624078}
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-60000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.6784188406808034, "val/accuracy": 0.469940669952877, "val/perplexity": 14.562050161928429, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.7510167471370344, "lambada/accuracy/total": 0.23369565217391305, "lambada/accuracy/openai_last_token": 0.7515527950310559, "lambada/perplexity": 13.177129933926992, "lambada/lm_loss": 3.2212108608927403, "lambada/lm_perplexity": 25.05844410860798, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.35181816106339503, "mean_loss": 2.714717793908919, "blimp/accuracy/passive_2": 0.917, "blimp/accuracy/determiner_noun_agreement_2": 0.985, "blimp/accuracy/ellipsis_n_bar_1": 0.805, "blimp/accuracy/tough_vs_raising_2": 0.893, "blimp/accuracy/tough_vs_raising_1": 0.574, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.918, "blimp/accuracy/principle_A_reconstruction": 0.288, "blimp/accuracy/wh_vs_that_with_gap": 0.495, "blimp/accuracy/principle_A_domain_2": 0.812, "blimp/accuracy/determiner_noun_agreement_1": 0.979, "blimp/accuracy/ellipsis_n_bar_2": 0.898, "blimp/accuracy/principle_A_domain_3": 0.553, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.917, "blimp/accuracy/animate_subject_trans": 0.908, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.89, "blimp/accuracy/distractor_agreement_relative_clause": 0.642, "blimp/accuracy/transitive": 0.865, "blimp/accuracy/sentential_subject_island": 0.322, "blimp/accuracy/adjunct_island": 0.812, "blimp/accuracy/intransitive": 0.803, "blimp/accuracy/existential_there_subject_raising": 0.873, "blimp/accuracy/irregular_past_participle_adjectives": 0.921, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.277, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.246, "blimp/accuracy/only_npi_scope": 0.765, "blimp/accuracy/superlative_quantifiers_2": 0.846, "blimp/accuracy/passive_1": 0.9, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.905, "blimp/accuracy/inchoative": 0.632, "blimp/accuracy/anaphor_gender_agreement": 0.964, "blimp/accuracy/principle_A_c_command": 0.589, "blimp/accuracy/only_npi_licensor_present": 0.586, "blimp/accuracy/expletive_it_object_raising": 0.764, "blimp/accuracy/left_branch_island_simple_question": 0.389, "blimp/accuracy/wh_questions_subject_gap": 0.937, "blimp/accuracy/existential_there_quantifiers_2": 0.425, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.928, "blimp/accuracy/sentential_negation_npi_scope": 0.578, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.831, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.869, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.887, "blimp/accuracy/principle_A_case_2": 0.958, "blimp/accuracy/distractor_agreement_relational_noun": 0.807, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.979, "blimp/accuracy/superlative_quantifiers_1": 0.797, "blimp/accuracy/wh_island": 0.844, "blimp/accuracy/principle_A_domain_1": 0.993, "blimp/accuracy/complex_NP_island": 0.556, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.974, "blimp/accuracy/irregular_past_participle_verbs": 0.883, "blimp/accuracy/drop_argument": 0.756, "blimp/accuracy/wh_questions_object_gap": 0.806, "blimp/accuracy/animate_subject_passive": 0.78, "blimp/accuracy/existential_there_quantifiers_1": 0.975, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.866, "blimp/accuracy/npi_present_2": 0.595, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.918, "blimp/accuracy/anaphor_number_agreement": 0.99, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.947, "blimp/accuracy/existential_there_object_raising": 0.792, "blimp/accuracy/matrix_question_npi_licensor_present": 0.254, "blimp/accuracy/npi_present_1": 0.521, "blimp/accuracy/wh_vs_that_no_gap": 0.973, "blimp/accuracy/left_branch_island_echo_question": 0.378, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.981, "blimp/accuracy/causative": 0.686, "blimp/accuracy/group_average": 