DavidNguyen commited on
Commit
518e71c
·
verified ·
1 Parent(s): 8b66f3b

cafe10edb19f74ceaee563019bb0770894c23405f666bc475770d78b08e0e127

Browse files
Pretrain_language_model/save/slimpajama_competesmoe_no_attmoe_660M_standardlb_down_flip/export/result-model-360000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.2778657482516382, "val/accuracy": 0.5237318469632056, "val/perplexity": 9.755836762978193, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.152370666124806, "lambada/accuracy/total": 0.38548136645962733, "lambada/accuracy/openai_last_token": 0.8049301242236024, "lambada/perplexity": 6.364111971040649, "lambada/lm_loss": 2.8554696257618963, "lambada/lm_perplexity": 17.38259860721917, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4546066067114165, "mean_loss": 2.215118207188222, "blimp/accuracy/passive_2": 0.914, "blimp/accuracy/determiner_noun_agreement_2": 0.983, "blimp/accuracy/ellipsis_n_bar_1": 0.866, "blimp/accuracy/tough_vs_raising_2": 0.906, "blimp/accuracy/tough_vs_raising_1": 0.573, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.886, "blimp/accuracy/principle_A_reconstruction": 0.474, "blimp/accuracy/wh_vs_that_with_gap": 0.448, "blimp/accuracy/principle_A_domain_2": 0.905, "blimp/accuracy/determiner_noun_agreement_1": 0.995, "blimp/accuracy/ellipsis_n_bar_2": 0.904, "blimp/accuracy/principle_A_domain_3": 0.632, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.934, "blimp/accuracy/animate_subject_trans": 0.904, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.927, "blimp/accuracy/distractor_agreement_relative_clause": 0.676, "blimp/accuracy/transitive": 0.878, "blimp/accuracy/sentential_subject_island": 0.33, "blimp/accuracy/adjunct_island": 0.876, "blimp/accuracy/intransitive": 0.746, "blimp/accuracy/existential_there_subject_raising": 0.887, "blimp/accuracy/irregular_past_participle_adjectives": 0.929, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.749, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.366, "blimp/accuracy/only_npi_scope": 0.655, "blimp/accuracy/superlative_quantifiers_2": 0.845, "blimp/accuracy/passive_1": 0.896, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.913, "blimp/accuracy/inchoative": 0.612, "blimp/accuracy/anaphor_gender_agreement": 0.98, "blimp/accuracy/principle_A_c_command": 0.719, "blimp/accuracy/only_npi_licensor_present": 0.707, "blimp/accuracy/expletive_it_object_raising": 0.77, "blimp/accuracy/left_branch_island_simple_question": 0.835, "blimp/accuracy/wh_questions_subject_gap": 0.937, "blimp/accuracy/existential_there_quantifiers_2": 0.506, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.946, "blimp/accuracy/sentential_negation_npi_scope": 0.75, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.825, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.901, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.892, "blimp/accuracy/principle_A_case_2": 0.922, "blimp/accuracy/distractor_agreement_relational_noun": 0.866, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.974, "blimp/accuracy/superlative_quantifiers_1": 0.823, "blimp/accuracy/wh_island": 0.736, "blimp/accuracy/principle_A_domain_1": 0.997, "blimp/accuracy/complex_NP_island": 0.613, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.974, "blimp/accuracy/irregular_past_participle_verbs": 0.923, "blimp/accuracy/drop_argument": 0.722, "blimp/accuracy/wh_questions_object_gap": 0.858, "blimp/accuracy/animate_subject_passive": 0.795, "blimp/accuracy/existential_there_quantifiers_1": 0.978, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.89, "blimp/accuracy/npi_present_2": 0.583, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.962, "blimp/accuracy/anaphor_number_agreement": 0.991, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.966, "blimp/accuracy/existential_there_object_raising": 0.831, "blimp/accuracy/matrix_question_npi_licensor_present": 