Upload folder using huggingface_hub
#4370
by
DavidNguyen
- opened
Pretrain_language_model/save/slimpajama_competesmoe_no_attmoe_660M_standardlb/export/result-model-280000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.311976771200857, "val/accuracy": 0.5189691358996976, "val/perplexity": 10.094359184046882, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.193172478527756, "lambada/accuracy/total": 0.37577639751552794, "lambada/accuracy/openai_last_token": 0.8016304347826086, "lambada/perplexity": 6.779006294918139, "lambada/lm_loss": 2.8871369140285337, "lambada/lm_perplexity": 17.941866886848043, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4473727667076128, "mean_loss": 2.2525746248643066, "blimp/accuracy/passive_2": 0.912, "blimp/accuracy/determiner_noun_agreement_2": 0.984, "blimp/accuracy/ellipsis_n_bar_1": 0.84, "blimp/accuracy/tough_vs_raising_2": 0.873, "blimp/accuracy/tough_vs_raising_1": 0.603, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.855, "blimp/accuracy/principle_A_reconstruction": 0.421, "blimp/accuracy/wh_vs_that_with_gap": 0.429, "blimp/accuracy/principle_A_domain_2": 0.888, "blimp/accuracy/determiner_noun_agreement_1": 0.989, "blimp/accuracy/ellipsis_n_bar_2": 0.918, "blimp/accuracy/principle_A_domain_3": 0.634, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.92, "blimp/accuracy/animate_subject_trans": 0.902, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.914, "blimp/accuracy/distractor_agreement_relative_clause": 0.726, "blimp/accuracy/transitive": 0.901, "blimp/accuracy/sentential_subject_island": 0.328, "blimp/accuracy/adjunct_island": 0.868, "blimp/accuracy/intransitive": 0.758, "blimp/accuracy/existential_there_subject_raising": 0.909, "blimp/accuracy/irregular_past_participle_adjectives": 0.769, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.725, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.291, "blimp/accuracy/only_npi_scope": 0.679, "blimp/accuracy/superlative_quantifiers_2": 0.782, "blimp/accuracy/passive_1": 0.901, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.914, "blimp/accuracy/inchoative": 0.609, "blimp/accuracy/anaphor_gender_agreement": 0.977, "blimp/accuracy/principle_A_c_command": 0.698, "blimp/accuracy/only_npi_licensor_present": 0.856, "blimp/accuracy/expletive_it_object_raising": 0.778, "blimp/accuracy/left_branch_island_simple_question": 0.799, "blimp/accuracy/wh_questions_subject_gap": 0.941, "blimp/accuracy/existential_there_quantifiers_2": 0.55, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.949, "blimp/accuracy/sentential_negation_npi_scope": 0.677, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.839, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.914, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.874, "blimp/accuracy/principle_A_case_2": 0.932, "blimp/accuracy/distractor_agreement_relational_noun": 0.866, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.956, "blimp/accuracy/superlative_quantifiers_1": 0.835, "blimp/accuracy/wh_island": 0.768, "blimp/accuracy/principle_A_domain_1": 0.993, "blimp/accuracy/complex_NP_island": 0.622, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.982, "blimp/accuracy/irregular_past_participle_verbs": 0.927, "blimp/accuracy/drop_argument": 0.727, "blimp/accuracy/wh_questions_object_gap": 0.848, "blimp/accuracy/animate_subject_passive": 0.802, "blimp/accuracy/existential_there_quantifiers_1": 0.98, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.864, "blimp/accuracy/npi_present_2": 0.576, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.938, "blimp/accuracy/anaphor_number_agreement": 0.991, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.962, "blimp/accuracy/existential_there_object_raising": 0.86, "blimp/accuracy/matrix_question_npi_licensor_present": 0.433, "blimp/accuracy/npi_present_1": 0.615, "blimp/accuracy/wh_vs_that_no_gap": 0.98, "blimp/accuracy/left_branch_island_echo_question": 0.482, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.973, "blimp/accuracy/causative": 0.755, "blimp/accuracy/group_average": 0.8024029850746269, "blimp/accuracy/seq_average": 0.8024029850746268, "cbt/accuracy/NE": 0.8261217948717948, "cbt/accuracy/V": 0.9348, "cbt/accuracy/CN": 0.8856, "cbt/accuracy/P": 0.9168, "cbt/accuracy/group_average": 0.8908304487179487, "cbt/accuracy/seq_average": 0.8908563425370148, "hellaswag/accuracy/val": 0.3626767576180044, "hellaswag/accuracy/group_average": 0.3626767576180044, "hellaswag/accuracy/seq_average": 0.3626767576180044, "piqa/accuracy/val": 0.6322089227421109, "piqa/accuracy/group_average": 0.6322089227421109, "piqa/accuracy/seq_average": 0.6322089227421109, "ai2arc/accuracy/ARC-Easy": 0.38054968287526425, "ai2arc/accuracy/ARC-Challenge": 0.2257510729613734, "ai2arc/accuracy/group_average": 0.30315037791831884, "ai2arc/accuracy/seq_average": 0.32946175637393765, "mmlu/accuracy/MMLU": 0.25927779764032893, "mmlu/accuracy/group_average": 0.25927779764032893, "mmlu/accuracy/seq_average": 0.25927779764032893, "openbookqa/accuracy/test": 0.276, "openbookqa/accuracy/group_average": 0.276, "openbookqa/accuracy/seq_average": 0.276, "race/accuracy/test/high": 0.28987993138936535, "race/accuracy/test/middle": 0.3767409470752089, "race/accuracy/group_average": 0.3333104392322871, "race/accuracy/seq_average": 0.3151601134981759, "siqa/accuracy/dev": 0.37461617195496416, "siqa/accuracy/group_average": 0.37461617195496416, "siqa/accuracy/seq_average": 0.37461617195496416, "winogrande/accuracy/dev": 0.5059194948697711, "winogrande/accuracy/group_average": 0.5059194948697711, "winogrande/accuracy/seq_average": 0.5059194948697711, "commonsenseqa/accuracy/dev_rand_split": 0.2702702702702703, "commonsenseqa/accuracy/group_average": 0.2702702702702703, "commonsenseqa/accuracy/seq_average": 0.2702702702702703}
|