0.7671194029850746, "blimp/accuracy/seq_average": 0.7671194029850746, "cbt/accuracy/NE": 0.7532051282051282, "cbt/accuracy/V": 0.9064, "cbt/accuracy/CN": 0.812, "cbt/accuracy/P": 0.8784, "cbt/accuracy/group_average": 0.8375012820512822, "cbt/accuracy/seq_average": 0.8375350140056023, "hellaswag/accuracy/val": 0.2853017327225652, "hellaswag/accuracy/group_average": 0.2853017327225652, "hellaswag/accuracy/seq_average": 0.2853017327225652, "piqa/accuracy/val": 0.5750816104461371, "piqa/accuracy/group_average": 0.5750816104461371, "piqa/accuracy/seq_average": 0.5750816104461371, "ai2arc/accuracy/ARC-Easy": 0.32642706131078225, "ai2arc/accuracy/ARC-Challenge": 0.21030042918454936, "ai2arc/accuracy/group_average": 0.2683637452476658, "ai2arc/accuracy/seq_average": 0.28810198300283285, "race/accuracy/test/high": 0.2698684962835906, "race/accuracy/test/middle": 0.346100278551532, "race/accuracy/group_average": 0.3079843874175613, "race/accuracy/seq_average": 0.2920551276854479, "siqa/accuracy/dev": 0.3638689866939611, "siqa/accuracy/group_average": 0.3638689866939611, "siqa/accuracy/seq_average": 0.3638689866939611, "commonsenseqa/accuracy/dev_rand_split": 0.2538902538902539, "commonsenseqa/accuracy/group_average": 0.2538902538902539, "commonsenseqa/accuracy/seq_average": 0.2538902538902539}
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-70000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.652042691669767, "val/accuracy": 0.47436620318700395, "val/perplexity": 14.182980531821897, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.7163078355493013, "lambada/accuracy/total": 0.22903726708074534, "lambada/accuracy/openai_last_token": 0.7542701863354038, "lambada/perplexity": 13.154989248938678, "lambada/lm_loss": 3.2131376343049665, "lambada/lm_perplexity": 24.856956035182154, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.35170173513387465, "mean_loss": 2.684175263609534, "blimp/accuracy/passive_2": 0.913, "blimp/accuracy/determiner_noun_agreement_2": 0.978, "blimp/accuracy/ellipsis_n_bar_1": 0.821, "blimp/accuracy/tough_vs_raising_2": 0.867, "blimp/accuracy/tough_vs_raising_1": 0.591, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.9, "blimp/accuracy/principle_A_reconstruction": 0.309, "blimp/accuracy/wh_vs_that_with_gap": 0.48, "blimp/accuracy/principle_A_domain_2": 0.813, "blimp/accuracy/determiner_noun_agreement_1": 0.986, "blimp/accuracy/ellipsis_n_bar_2": 0.884, "blimp/accuracy/principle_A_domain_3": 0.569, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.889, "blimp/accuracy/animate_subject_trans": 0.902, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.873, "blimp/accuracy/distractor_agreement_relative_clause": 0.659, "blimp/accuracy/transitive": 0.863, "blimp/accuracy/sentential_subject_island": 0.321, "blimp/accuracy/adjunct_island": 0.816, "blimp/accuracy/intransitive": 0.777, "blimp/accuracy/existential_there_subject_raising": 0.873, "blimp/accuracy/irregular_past_participle_adjectives": 0.974, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.235, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.257, "blimp/accuracy/only_npi_scope": 0.778, "blimp/accuracy/superlative_quantifiers_2": 0.815, "blimp/accuracy/passive_1": 0.905, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.884, "blimp/accuracy/inchoative": 0.638, "blimp/accuracy/anaphor_gender_agreement": 0.966, "blimp/accuracy/principle_A_c_command": 0.548, "blimp/accuracy/only_npi_licensor_present": 0.416, "blimp/accuracy/expletive_it_object_raising": 0.759, "blimp/accuracy/left_branch_island_simple_question": 0.348, "blimp/accuracy/wh_questions_subject_gap": 0.939, "blimp/accuracy/existential_there_quantifiers_2": 0.431, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.913, "blimp/accuracy/sentential_negation_npi_scope": 0.611, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.837, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.885, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.912, "blimp/accuracy/principle_A_case_2": 