Upload folder using huggingface_hub
#316
by
DavidNguyen
- opened
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-100000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-120000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-140000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-160000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-180000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-20000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-200000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-220000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-240000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-260000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-280000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-300000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-320000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-340000.pth.json +112 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-360000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-380000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-40000.pth.json +112 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-400000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-60000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-80000.pth.json +1 -0
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-100000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.434325687468998, "val/accuracy": 0.5007895817832341, "val/perplexity": 11.40812347854509, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.5387637689246896, "lambada/accuracy/total": 0.3231754658385093, "lambada/accuracy/openai_last_token": 0.7820263975155279, "lambada/perplexity": 8.540076827320044, "lambada/lm_loss": 3.018086463857454, "lambada/lm_perplexity": 20.45211834869759, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4119825238108717, "mean_loss": 2.4865447281968436, "blimp/accuracy/passive_2": 0.889, "blimp/accuracy/determiner_noun_agreement_2": 0.986, "blimp/accuracy/ellipsis_n_bar_1": 0.825, "blimp/accuracy/tough_vs_raising_2": 0.887, "blimp/accuracy/tough_vs_raising_1": 0.674, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.92, "blimp/accuracy/principle_A_reconstruction": 0.355, "blimp/accuracy/wh_vs_that_with_gap": 0.528, "blimp/accuracy/principle_A_domain_2": 0.899, "blimp/accuracy/determiner_noun_agreement_1": 0.989, "blimp/accuracy/ellipsis_n_bar_2": 0.918, "blimp/accuracy/principle_A_domain_3": 0.63, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.924, "blimp/accuracy/animate_subject_trans": 0.9, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.901, "blimp/accuracy/distractor_agreement_relative_clause": 0.683, "blimp/accuracy/transitive": 0.868, "blimp/accuracy/sentential_subject_island": 0.383, "blimp/accuracy/adjunct_island": 0.883, "blimp/accuracy/intransitive": 0.807, "blimp/accuracy/existential_there_subject_raising": 0.883, "blimp/accuracy/irregular_past_participle_adjectives": 0.884, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.572, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.369, "blimp/accuracy/only_npi_scope": 0.788, "blimp/accuracy/superlative_quantifiers_2": 0.784, "blimp/accuracy/passive_1": 0.903, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.913, "blimp/accuracy/inchoative": 0.692, "blimp/accuracy/anaphor_gender_agreement": 0.982, "blimp/accuracy/principle_A_c_command": 0.734, "blimp/accuracy/only_npi_licensor_present": 0.651, "blimp/accuracy/expletive_it_object_raising": 0.792, "blimp/accuracy/left_branch_island_simple_question": 0.679, "blimp/accuracy/wh_questions_subject_gap": 0.933, "blimp/accuracy/existential_there_quantifiers_2": 0.457, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.931, "blimp/accuracy/sentential_negation_npi_scope": 0.649, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.798, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.87, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.906, "blimp/accuracy/principle_A_case_2": 0.955, "blimp/accuracy/distractor_agreement_relational_noun": 0.859, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.978, "blimp/accuracy/superlative_quantifiers_1": 0.714, "blimp/accuracy/wh_island": 0.728, "blimp/accuracy/principle_A_domain_1": 0.974, "blimp/accuracy/complex_NP_island": 0.584, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.974, "blimp/accuracy/irregular_past_participle_verbs": 0.882, "blimp/accuracy/drop_argument": 0.768, "blimp/accuracy/wh_questions_object_gap": 0.86, "blimp/accuracy/animate_subject_passive": 0.795, "blimp/accuracy/existential_there_quantifiers_1": 0.968, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.914, "blimp/accuracy/npi_present_2": 0.558, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.971, "blimp/accuracy/anaphor_number_agreement": 0.993, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.961, "blimp/accuracy/existential_there_object_raising": 0.832, "blimp/accuracy/matrix_question_npi_licensor_present": 0.278, "blimp/accuracy/npi_present_1": 0.499, "blimp/accuracy/wh_vs_that_no_gap": 0.97, "blimp/accuracy/left_branch_island_echo_question": 0.482, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.962, "blimp/accuracy/causative": 0.759, "blimp/accuracy/group_average": 0.7945820895522387, "blimp/accuracy/seq_average": 0.7945820895522389, "cbt/accuracy/NE": 0.8092948717948718, "cbt/accuracy/V": 0.9264, "cbt/accuracy/CN": 0.8608, "cbt/accuracy/P": 0.9116, "cbt/accuracy/group_average": 0.8770237179487179, "cbt/accuracy/seq_average": 0.8770508203281312, "hellaswag/accuracy/val": 0.3302131049591715, "hellaswag/accuracy/group_average": 0.3302131049591715, "hellaswag/accuracy/seq_average": 0.3302131049591715, "piqa/accuracy/val": 0.6300326441784548, "piqa/accuracy/group_average": 0.6300326441784548, "piqa/accuracy/seq_average": 0.6300326441784548, "ai2arc/accuracy/ARC-Easy": 0.36194503171247355, "ai2arc/accuracy/ARC-Challenge": 0.2206008583690987, "ai2arc/accuracy/group_average": 0.29127294504078616, "ai2arc/accuracy/seq_average": 0.3152974504249292, "race/accuracy/test/high": 0.2850200114351058, "race/accuracy/test/middle": 0.3544568245125348, "race/accuracy/group_average": 0.3197384179738203, "race/accuracy/seq_average": 0.3052290231049858, "siqa/accuracy/dev": 0.3556806550665302, "siqa/accuracy/group_average": 0.3556806550665302, "siqa/accuracy/seq_average": 0.3556806550665302, "commonsenseqa/accuracy/dev_rand_split": 0.26371826371826373, "commonsenseqa/accuracy/group_average": 0.26371826371826373, "commonsenseqa/accuracy/seq_average": 0.26371826371826373}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-120000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.4086763896639387, "val/accuracy": 0.504578605530754, "val/perplexity": 11.119233867750744, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.47574478054639, "lambada/accuracy/total": 0.3470496894409938, "lambada/accuracy/openai_last_token": 0.7849378881987578, "lambada/perplexity": 7.565643098142509, "lambada/lm_loss": 2.994189786344217, "lambada/lm_perplexity": 19.96917403624386, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4258141474858739, "mean_loss": 2.4422105851051645, "blimp/accuracy/passive_2": 0.911, "blimp/accuracy/determiner_noun_agreement_2": 