0.426, "blimp/accuracy/npi_present_1": 0.577, "blimp/accuracy/wh_vs_that_no_gap": 0.98, "blimp/accuracy/left_branch_island_echo_question": 0.578, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.958, "blimp/accuracy/causative": 0.752, "blimp/accuracy/group_average": 0.8067462686567164, "blimp/accuracy/seq_average": 0.8067462686567164, "cbt/accuracy/NE": 0.8217147435897436, "cbt/accuracy/V": 0.9432, "cbt/accuracy/CN": 0.8892, "cbt/accuracy/P": 0.9212, "cbt/accuracy/group_average": 0.8938286858974358, "cbt/accuracy/seq_average": 0.8938575430172069, "hellaswag/accuracy/val": 0.3732324238199562, "hellaswag/accuracy/group_average": 0.3732324238199562, "hellaswag/accuracy/seq_average": 0.3732324238199562, "piqa/accuracy/val": 0.6349292709466812, "piqa/accuracy/group_average": 0.6349292709466812, "piqa/accuracy/seq_average": 0.6349292709466812, "ai2arc/accuracy/ARC-Easy": 0.38520084566596197, "ai2arc/accuracy/ARC-Challenge": 0.23090128755364808, "ai2arc/accuracy/group_average": 0.308051066609805, "ai2arc/accuracy/seq_average": 0.3342776203966006, "mmlu/accuracy/MMLU": 0.2621380050053629, "mmlu/accuracy/group_average": 0.2621380050053629, "mmlu/accuracy/seq_average": 0.2621380050053629, "openbookqa/accuracy/test": 0.284, "openbookqa/accuracy/group_average": 0.284, "openbookqa/accuracy/seq_average": 0.284, "race/accuracy/test/high": 0.2890222984562607, "race/accuracy/test/middle": 0.3725626740947075, "race/accuracy/group_average": 0.3307924862754841, "race/accuracy/seq_average": 0.3133360356708553, "siqa/accuracy/dev": 0.37871033776867963, "siqa/accuracy/group_average": 0.37871033776867963, "siqa/accuracy/seq_average": 0.37871033776867963, "winogrande/accuracy/dev": 0.5035516969218626, "winogrande/accuracy/group_average": 0.5035516969218626, "winogrande/accuracy/seq_average": 0.5035516969218626, "commonsenseqa/accuracy/dev_rand_split": 0.27682227682227684, "commonsenseqa/accuracy/group_average": 0.27682227682227684, "commonsenseqa/accuracy/seq_average": 0.27682227682227684}
Pretrain_language_model/save/slimpajama_competesmoe_no_attmoe_660M_standardlb_down_flip/export/result-model-380000.pth.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"val/loss": 2.2734333161384828, "val/accuracy": 0.5244495022681451, "val/perplexity": 9.712690371184987, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.161026664402174, "lambada/accuracy/total": 0.3825698757763975, "lambada/accuracy/openai_last_token": 0.8060947204968945, "lambada/perplexity": 6.370929817950676, "lambada/lm_loss": 2.8524791362414432, "lambada/lm_perplexity": 17.330693777353112, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4535096890222713, "mean_loss": 2.2172299902703285, "blimp/accuracy/passive_2": 0.91, "blimp/accuracy/determiner_noun_agreement_2": 0.989, "blimp/accuracy/ellipsis_n_bar_1": 0.867, "blimp/accuracy/tough_vs_raising_2": 0.88, "blimp/accuracy/tough_vs_raising_1": 0.568, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.891, "blimp/accuracy/principle_A_reconstruction": 0.412, "blimp/accuracy/wh_vs_that_with_gap": 0.415, "blimp/accuracy/principle_A_domain_2": 0.889, "blimp/accuracy/determiner_noun_agreement_1": 0.992, "blimp/accuracy/ellipsis_n_bar_2": 0.905, "blimp/accuracy/principle_A_domain_3": 0.612, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.93, "blimp/accuracy/animate_subject_trans": 0.905, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.924, "blimp/accuracy/distractor_agreement_relative_clause": 0.709, "blimp/accuracy/transitive": 0.892, "blimp/accuracy/sentential_subject_island": 0.335, "blimp/accuracy/adjunct_island": 0.861, "blimp/accuracy/intransitive": 0.761, "blimp/accuracy/existential_there_subject_raising": 0.893, "blimp/accuracy/irregular_past_participle_adjectives": 0.976, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.748, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.339, "blimp/accuracy/only_npi_scope": 