0.953, "blimp/accuracy/distractor_agreement_relational_noun": 0.845, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.982, "blimp/accuracy/superlative_quantifiers_1": 0.668, "blimp/accuracy/wh_island": 0.803, "blimp/accuracy/principle_A_domain_1": 0.985, "blimp/accuracy/complex_NP_island": 0.541, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.978, "blimp/accuracy/irregular_past_participle_verbs": 0.9, "blimp/accuracy/drop_argument": 0.75, "blimp/accuracy/wh_questions_object_gap": 0.804, "blimp/accuracy/animate_subject_passive": 0.783, "blimp/accuracy/existential_there_quantifiers_1": 0.975, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.872, "blimp/accuracy/npi_present_2": 0.578, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.913, "blimp/accuracy/anaphor_number_agreement": 0.987, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.945, "blimp/accuracy/existential_there_object_raising": 0.805, "blimp/accuracy/matrix_question_npi_licensor_present": 0.25, "blimp/accuracy/npi_present_1": 0.485, "blimp/accuracy/wh_vs_that_no_gap": 0.969, "blimp/accuracy/left_branch_island_echo_question": 0.375, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.977, "blimp/accuracy/causative": 0.685, "blimp/accuracy/group_average": 0.7603432835820896, "blimp/accuracy/seq_average": 0.7603432835820896, "cbt/accuracy/NE": 0.7580128205128205, "cbt/accuracy/V": 0.9048, "cbt/accuracy/CN": 0.8228, "cbt/accuracy/P": 0.8796, "cbt/accuracy/group_average": 0.8413032051282051, "cbt/accuracy/seq_average": 0.8413365346138455, "hellaswag/accuracy/val": 0.2925712009559849, "hellaswag/accuracy/group_average": 0.2925712009559849, "hellaswag/accuracy/seq_average": 0.2925712009559849, "piqa/accuracy/val": 0.5924918389553863, "piqa/accuracy/group_average": 0.5924918389553863, "piqa/accuracy/seq_average": 0.5924918389553863, "ai2arc/accuracy/ARC-Easy": 0.3298097251585624, "ai2arc/accuracy/ARC-Challenge": 0.20257510729613734, "ai2arc/accuracy/group_average": 0.26619241622734985, "ai2arc/accuracy/seq_average": 0.2878186968838527, "race/accuracy/test/high": 0.2715837621497999, "race/accuracy/test/middle": 0.32729805013927576, "race/accuracy/group_average": 0.29944090614453783, "race/accuracy/seq_average": 0.2877989460883664, "siqa/accuracy/dev": 0.36489252814739, "siqa/accuracy/group_average": 0.36489252814739, "siqa/accuracy/seq_average": 0.36489252814739, "commonsenseqa/accuracy/dev_rand_split": 0.26453726453726456, "commonsenseqa/accuracy/group_average": 0.26453726453726456, "commonsenseqa/accuracy/seq_average": 0.26453726453726456}
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-80000.pth.json ADDED
File without changes
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_unigram/export/result-model-90000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.6180616106305803, "val/accuracy": 0.4787646096850198, "val/perplexity": 13.709124192817526, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.6515226186432455, "lambada/accuracy/total": 0.2422360248447205, "lambada/accuracy/openai_last_token": 0.7618400621118012, "lambada/perplexity": 12.240854589298449, "lambada/lm_loss": 3.1671777309374947, "lambada/lm_perplexity": 23.74038795645673, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3605003172648702, "mean_loss": 2.634792114636913, "blimp/accuracy/passive_2": 0.924, "blimp/accuracy/determiner_noun_agreement_2": 0.988, "blimp/accuracy/ellipsis_n_bar_1": 0.826, "blimp/accuracy/tough_vs_raising_2": 0.888, "blimp/accuracy/tough_vs_raising_1": 0.597, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.901, "blimp/accuracy/principle_A_reconstruction": 0.313, "blimp/accuracy/wh_vs_that_with_gap": 0.491, "blimp/accuracy/principle_A_domain_2": 0.819, "blimp/accuracy/determiner_noun_agreement_1": 0.985, "blimp/accuracy/ellipsis_n_bar_2": 0.892, "blimp/accuracy/principle_A_domain_3": 0.567, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.924, "blimp/accuracy/animate_subject_trans": 