0.989, "blimp/accuracy/ellipsis_n_bar_1": 0.835, "blimp/accuracy/tough_vs_raising_2": 0.897, "blimp/accuracy/tough_vs_raising_1": 0.601, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.935, "blimp/accuracy/principle_A_reconstruction": 0.361, "blimp/accuracy/wh_vs_that_with_gap": 0.487, "blimp/accuracy/principle_A_domain_2": 0.876, "blimp/accuracy/determiner_noun_agreement_1": 0.993, "blimp/accuracy/ellipsis_n_bar_2": 0.921, "blimp/accuracy/principle_A_domain_3": 0.589, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.931, "blimp/accuracy/animate_subject_trans": 0.9, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.887, "blimp/accuracy/distractor_agreement_relative_clause": 0.628, "blimp/accuracy/transitive": 0.847, "blimp/accuracy/sentential_subject_island": 0.409, "blimp/accuracy/adjunct_island": 0.87, "blimp/accuracy/intransitive": 0.777, "blimp/accuracy/existential_there_subject_raising": 0.889, "blimp/accuracy/irregular_past_participle_adjectives": 0.888, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.648, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.336, "blimp/accuracy/only_npi_scope": 0.709, "blimp/accuracy/superlative_quantifiers_2": 0.669, "blimp/accuracy/passive_1": 0.917, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.899, "blimp/accuracy/inchoative": 0.639, "blimp/accuracy/anaphor_gender_agreement": 0.954, "blimp/accuracy/principle_A_c_command": 0.678, "blimp/accuracy/only_npi_licensor_present": 0.703, "blimp/accuracy/expletive_it_object_raising": 0.793, "blimp/accuracy/left_branch_island_simple_question": 0.701, "blimp/accuracy/wh_questions_subject_gap": 0.948, "blimp/accuracy/existential_there_quantifiers_2": 0.454, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.935, "blimp/accuracy/sentential_negation_npi_scope": 0.723, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.765, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.895, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.904, "blimp/accuracy/principle_A_case_2": 0.959, "blimp/accuracy/distractor_agreement_relational_noun": 0.844, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.985, "blimp/accuracy/superlative_quantifiers_1": 0.728, "blimp/accuracy/wh_island": 0.785, "blimp/accuracy/principle_A_domain_1": 0.984, "blimp/accuracy/complex_NP_island": 0.544, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.971, "blimp/accuracy/irregular_past_participle_verbs": 0.892, "blimp/accuracy/drop_argument": 0.726, "blimp/accuracy/wh_questions_object_gap": 0.827, "blimp/accuracy/animate_subject_passive": 0.804, "blimp/accuracy/existential_there_quantifiers_1": 0.984, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.924, "blimp/accuracy/npi_present_2": 0.619, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.94, "blimp/accuracy/anaphor_number_agreement": 0.985, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.953, "blimp/accuracy/existential_there_object_raising": 0.852, "blimp/accuracy/matrix_question_npi_licensor_present": 0.267, "blimp/accuracy/npi_present_1": 0.58, "blimp/accuracy/wh_vs_that_no_gap": 0.971, "blimp/accuracy/left_branch_island_echo_question": 0.483, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.962, "blimp/accuracy/causative": 0.764, "blimp/accuracy/group_average": 0.7914029850746269, "blimp/accuracy/seq_average": 0.7914029850746269, "cbt/accuracy/NE": 0.8157051282051282, "cbt/accuracy/V": 0.9308, "cbt/accuracy/CN": 0.872, "cbt/accuracy/P": 0.9112, "cbt/accuracy/group_average": 0.882426282051282, "cbt/accuracy/seq_average": 0.882452981192477, "hellaswag/accuracy/val": 0.33300139414459273, "hellaswag/accuracy/group_average": 0.33300139414459273, "hellaswag/accuracy/seq_average": 0.33300139414459273, "piqa/accuracy/val": 0.6284004352557128, "piqa/accuracy/group_average": 0.6284004352557128, "piqa/accuracy/seq_average": 0.6284004352557128, "ai2arc/accuracy/ARC-Easy": 0.36617336152219876, "ai2arc/accuracy/ARC-Challenge": 0.23261802575107296, "ai2arc/accuracy/group_average": 0.2993956936366359, "ai2arc/accuracy/seq_average": 0.32209631728045324, "race/accuracy/test/high": 0.2847341337907376, "race/accuracy/test/middle": 0.3593314763231198, "race/accuracy/group_average": 0.32203280505692866, "race/accuracy/seq_average": 0.30644507498986623, "siqa/accuracy/dev": 0.37001023541453426, "siqa/accuracy/group_average": 0.37001023541453426, "siqa/accuracy/seq_average": 0.37001023541453426, "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_660M_standardlb_plus_plus/export/result-model-140000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.3863457573784723, "val/accuracy": 0.5076739598834326, "val/perplexity": 10.873686166260534, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.4169802458389946, "lambada/accuracy/total": 0.328027950310559, "lambada/accuracy/openai_last_token": 0.781638198757764, "lambada/perplexity": 7.498153290464985, "lambada/lm_loss": 2.9831560376563866, "lambada/lm_perplexity": 19.750050289671826, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.41785095509699577, "mean_loss": 2.4016630016087337, "blimp/accuracy/passive_2": 0.896, "blimp/accuracy/determiner_noun_agreement_2": 0.986, "blimp/accuracy/ellipsis_n_bar_1": 0.855, "blimp/accuracy/tough_vs_raising_2": 0.893, "blimp/accuracy/tough_vs_raising_1": 0.647, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.906, "blimp/accuracy/principle_A_reconstruction": 0.421, "blimp/accuracy/wh_vs_that_with_gap": 0.529, "blimp/accuracy/principle_A_domain_2": 0.902, "blimp/accuracy/determiner_noun_agreement_1": 0.992, "blimp/accuracy/ellipsis_n_bar_2": 0.911, "blimp/accuracy/principle_A_domain_3": 0.62, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.934, "blimp/accuracy/animate_subject_trans": 0.905, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.886, "blimp/accuracy/distractor_agreement_relative_clause": 0.666, "blimp/accuracy/transitive": 0.88, "blimp/accuracy/sentential_subject_island": 0.398, "blimp/accuracy/adjunct_island": 0.887, "blimp/accuracy/intransitive": 0.775, "blimp/accuracy/existential_there_subject_raising": 0.889, "blimp/accuracy/irregular_past_participle_adjectives": 0.859, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.638, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.405, "blimp/accuracy/only_npi_scope": 0.711, "blimp/accuracy/superlative_quantifiers_2": 0.763, "blimp/accuracy/passive_1": 0.915, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.915, "blimp/accuracy/inchoative": 0.651, "blimp/accuracy/anaphor_gender_agreement": 0.979, "blimp/accuracy/principle_A_c_command": 0.675, "blimp/accuracy/only_npi_licensor_present": 0.645, "blimp/accuracy/expletive_it_object_raising": 0.819, "blimp/accuracy/left_branch_island_simple_question": 0.739, "blimp/accuracy/wh_questions_subject_gap": 0.944, "blimp/accuracy/existential_there_quantifiers_2": 0.393, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.94, "blimp/accuracy/sentential_negation_npi_scope": 0.706, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.784, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.894, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.895, "blimp/accuracy/principle_A_case_2": 0.944, "blimp/accuracy/distractor_agreement_relational_noun": 