0.718, "blimp/accuracy/superlative_quantifiers_2": 0.837, "blimp/accuracy/passive_1": 0.896, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.932, "blimp/accuracy/inchoative": 0.613, "blimp/accuracy/anaphor_gender_agreement": 0.983, "blimp/accuracy/principle_A_c_command": 0.702, "blimp/accuracy/only_npi_licensor_present": 0.732, "blimp/accuracy/expletive_it_object_raising": 0.766, "blimp/accuracy/left_branch_island_simple_question": 0.839, "blimp/accuracy/wh_questions_subject_gap": 0.938, "blimp/accuracy/existential_there_quantifiers_2": 0.463, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.94, "blimp/accuracy/sentential_negation_npi_scope": 0.739, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.821, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.899, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.903, "blimp/accuracy/principle_A_case_2": 0.92, "blimp/accuracy/distractor_agreement_relational_noun": 0.852, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.973, "blimp/accuracy/superlative_quantifiers_1": 0.87, "blimp/accuracy/wh_island": 0.741, "blimp/accuracy/principle_A_domain_1": 0.995, "blimp/accuracy/complex_NP_island": 0.606, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.975, "blimp/accuracy/irregular_past_participle_verbs": 0.951, "blimp/accuracy/drop_argument": 0.727, "blimp/accuracy/wh_questions_object_gap": 0.866, "blimp/accuracy/animate_subject_passive": 0.798, "blimp/accuracy/existential_there_quantifiers_1": 0.963, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.894, "blimp/accuracy/npi_present_2": 0.566, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.962, "blimp/accuracy/anaphor_number_agreement": 0.992, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.966, "blimp/accuracy/existential_there_object_raising": 0.843, "blimp/accuracy/matrix_question_npi_licensor_present": 0.405, "blimp/accuracy/npi_present_1": 0.544, "blimp/accuracy/wh_vs_that_no_gap": 0.983, "blimp/accuracy/left_branch_island_echo_question": 0.515, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.965, "blimp/accuracy/causative": 0.756, "blimp/accuracy/group_average": 0.8052537313432835, "blimp/accuracy/seq_average": 0.8052537313432836, "cbt/accuracy/NE": 0.8205128205128205, "cbt/accuracy/V": 0.9424, "cbt/accuracy/CN": 0.89, "cbt/accuracy/P": 0.9236, "cbt/accuracy/group_average": 0.8941282051282051, "cbt/accuracy/seq_average": 0.894157663065226, "hellaswag/accuracy/val": 0.3738299143596893, "hellaswag/accuracy/group_average": 0.3738299143596893, "hellaswag/accuracy/seq_average": 0.3738299143596893, "piqa/accuracy/val": 0.6365614798694232, "piqa/accuracy/group_average": 0.6365614798694232, "piqa/accuracy/seq_average": 0.6365614798694232, "ai2arc/accuracy/ARC-Easy": 0.3864693446088795, "ai2arc/accuracy/ARC-Challenge": 0.23605150214592274, "ai2arc/accuracy/group_average": 0.3112604233774011, "ai2arc/accuracy/seq_average": 0.33682719546742207, "mmlu/accuracy/MMLU": 0.262567036110118, "mmlu/accuracy/group_average": 0.262567036110118, "mmlu/accuracy/seq_average": 0.262567036110118, "openbookqa/accuracy/test": 0.278, "openbookqa/accuracy/group_average": 0.278, "openbookqa/accuracy/seq_average": 0.278, "race/accuracy/test/high": 0.29130931961120643, "race/accuracy/test/middle": 0.36908077994428967, "race/accuracy/group_average": 0.33019504977774805, "race/accuracy/seq_average": 0.3139440616132955, "siqa/accuracy/dev": 0.3751279426816786, "siqa/accuracy/group_average": 0.3751279426816786, "siqa/accuracy/seq_average": 0.3751279426816786, "winogrande/accuracy/dev": 0.5082872928176796, "winogrande/accuracy/group_average": 0.5082872928176796, "winogrande/accuracy/seq_average": 0.5082872928176796, "commonsenseqa/accuracy/dev_rand_split": 0.2719082719082719, "commonsenseqa/accuracy/group_average": 0.2719082719082719, "commonsenseqa/accuracy/seq_average": 0.2719082719082719}