0.902, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.895, "blimp/accuracy/distractor_agreement_relative_clause": 0.678, "blimp/accuracy/transitive": 0.874, "blimp/accuracy/sentential_subject_island": 0.287, "blimp/accuracy/adjunct_island": 0.816, "blimp/accuracy/intransitive": 0.8, "blimp/accuracy/existential_there_subject_raising": 0.866, "blimp/accuracy/irregular_past_participle_adjectives": 0.928, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.263, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.266, "blimp/accuracy/only_npi_scope": 0.73, "blimp/accuracy/superlative_quantifiers_2": 0.791, "blimp/accuracy/passive_1": 0.911, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.906, "blimp/accuracy/inchoative": 0.642, "blimp/accuracy/anaphor_gender_agreement": 0.958, "blimp/accuracy/principle_A_c_command": 0.579, "blimp/accuracy/only_npi_licensor_present": 0.653, "blimp/accuracy/expletive_it_object_raising": 0.781, "blimp/accuracy/left_branch_island_simple_question": 0.364, "blimp/accuracy/wh_questions_subject_gap": 0.938, "blimp/accuracy/existential_there_quantifiers_2": 0.47, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.927, "blimp/accuracy/sentential_negation_npi_scope": 0.538, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.829, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.883, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.887, "blimp/accuracy/principle_A_case_2": 0.942, "blimp/accuracy/distractor_agreement_relational_noun": 0.873, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.975, "blimp/accuracy/superlative_quantifiers_1": 0.666, "blimp/accuracy/wh_island": 0.831, "blimp/accuracy/principle_A_domain_1": 0.986, "blimp/accuracy/complex_NP_island": 0.568, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.976, "blimp/accuracy/irregular_past_participle_verbs": 0.902, "blimp/accuracy/drop_argument": 0.778, "blimp/accuracy/wh_questions_object_gap": 0.808, "blimp/accuracy/animate_subject_passive": 0.783, "blimp/accuracy/existential_there_quantifiers_1": 0.99, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.87, "blimp/accuracy/npi_present_2": 0.619, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.922, "blimp/accuracy/anaphor_number_agreement": 0.992, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.954, "blimp/accuracy/existential_there_object_raising": 0.805, "blimp/accuracy/matrix_question_npi_licensor_present": 0.256, "blimp/accuracy/npi_present_1": 0.552, "blimp/accuracy/wh_vs_that_no_gap": 0.976, "blimp/accuracy/left_branch_island_echo_question": 0.362, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.977, "blimp/accuracy/causative": 0.693, "blimp/accuracy/group_average": 0.769149253731343, "blimp/accuracy/seq_average": 0.7691492537313432, "cbt/accuracy/NE": 0.7652243589743589, "cbt/accuracy/V": 0.908, "cbt/accuracy/CN": 0.8288, "cbt/accuracy/P": 0.8804, "cbt/accuracy/group_average": 0.8456060897435898, "cbt/accuracy/seq_average": 0.8456382553021209, "hellaswag/accuracy/val": 0.29087831109340767, "hellaswag/accuracy/group_average": 0.29087831109340767, "hellaswag/accuracy/seq_average": 0.29087831109340767, "piqa/accuracy/val": 0.5903155603917302, "piqa/accuracy/group_average": 0.5903155603917302, "piqa/accuracy/seq_average": 0.5903155603917302, "ai2arc/accuracy/ARC-Easy": 0.3293868921775899, "ai2arc/accuracy/ARC-Challenge": 0.20858369098712445, "ai2arc/accuracy/group_average": 0.2689852915823572, "ai2arc/accuracy/seq_average": 0.2895184135977337, "race/accuracy/test/high": 0.27387078330474557, "race/accuracy/test/middle": 0.33565459610027853, "race/accuracy/group_average": 0.3047626897025121, "race/accuracy/seq_average": 0.2918524523713012, "siqa/accuracy/dev": 0.36591606960081885, "siqa/accuracy/group_average": 0.36591606960081885, "siqa/accuracy/seq_average": 0.36591606960081885, "commonsenseqa/accuracy/dev_rand_split": 0.24651924651924653, "commonsenseqa/accuracy/group_average": 0.24651924651924653, "commonsenseqa/accuracy/seq_average": 0.24651924651924653}