0.87, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.989, "blimp/accuracy/superlative_quantifiers_1": 0.868, "blimp/accuracy/wh_island": 0.789, "blimp/accuracy/principle_A_domain_1": 0.971, "blimp/accuracy/complex_NP_island": 0.66, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.979, "blimp/accuracy/irregular_past_participle_verbs": 0.895, "blimp/accuracy/drop_argument": 0.762, "blimp/accuracy/wh_questions_object_gap": 0.861, "blimp/accuracy/animate_subject_passive": 0.806, "blimp/accuracy/existential_there_quantifiers_1": 0.978, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.903, "blimp/accuracy/npi_present_2": 0.513, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.96, "blimp/accuracy/anaphor_number_agreement": 0.989, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.948, "blimp/accuracy/existential_there_object_raising": 0.851, "blimp/accuracy/matrix_question_npi_licensor_present": 0.286, "blimp/accuracy/npi_present_1": 0.516, "blimp/accuracy/wh_vs_that_no_gap": 0.973, "blimp/accuracy/left_branch_island_echo_question": 0.5, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.958, "blimp/accuracy/causative": 0.74, "blimp/accuracy/group_average": 0.7993582089552237, "blimp/accuracy/seq_average": 0.7993582089552239, "cbt/accuracy/NE": 0.8141025641025641, "cbt/accuracy/V": 0.9364, "cbt/accuracy/CN": 0.8716, "cbt/accuracy/P": 0.9024, "cbt/accuracy/group_average": 0.8811256410256411, "cbt/accuracy/seq_average": 0.8811524609843937, "hellaswag/accuracy/val": 0.3406691894045011, "hellaswag/accuracy/group_average": 0.3406691894045011, "hellaswag/accuracy/seq_average": 0.3406691894045011, "piqa/accuracy/val": 0.6262241566920566, "piqa/accuracy/group_average": 0.6262241566920566, "piqa/accuracy/seq_average": 0.6262241566920566, "ai2arc/accuracy/ARC-Easy": 0.36617336152219876, "ai2arc/accuracy/ARC-Challenge": 0.24206008583690988, "ai2arc/accuracy/group_average": 0.30411672367955433, "ai2arc/accuracy/seq_average": 0.32521246458923514, "race/accuracy/test/high": 0.28101772441395084, "race/accuracy/test/middle": 0.3635097493036212, "race/accuracy/group_average": 0.322263736858786, "race/accuracy/seq_average": 0.3050263477908391, "siqa/accuracy/dev": 0.372057318321392, "siqa/accuracy/group_average": 0.372057318321392, "siqa/accuracy/seq_average": 0.372057318321392, "commonsenseqa/accuracy/dev_rand_split": 0.26945126945126946, "commonsenseqa/accuracy/group_average": 0.26945126945126946, "commonsenseqa/accuracy/seq_average": 0.26945126945126946}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-160000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.367560734824529, "val/accuracy": 0.510651119171627, "val/perplexity": 10.671330306603563, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.3862204225907413, "lambada/accuracy/total": 0.3202639751552795, "lambada/accuracy/openai_last_token": 0.7857142857142857, "lambada/perplexity": 7.798124961258817, "lambada/lm_loss": 2.9581918145760304, "lambada/lm_perplexity": 19.263108972948665, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.41545754716345323, "mean_loss": 2.376890578707635, "blimp/accuracy/passive_2": 0.903, "blimp/accuracy/determiner_noun_agreement_2": 0.987, "blimp/accuracy/ellipsis_n_bar_1": 0.859, "blimp/accuracy/tough_vs_raising_2": 0.874, "blimp/accuracy/tough_vs_raising_1": 0.615, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.937, "blimp/accuracy/principle_A_reconstruction": 0.341, "blimp/accuracy/wh_vs_that_with_gap": 0.461, "blimp/accuracy/principle_A_domain_2": 0.898, "blimp/accuracy/determiner_noun_agreement_1": 0.993, "blimp/accuracy/ellipsis_n_bar_2": 0.912, "blimp/accuracy/principle_A_domain_3": 0.589, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.937, "blimp/accuracy/animate_subject_trans": 0.9, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.892, "blimp/accuracy/distractor_agreement_relative_clause": 0.638, "blimp/accuracy/transitive": 0.87, "blimp/accuracy/sentential_subject_island": 0.407, "blimp/accuracy/adjunct_island": 0.894, "blimp/accuracy/intransitive": 0.766, "blimp/accuracy/existential_there_subject_raising": 0.897, "blimp/accuracy/irregular_past_participle_adjectives": 0.844, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.662, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.346, "blimp/accuracy/only_npi_scope": 0.771, "blimp/accuracy/superlative_quantifiers_2": 0.852, "blimp/accuracy/passive_1": 0.921, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.931, "blimp/accuracy/inchoative": 0.665, "blimp/accuracy/anaphor_gender_agreement": 0.976, "blimp/accuracy/principle_A_c_command": 0.68, "blimp/accuracy/only_npi_licensor_present": 0.587, "blimp/accuracy/expletive_it_object_raising": 0.785, "blimp/accuracy/left_branch_island_simple_question": 0.753, "blimp/accuracy/wh_questions_subject_gap": 0.926, "blimp/accuracy/existential_there_quantifiers_2": 0.361, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.946, "blimp/accuracy/sentential_negation_npi_scope": 0.683, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.809, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.899, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.917, "blimp/accuracy/principle_A_case_2": 0.962, "blimp/accuracy/distractor_agreement_relational_noun": 0.878, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.985, "blimp/accuracy/superlative_quantifiers_1": 0.835, "blimp/accuracy/wh_island": 0.849, "blimp/accuracy/principle_A_domain_1": 0.989, "blimp/accuracy/complex_NP_island": 0.624, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.972, "blimp/accuracy/irregular_past_participle_verbs": 0.885, "blimp/accuracy/drop_argument": 0.72, "blimp/accuracy/wh_questions_object_gap": 0.85, "blimp/accuracy/animate_subject_passive": 0.781, "blimp/accuracy/existential_there_quantifiers_1": 0.971, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.921, "blimp/accuracy/npi_present_2": 0.533, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.982, "blimp/accuracy/anaphor_number_agreement": 0.993, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.963, "blimp/accuracy/existential_there_object_raising": 0.86, "blimp/accuracy/matrix_question_npi_licensor_present": 0.272, "blimp/accuracy/npi_present_1": 0.513, "blimp/accuracy/wh_vs_that_no_gap": 0.974, "blimp/accuracy/left_branch_island_echo_question": 0.503, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.95, "blimp/accuracy/causative": 0.771, "blimp/accuracy/group_average": 0.7973134328358208, "blimp/accuracy/seq_average": 0.7973134328358209, "cbt/accuracy/NE": 0.811698717948718, "cbt/accuracy/V": 0.9336, "cbt/accuracy/CN": 0.8764, "cbt/accuracy/P": 0.914, "cbt/accuracy/group_average": 0.8839246794871795, "cbt/accuracy/seq_average": 0.8839535814325731, "hellaswag/accuracy/val": 0.34166500697072294, "hellaswag/accuracy/group_average": 0.34166500697072294, "hellaswag/accuracy/seq_average": 0.34166500697072294, "piqa/accuracy/val": 0.6289445048966268, "piqa/accuracy/group_average": 0.6289445048966268, "piqa/accuracy/seq_average": 0.6289445048966268, "ai2arc/accuracy/ARC-Easy": 0.37251585623678646, "ai2arc/accuracy/ARC-Challenge": 0.22660944206008585, "ai2arc/accuracy/group_average": 0.29956264914843617, "ai2arc/accuracy/seq_average": 0.3243626062322946, "race/accuracy/test/high": 0.29245283018867924, "race/accuracy/test/middle": 0.3607242339832869, "race/accuracy/group_average": 0.32658853208598304, "race/accuracy/seq_average": 0.3123226591001216, "siqa/accuracy/dev": 0.37563971340839303, "siqa/accuracy/group_average": 0.37563971340839303, "siqa/accuracy/seq_average": 0.37563971340839303, "commonsenseqa/accuracy/dev_rand_split": 0.26535626535626533, "commonsenseqa/accuracy/group_average": 0.26535626535626533, "commonsenseqa/accuracy/seq_average": 0.26535626535626533}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-180000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.346894279358879, "val/accuracy": 0.5134490482390873, "val/perplexity": 10.453054991373902, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.399798659804445, "lambada/accuracy/total": 0.3423913043478261, "lambada/accuracy/openai_last_token": 0.7876552795031055, "lambada/perplexity": 7.337695776492842, "lambada/lm_loss": 2.9513198173753254, "lambada/lm_perplexity": 19.131186745758992, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4279201762934567, "mean_loss": 2.373346469581662, "blimp/accuracy/passive_2": 0.908, "blimp/accuracy/determiner_noun_agreement_2": 0.984, "blimp/accuracy/ellipsis_n_bar_1": 0.848, "blimp/accuracy/tough_vs_raising_2": 0.877, "blimp/accuracy/tough_vs_raising_1": 0.647, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.929, "blimp/accuracy/principle_A_reconstruction": 0.316, "blimp/accuracy/wh_vs_that_with_gap": 0.476, "blimp/accuracy/principle_A_domain_2": 0.9, "blimp/accuracy/determiner_noun_agreement_1": 0.988, "blimp/accuracy/ellipsis_n_bar_2": 0.906, "blimp/accuracy/principle_A_domain_3": 0.634, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.923, "blimp/accuracy/animate_subject_trans": 0.902, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.914, "blimp/accuracy/distractor_agreement_relative_clause": 0.655, "blimp/accuracy/transitive": 0.862, "blimp/accuracy/sentential_subject_island": 0.439, "blimp/accuracy/adjunct_island": 0.893, "blimp/accuracy/intransitive": 0.778, "blimp/accuracy/existential_there_subject_raising": 0.892, "blimp/accuracy/irregular_past_participle_adjectives": 0.973, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.712, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.374, "blimp/accuracy/only_npi_scope": 0.657, "blimp/accuracy/superlative_quantifiers_2": 0.7, "blimp/accuracy/passive_1": 0.908, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.917, "blimp/accuracy/inchoative": 0.65, "blimp/accuracy/anaphor_gender_agreement": 0.976, "blimp/accuracy/principle_A_c_command": 0.696, "blimp/accuracy/only_npi_licensor_present": 0.532, "blimp/accuracy/expletive_it_object_raising": 0.821, "blimp/accuracy/left_branch_island_simple_question": 0.784, "blimp/accuracy/wh_questions_subject_gap": 0.948, "blimp/accuracy/existential_there_quantifiers_2": 0.331, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.942, "blimp/accuracy/sentential_negation_npi_scope": 0.734, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.776, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.926, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.894, "blimp/accuracy/principle_A_case_2": 0.924, "blimp/accuracy/distractor_agreement_relational_noun": 0.865, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.991, "blimp/accuracy/superlative_quantifiers_1": 0.661, "blimp/accuracy/wh_island": 0.769, "blimp/accuracy/principle_A_domain_1": 0.987, "blimp/accuracy/complex_NP_island": 0.592, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.973, "blimp/accuracy/irregular_past_participle_verbs": 0.866, "blimp/accuracy/drop_argument": 0.722, "blimp/accuracy/wh_questions_object_gap": 0.862, "blimp/accuracy/animate_subject_passive": 0.812, "blimp/accuracy/existential_there_quantifiers_1": 0.978, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.909, "blimp/accuracy/npi_present_2": 0.528, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.949, "blimp/accuracy/anaphor_number_agreement": 0.99, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.95, "blimp/accuracy/existential_there_object_raising": 0.867, "blimp/accuracy/matrix_question_npi_licensor_present": 0.319, "blimp/accuracy/npi_present_1": 0.548, "blimp/accuracy/wh_vs_that_no_gap": 0.981, "blimp/accuracy/left_branch_island_echo_question": 0.511, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.961, "blimp/accuracy/causative": 0.758, "blimp/accuracy/group_average": 0.7939552238805971, "blimp/accuracy/seq_average": 0.793955223880597, "cbt/accuracy/NE": 0.8108974358974359, "cbt/accuracy/V": 0.9356, "cbt/accuracy/CN": 0.8812, "cbt/accuracy/P": 0.9196, "cbt/accuracy/group_average": 0.886824358974359, "cbt/accuracy/seq_average": 0.8868547418967587, "hellaswag/accuracy/val": 0.3472415853415654, "hellaswag/accuracy/group_average": 0.3472415853415654, "hellaswag/accuracy/seq_average": 0.3472415853415654, "piqa/accuracy/val": 0.6332970620239391, "piqa/accuracy/group_average": 0.6332970620239391, "piqa/accuracy/seq_average": 0.6332970620239391, "ai2arc/accuracy/ARC-Easy": 0.38054968287526425, "ai2arc/accuracy/ARC-Challenge": 0.23862660944206007, "ai2arc/accuracy/group_average": 0.30958814615866215, "ai2arc/accuracy/seq_average": 0.3337110481586402, "race/accuracy/test/high": 0.2950257289879931, "race/accuracy/test/middle": 0.36768802228412256, "race/accuracy/group_average": 0.33135687563605787, "race/accuracy/seq_average": 0.3161734900689096, "siqa/accuracy/dev": 0.3725690890481064, "siqa/accuracy/group_average": 0.3725690890481064, "siqa/accuracy/seq_average": 0.3725690890481064, "commonsenseqa/accuracy/dev_rand_split": 0.2809172809172809, "commonsenseqa/accuracy/group_average": 0.2809172809172809, "commonsenseqa/accuracy/seq_average": 0.2809172809172809}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-20000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.717951941111731, "val/accuracy": 0.4622221447172619, "val/perplexity": 15.149263866603562, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.6900031996069487, "lambada/accuracy/total": 0.2204968944099379, "lambada/accuracy/openai_last_token": 0.7476708074534162, "lambada/perplexity": 14.531435402026652, "lambada/lm_loss": 3.2611571083448747, "lambada/lm_perplexity": 26.07969672491325, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3413595195635999, "mean_loss": 2.70397757035934, "blimp/accuracy/passive_2": 0.886, "blimp/accuracy/determiner_noun_agreement_2": 0.984, "blimp/accuracy/ellipsis_n_bar_1": 0.784, "blimp/accuracy/tough_vs_raising_2": 0.873, "blimp/accuracy/tough_vs_raising_1": 0.594, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.843, "blimp/accuracy/principle_A_reconstruction": 0.282, "blimp/accuracy/wh_vs_that_with_gap": 0.553, "blimp/accuracy/principle_A_domain_2": 0.84, "blimp/accuracy/determiner_noun_agreement_1": 0.987, "blimp/accuracy/ellipsis_n_bar_2": 0.908, "blimp/accuracy/principle_A_domain_3": 0.563, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.92, "blimp/accuracy/animate_subject_trans": 0.891, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.865, "blimp/accuracy/distractor_agreement_relative_clause": 0.551, "blimp/accuracy/transitive": 0.844, "blimp/accuracy/sentential_subject_island": 0.338, "blimp/accuracy/adjunct_island": 0.83, "blimp/accuracy/intransitive": 0.774, "blimp/accuracy/existential_there_subject_raising": 0.859, "blimp/accuracy/irregular_past_participle_adjectives": 0.87, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.262, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.245, "blimp/accuracy/only_npi_scope": 0.725, "blimp/accuracy/superlative_quantifiers_2": 0.444, "blimp/accuracy/passive_1": 0.882, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.895, "blimp/accuracy/inchoative": 0.617, "blimp/accuracy/anaphor_gender_agreement": 0.959, "blimp/accuracy/principle_A_c_command": 0.568, "blimp/accuracy/only_npi_licensor_present": 0.733, "blimp/accuracy/expletive_it_object_raising": 0.783, "blimp/accuracy/left_branch_island_simple_question": 0.332, "blimp/accuracy/wh_questions_subject_gap": 0.924, "blimp/accuracy/existential_there_quantifiers_2": 0.216, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.942, "blimp/accuracy/sentential_negation_npi_scope": 0.572, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.735, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.875, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.835, "blimp/accuracy/principle_A_case_2": 0.954, "blimp/accuracy/distractor_agreement_relational_noun": 0.762, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.996, "blimp/accuracy/superlative_quantifiers_1": 0.695, "blimp/accuracy/wh_island": 0.714, "blimp/accuracy/principle_A_domain_1": 0.965, "blimp/accuracy/complex_NP_island": 0.496, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.959, "blimp/accuracy/irregular_past_participle_verbs": 0.865, "blimp/accuracy/drop_argument": 0.755, "blimp/accuracy/wh_questions_object_gap": 0.794, "blimp/accuracy/animate_subject_passive": 0.78, "blimp/accuracy/existential_there_quantifiers_1": 0.979, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.869, "blimp/accuracy/npi_present_2": 0.583, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.925, "blimp/accuracy/anaphor_number_agreement": 0.991, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.943, "blimp/accuracy/existential_there_object_raising": 0.702, "blimp/accuracy/matrix_question_npi_licensor_present": 0.187, "blimp/accuracy/npi_present_1": 0.497, "blimp/accuracy/wh_vs_that_no_gap": 0.962, "blimp/accuracy/left_branch_island_echo_question": 0.378, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.976, "blimp/accuracy/causative": 0.696, "blimp/accuracy/group_average": 0.7433731343283583, "blimp/accuracy/seq_average": 0.7433731343283582, "cbt/accuracy/NE": 0.7355769230769231, "cbt/accuracy/V": 0.9032, "cbt/accuracy/CN": 0.818, "cbt/accuracy/P": 0.8756, "cbt/accuracy/group_average": 0.8330942307692307, "cbt/accuracy/seq_average": 0.8331332533013205, "hellaswag/accuracy/val": 0.28669587731527585, "hellaswag/accuracy/group_average": 0.28669587731527585, "hellaswag/accuracy/seq_average": 0.28669587731527585, "piqa/accuracy/val": 0.5685527747551686, "piqa/accuracy/group_average": 0.5685527747551686, "piqa/accuracy/seq_average": 0.5685527747551686, "ai2arc/accuracy/ARC-Easy": 0.3289640591966173, "ai2arc/accuracy/ARC-Challenge": 0.21630901287553647, "ai2arc/accuracy/group_average": 0.2726365360360769, "ai2arc/accuracy/seq_average": 0.29178470254957506, "race/accuracy/test/high": 0.26500857632933106, "race/accuracy/test/middle": 0.3384401114206128, "race/accuracy/group_average": 0.30172434387497193, "race/accuracy/seq_average": 0.2863802188893393, "siqa/accuracy/dev": 0.35670419651995905, "siqa/accuracy/group_average": 0.35670419651995905, "siqa/accuracy/seq_average": 0.35670419651995905, "commonsenseqa/accuracy/dev_rand_split": 0.24651924651924653, "commonsenseqa/accuracy/group_average": 0.24651924651924653, "commonsenseqa/accuracy/seq_average": 0.24651924651924653}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-200000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.3325994582403276, "val/accuracy": 0.5161239381820436, "val/perplexity": 10.304693367930023, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.329006218762131, "lambada/accuracy/total": 0.34607919254658387, "lambada/accuracy/openai_last_token": 0.7903726708074534, "lambada/perplexity": 7.344714817317364, "lambada/lm_loss": 2.9410780848295386, "lambada/lm_perplexity": 18.936250195784584, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.43110156536431377, "mean_loss": 2.3308028385012296, "blimp/accuracy/passive_2": 0.91, "blimp/accuracy/determiner_noun_agreement_2": 0.986, "blimp/accuracy/ellipsis_n_bar_1": 0.838, "blimp/accuracy/tough_vs_raising_2": 0.867, "blimp/accuracy/tough_vs_raising_1": 0.636, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.937, "blimp/accuracy/principle_A_reconstruction": 0.349, "blimp/accuracy/wh_vs_that_with_gap": 0.519, "blimp/accuracy/principle_A_domain_2": 0.896, "blimp/accuracy/determiner_noun_agreement_1": 0.994, "blimp/accuracy/ellipsis_n_bar_2": 0.901, "blimp/accuracy/principle_A_domain_3": 0.618, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.95, "blimp/accuracy/animate_subject_trans": 0.904, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.927, "blimp/accuracy/distractor_agreement_relative_clause": 0.655, "blimp/accuracy/transitive": 0.863, "blimp/accuracy/sentential_subject_island": 0.479, "blimp/accuracy/adjunct_island": 0.898, "blimp/accuracy/intransitive": 0.765, "blimp/accuracy/existential_there_subject_raising": 0.912, "blimp/accuracy/irregular_past_participle_adjectives": 0.999, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.734, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.403, "blimp/accuracy/only_npi_scope": 0.767, "blimp/accuracy/superlative_quantifiers_2": 0.821, "blimp/accuracy/passive_1": 0.918, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.903, "blimp/accuracy/inchoative": 0.647, "blimp/accuracy/anaphor_gender_agreement": 0.985, "blimp/accuracy/principle_A_c_command": 0.707, "blimp/accuracy/only_npi_licensor_present": 0.978, "blimp/accuracy/expletive_it_object_raising": 0.825, "blimp/accuracy/left_branch_island_simple_question": 0.826, "blimp/accuracy/wh_questions_subject_gap": 0.939, "blimp/accuracy/existential_there_quantifiers_2": 0.456, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.955, "blimp/accuracy/sentential_negation_npi_scope": 0.734, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.847, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.897, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.913, "blimp/accuracy/principle_A_case_2": 0.955, "blimp/accuracy/distractor_agreement_relational_noun": 0.843, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.988, "blimp/accuracy/superlative_quantifiers_1": 0.742, "blimp/accuracy/wh_island": 0.747, "blimp/accuracy/principle_A_domain_1": 0.983, "blimp/accuracy/complex_NP_island": 0.601, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.981, "blimp/accuracy/irregular_past_participle_verbs": 0.859, "blimp/accuracy/drop_argument": 0.765, "blimp/accuracy/wh_questions_object_gap": 0.852, "blimp/accuracy/animate_subject_passive": 0.782, "blimp/accuracy/existential_there_quantifiers_1": 0.981, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.927, "blimp/accuracy/npi_present_2": 0.518, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.955, "blimp/accuracy/anaphor_number_agreement": 0.992, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.963, "blimp/accuracy/existential_there_object_raising": 0.86, "blimp/accuracy/matrix_question_npi_licensor_present": 0.301, "blimp/accuracy/npi_present_1": 0.527, "blimp/accuracy/wh_vs_that_no_gap": 0.971, "blimp/accuracy/left_branch_island_echo_question": 0.574, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.966, "blimp/accuracy/causative": 0.772, "blimp/accuracy/group_average": 0.8128805970149252, "blimp/accuracy/seq_average": 0.8128805970149253, "cbt/accuracy/NE": 0.8092948717948718, "cbt/accuracy/V": 0.94, "cbt/accuracy/CN": 0.8776, "cbt/accuracy/P": 0.9188, "cbt/accuracy/group_average": 0.886423717948718, "cbt/accuracy/seq_average": 0.8864545818327331, "hellaswag/accuracy/val": 0.3536148177653854, "hellaswag/accuracy/group_average": 0.3536148177653854, "hellaswag/accuracy/seq_average": 0.3536148177653854, "piqa/accuracy/val": 0.6284004352557128, "piqa/accuracy/group_average": 0.6284004352557128, "piqa/accuracy/seq_average": 0.6284004352557128, "ai2arc/accuracy/ARC-Easy": 0.37124735729386893, "ai2arc/accuracy/ARC-Challenge": 0.23433476394849787, "ai2arc/accuracy/group_average": 0.3027910606211834, "ai2arc/accuracy/seq_average": 0.32606232294617565, "race/accuracy/test/high": 0.29531160663236133, "race/accuracy/test/middle": 0.36142061281337046, "race/accuracy/group_average": 0.3283661097228659, "race/accuracy/seq_average": 0.3145520875557357, "siqa/accuracy/dev": 0.37154554759467756, "siqa/accuracy/group_average": 0.37154554759467756, "siqa/accuracy/seq_average": 0.37154554759467756, "commonsenseqa/accuracy/dev_rand_split": 0.27927927927927926, "commonsenseqa/accuracy/group_average": 0.27927927927927926, "commonsenseqa/accuracy/seq_average": 0.27927927927927926}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-220000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.318508814251612, "val/accuracy": 0.5181661938864087, "val/perplexity": 10.160511793438912, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.357985786769701, "lambada/accuracy/total": 0.3404503105590062, "lambada/accuracy/openai_last_token": 0.7946428571428571, "lambada/perplexity": 7.228442154102568, "lambada/lm_loss": 2.922465181671322, "lambada/lm_perplexity": 18.587051486899693, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.42930825222270746, "mean_loss": 2.3382473005106563, "blimp/accuracy/passive_2": 0.913, "blimp/accuracy/determiner_noun_agreement_2": 0.987, "blimp/accuracy/ellipsis_n_bar_1": 0.858, "blimp/accuracy/tough_vs_raising_2": 0.894, "blimp/accuracy/tough_vs_raising_1": 0.661, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.914, "blimp/accuracy/principle_A_reconstruction": 0.326, "blimp/accuracy/wh_vs_that_with_gap": 0.459, "blimp/accuracy/principle_A_domain_2": 0.899, "blimp/accuracy/determiner_noun_agreement_1": 0.988, "blimp/accuracy/ellipsis_n_bar_2": 0.922, "blimp/accuracy/principle_A_domain_3": 0.647, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.935, "blimp/accuracy/animate_subject_trans": 0.917, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.885, "blimp/accuracy/distractor_agreement_relative_clause": 0.648, "blimp/accuracy/transitive": 0.867, "blimp/accuracy/sentential_subject_island": 0.493, "blimp/accuracy/adjunct_island": 0.906, "blimp/accuracy/intransitive": 0.767, "blimp/accuracy/existential_there_subject_raising": 0.902, "blimp/accuracy/irregular_past_participle_adjectives": 0.982, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.646, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.389, "blimp/accuracy/only_npi_scope": 0.75, "blimp/accuracy/superlative_quantifiers_2": 0.75, "blimp/accuracy/passive_1": 0.901, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.911, "blimp/accuracy/inchoative": 0.652, "blimp/accuracy/anaphor_gender_agreement": 0.979, "blimp/accuracy/principle_A_c_command": 0.656, "blimp/accuracy/only_npi_licensor_present": 0.712, "blimp/accuracy/expletive_it_object_raising": 0.807, "blimp/accuracy/left_branch_island_simple_question": 0.698, "blimp/accuracy/wh_questions_subject_gap": 0.936, "blimp/accuracy/existential_there_quantifiers_2": 0.362, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.942, "blimp/accuracy/sentential_negation_npi_scope": 0.715, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.811, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.9, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.91, "blimp/accuracy/principle_A_case_2": 0.94, "blimp/accuracy/distractor_agreement_relational_noun": 0.856, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.986, "blimp/accuracy/superlative_quantifiers_1": 0.82, "blimp/accuracy/wh_island": 0.831, "blimp/accuracy/principle_A_domain_1": 0.978, "blimp/accuracy/complex_NP_island": 0.594, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.975, "blimp/accuracy/irregular_past_participle_verbs": 0.887, "blimp/accuracy/drop_argument": 0.741, "blimp/accuracy/wh_questions_object_gap": 0.851, "blimp/accuracy/animate_subject_passive": 0.77, "blimp/accuracy/existential_there_quantifiers_1": 0.986, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.903, "blimp/accuracy/npi_present_2": 0.562, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.935, "blimp/accuracy/anaphor_number_agreement": 0.993, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.953, "blimp/accuracy/existential_there_object_raising": 0.863, "blimp/accuracy/matrix_question_npi_licensor_present": 0.33, "blimp/accuracy/npi_present_1": 0.609, "blimp/accuracy/wh_vs_that_no_gap": 0.979, "blimp/accuracy/left_branch_island_echo_question": 0.538, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.971, "blimp/accuracy/causative": 0.755, "blimp/accuracy/group_average": 0.8030298507462686, "blimp/accuracy/seq_average": 0.8030298507462686, "cbt/accuracy/NE": 0.8165064102564102, "cbt/accuracy/V": 0.9396, "cbt/accuracy/CN": 0.8768, "cbt/accuracy/P": 0.9196, "cbt/accuracy/group_average": 0.8881266025641026, "cbt/accuracy/seq_average": 0.888155262104842, "hellaswag/accuracy/val": 0.3556064528978291, "hellaswag/accuracy/group_average": 0.3556064528978291, "hellaswag/accuracy/seq_average": 0.3556064528978291, "piqa/accuracy/val": 0.6305767138193689, "piqa/accuracy/group_average": 0.6305767138193689, "piqa/accuracy/seq_average": 0.6305767138193689, "ai2arc/accuracy/ARC-Easy": 0.38097251585623676, "ai2arc/accuracy/ARC-Challenge": 0.2223175965665236, "ai2arc/accuracy/group_average": 0.30164505621138016, "ai2arc/accuracy/seq_average": 0.3286118980169972, "race/accuracy/test/high": 0.2884505431675243, "race/accuracy/test/middle": 0.3732590529247911, "race/accuracy/group_average": 0.3308547980461577, "race/accuracy/seq_average": 0.3131333603567086, "siqa/accuracy/dev": 0.372057318321392, "siqa/accuracy/group_average": 0.372057318321392, "siqa/accuracy/seq_average": 0.372057318321392, "commonsenseqa/accuracy/dev_rand_split": 0.27927927927927926, "commonsenseqa/accuracy/group_average": 0.27927927927927926, "commonsenseqa/accuracy/seq_average": 0.27927927927927926}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-240000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.3040357317243303, "val/accuracy": 0.520081535218254, "val/perplexity": 10.01451691415608, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.4006120196040373, "lambada/accuracy/total": 0.3639363354037267, "lambada/accuracy/openai_last_token": 0.7993012422360248, "lambada/perplexity": 6.455044904471129, "lambada/lm_loss": 2.904104759849391, "lambada/lm_perplexity": 18.248899189932118, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.44200893531099034, "mean_loss": 2.352323875664184, "blimp/accuracy/passive_2": 0.9, "blimp/accuracy/determiner_noun_agreement_2": 0.988, "blimp/accuracy/ellipsis_n_bar_1": 0.85, "blimp/accuracy/tough_vs_raising_2": 0.898, "blimp/accuracy/tough_vs_raising_1": 0.631, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.928, "blimp/accuracy/principle_A_reconstruction": 0.413, "blimp/accuracy/wh_vs_that_with_gap": 0.479, "blimp/accuracy/principle_A_domain_2": 0.9, "blimp/accuracy/determiner_noun_agreement_1": 0.993, "blimp/accuracy/ellipsis_n_bar_2": 0.918, "blimp/accuracy/principle_A_domain_3": 0.638, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.937, "blimp/accuracy/animate_subject_trans": 0.912, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.904, "blimp/accuracy/distractor_agreement_relative_clause": 0.696, "blimp/accuracy/transitive": 0.881, "blimp/accuracy/sentential_subject_island": 0.398, "blimp/accuracy/adjunct_island": 0.908, "blimp/accuracy/intransitive": 0.763, "blimp/accuracy/existential_there_subject_raising": 0.892, "blimp/accuracy/irregular_past_participle_adjectives": 0.831, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.754, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.37, "blimp/accuracy/only_npi_scope": 0.714, "blimp/accuracy/superlative_quantifiers_2": 0.79, "blimp/accuracy/passive_1": 0.908, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.903, "blimp/accuracy/inchoative": 0.642, "blimp/accuracy/anaphor_gender_agreement": 0.977, "blimp/accuracy/principle_A_c_command": 0.706, "blimp/accuracy/only_npi_licensor_present": 0.684, "blimp/accuracy/expletive_it_object_raising": 0.791, "blimp/accuracy/left_branch_island_simple_question": 0.829, "blimp/accuracy/wh_questions_subject_gap": 0.946, "blimp/accuracy/existential_there_quantifiers_2": 0.499, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.942, "blimp/accuracy/sentential_negation_npi_scope": 0.718, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.809, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.914, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.921, "blimp/accuracy/principle_A_case_2": 0.956, "blimp/accuracy/distractor_agreement_relational_noun": 0.872, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.982, "blimp/accuracy/superlative_quantifiers_1": 0.887, "blimp/accuracy/wh_island": 0.829, "blimp/accuracy/principle_A_domain_1": 0.983, "blimp/accuracy/complex_NP_island": 0.622, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.977, "blimp/accuracy/irregular_past_participle_verbs": 0.894, "blimp/accuracy/drop_argument": 0.732, "blimp/accuracy/wh_questions_object_gap": 0.878, "blimp/accuracy/animate_subject_passive": 0.788, "blimp/accuracy/existential_there_quantifiers_1": 0.978, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.914, "blimp/accuracy/npi_present_2": 0.569, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.96, "blimp/accuracy/anaphor_number_agreement": 0.991, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.949, "blimp/accuracy/existential_there_object_raising": 0.87, "blimp/accuracy/matrix_question_npi_licensor_present": 0.307, "blimp/accuracy/npi_present_1": 0.564, "blimp/accuracy/wh_vs_that_no_gap": 0.971, "blimp/accuracy/left_branch_island_echo_question": 0.561, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.975, "blimp/accuracy/causative": 0.768, "blimp/accuracy/group_average": 0.809731343283582, "blimp/accuracy/seq_average": 0.8097313432835821, "cbt/accuracy/NE": 0.8193108974358975, "cbt/accuracy/V": 0.9348, "cbt/accuracy/CN": 0.886, "cbt/accuracy/P": 0.9224, "cbt/accuracy/group_average": 0.8906277243589744, "cbt/accuracy/seq_average": 0.890656262505002, "hellaswag/accuracy/val": 0.358195578570006, "hellaswag/accuracy/group_average": 0.358195578570006, "hellaswag/accuracy/seq_average": 0.358195578570006, "piqa/accuracy/val": 0.6376496191512514, "piqa/accuracy/group_average": 0.6376496191512514, "piqa/accuracy/seq_average": 0.6376496191512514, "ai2arc/accuracy/ARC-Easy": 0.3839323467230444, "ai2arc/accuracy/ARC-Challenge": 0.24549356223175967, "ai2arc/accuracy/group_average": 0.314712954477402, "ai2arc/accuracy/seq_average": 0.33824362606232294, "race/accuracy/test/high": 0.296169239565466, "race/accuracy/test/middle": 0.38091922005571033, "race/accuracy/group_average": 0.3385442298105882, "race/accuracy/seq_average": 0.32083502229428457, "siqa/accuracy/dev": 0.37871033776867963, "siqa/accuracy/group_average": 0.37871033776867963, "siqa/accuracy/seq_average": 0.37871033776867963, "commonsenseqa/accuracy/dev_rand_split": 0.2784602784602785, "commonsenseqa/accuracy/group_average": 0.2784602784602785, "commonsenseqa/accuracy/seq_average": 0.2784602784602785}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-260000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.2928820413256448, "val/accuracy": 0.5225878518725199, "val/perplexity": 9.903438710502822, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.3173710603891693, "lambada/accuracy/total": 0.36277173913043476, "lambada/accuracy/openai_last_token": 0.7983307453416149, "lambada/perplexity": 6.915678873726774, "lambada/lm_loss": 2.8835600077944448, "lambada/lm_perplexity": 17.877805151042217, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4426797955014773, "mean_loss": 2.3051265508574073, "blimp/accuracy/passive_2": 0.898, "blimp/accuracy/determiner_noun_agreement_2": 0.984, "blimp/accuracy/ellipsis_n_bar_1": 0.808, "blimp/accuracy/tough_vs_raising_2": 0.87, "blimp/accuracy/tough_vs_raising_1": 0.668, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.929, "blimp/accuracy/principle_A_reconstruction": 0.329, "blimp/accuracy/wh_vs_that_with_gap": 0.444, "blimp/accuracy/principle_A_domain_2": 0.902, "blimp/accuracy/determiner_noun_agreement_1": 0.993, "blimp/accuracy/ellipsis_n_bar_2": 0.92, "blimp/accuracy/principle_A_domain_3": 0.666, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.945, "blimp/accuracy/animate_subject_trans": 0.905, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.899, "blimp/accuracy/distractor_agreement_relative_clause": 0.654, "blimp/accuracy/transitive": 0.869, "blimp/accuracy/sentential_subject_island": 0.415, "blimp/accuracy/adjunct_island": 0.904, "blimp/accuracy/intransitive": 0.783, "blimp/accuracy/existential_there_subject_raising": 0.897, "blimp/accuracy/irregular_past_participle_adjectives": 0.928, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.721, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.369, "blimp/accuracy/only_npi_scope": 0.778, "blimp/accuracy/superlative_quantifiers_2": 0.783, "blimp/accuracy/passive_1": 0.909, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.922, "blimp/accuracy/inchoative": 0.659, "blimp/accuracy/anaphor_gender_agreement": 0.988, "blimp/accuracy/principle_A_c_command": 0.733, "blimp/accuracy/only_npi_licensor_present": 0.793, "blimp/accuracy/expletive_it_object_raising": 0.779, "blimp/accuracy/left_branch_island_simple_question": 0.8, "blimp/accuracy/wh_questions_subject_gap": 0.931, "blimp/accuracy/existential_there_quantifiers_2": 0.427, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.941, "blimp/accuracy/sentential_negation_npi_scope": 0.734, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.78, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.899, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.904, "blimp/accuracy/principle_A_case_2": 0.941, "blimp/accuracy/distractor_agreement_relational_noun": 0.86, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.987, "blimp/accuracy/superlative_quantifiers_1": 0.828, "blimp/accuracy/wh_island": 0.83, "blimp/accuracy/principle_A_domain_1": 0.98, "blimp/accuracy/complex_NP_island": 0.607, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.977, "blimp/accuracy/irregular_past_participle_verbs": 0.861, "blimp/accuracy/drop_argument": 0.747, "blimp/accuracy/wh_questions_object_gap": 0.859, "blimp/accuracy/animate_subject_passive": 0.811, "blimp/accuracy/existential_there_quantifiers_1": 0.989, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.923, "blimp/accuracy/npi_present_2": 0.621, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.965, "blimp/accuracy/anaphor_number_agreement": 0.988, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.963, "blimp/accuracy/existential_there_object_raising": 0.835, "blimp/accuracy/matrix_question_npi_licensor_present": 0.327, "blimp/accuracy/npi_present_1": 0.594, "blimp/accuracy/wh_vs_that_no_gap": 0.976, "blimp/accuracy/left_branch_island_echo_question": 0.532, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.978, "blimp/accuracy/causative": 0.783, "blimp/accuracy/group_average": 0.8092835820895523, "blimp/accuracy/seq_average": 0.8092835820895522, "cbt/accuracy/NE": 0.8297275641025641, "cbt/accuracy/V": 0.9412, "cbt/accuracy/CN": 0.8872, "cbt/accuracy/P": 0.9188, "cbt/accuracy/group_average": 0.894231891025641, "cbt/accuracy/seq_average": 0.8942577030812325, "hellaswag/accuracy/val": 0.36695877315275843, "hellaswag/accuracy/group_average": 0.36695877315275843, "hellaswag/accuracy/seq_average": 0.36695877315275843, "piqa/accuracy/val": 0.6409140369967355, "piqa/accuracy/group_average": 0.6409140369967355, "piqa/accuracy/seq_average": 0.6409140369967355, "ai2arc/accuracy/ARC-Easy": 0.38054968287526425, "ai2arc/accuracy/ARC-Challenge": 0.23605150214592274, "ai2arc/accuracy/group_average": 0.3083005925105935, "ai2arc/accuracy/seq_average": 0.3328611898016997, "race/accuracy/test/high": 0.2935963407661521, "race/accuracy/test/middle": 0.38440111420612816, "race/accuracy/group_average": 0.33899872748614013, "race/accuracy/seq_average": 0.3200243210376976, "siqa/accuracy/dev": 0.37563971340839303, "siqa/accuracy/group_average": 0.37563971340839303, "siqa/accuracy/seq_average": 0.37563971340839303, "commonsenseqa/accuracy/dev_rand_split": 0.2751842751842752, "commonsenseqa/accuracy/group_average": 0.2751842751842752, "commonsenseqa/accuracy/seq_average": 0.2751842751842752}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-280000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.2798258463541665, "val/accuracy": 0.5243908110119048, "val/perplexity": 9.774977913243708, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.3142203573854814, "lambada/accuracy/total": 0.3684006211180124, "lambada/accuracy/openai_last_token": 0.8027950310559007, "lambada/perplexity": 6.606654669045012, "lambada/lm_loss": 2.8686473705273614, "lambada/lm_perplexity": 17.61317797634008, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4463957160649586, "mean_loss": 2.297023101869824, "blimp/accuracy/passive_2": 0.908, "blimp/accuracy/determiner_noun_agreement_2": 0.983, "blimp/accuracy/ellipsis_n_bar_1": 0.847, "blimp/accuracy/tough_vs_raising_2": 0.881, "blimp/accuracy/tough_vs_raising_1": 0.639, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.911, "blimp/accuracy/principle_A_reconstruction": 0.374, "blimp/accuracy/wh_vs_that_with_gap": 0.502, "blimp/accuracy/principle_A_domain_2": 0.911, "blimp/accuracy/determiner_noun_agreement_1": 0.992, "blimp/accuracy/ellipsis_n_bar_2": 0.915, "blimp/accuracy/principle_A_domain_3": 0.623, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.934, "blimp/accuracy/animate_subject_trans": 0.9, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.902, "blimp/accuracy/distractor_agreement_relative_clause": 0.65, "blimp/accuracy/transitive": 0.877, "blimp/accuracy/sentential_subject_island": 0.403, "blimp/accuracy/adjunct_island": 0.899, "blimp/accuracy/intransitive": 0.802, "blimp/accuracy/existential_there_subject_raising": 0.899, "blimp/accuracy/irregular_past_participle_adjectives": 0.899, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.688, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.395, "blimp/accuracy/only_npi_scope": 0.71, "blimp/accuracy/superlative_quantifiers_2": 0.779, "blimp/accuracy/passive_1": 0.914, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.908, "blimp/accuracy/inchoative": 0.664, "blimp/accuracy/anaphor_gender_agreement": 0.983, "blimp/accuracy/principle_A_c_command": 0.73, "blimp/accuracy/only_npi_licensor_present": 0.846, "blimp/accuracy/expletive_it_object_raising": 0.784, "blimp/accuracy/left_branch_island_simple_question": 0.79, "blimp/accuracy/wh_questions_subject_gap": 0.915, "blimp/accuracy/existential_there_quantifiers_2": 0.423, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.941, "blimp/accuracy/sentential_negation_npi_scope": 0.734, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.808, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.882, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.91, "blimp/accuracy/principle_A_case_2": 0.935, "blimp/accuracy/distractor_agreement_relational_noun": 0.85, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.987, "blimp/accuracy/superlative_quantifiers_1": 0.83, "blimp/accuracy/wh_island": 0.778, "blimp/accuracy/principle_A_domain_1": 0.989, "blimp/accuracy/complex_NP_island": 0.581, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.974, "blimp/accuracy/irregular_past_participle_verbs": 0.9, "blimp/accuracy/drop_argument": 0.753, "blimp/accuracy/wh_questions_object_gap": 0.836, "blimp/accuracy/animate_subject_passive": 0.783, "blimp/accuracy/existential_there_quantifiers_1": 0.976, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.922, "blimp/accuracy/npi_present_2": 0.59, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.968, "blimp/accuracy/anaphor_number_agreement": 0.989, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.95, "blimp/accuracy/existential_there_object_raising": 0.845, "blimp/accuracy/matrix_question_npi_licensor_present": 0.322, "blimp/accuracy/npi_present_1": 0.556, "blimp/accuracy/wh_vs_that_no_gap": 0.979, "blimp/accuracy/left_branch_island_echo_question": 0.494, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.965, "blimp/accuracy/causative": 0.769, "blimp/accuracy/group_average": 0.8056119402985072, "blimp/accuracy/seq_average": 0.8056119402985075, "cbt/accuracy/NE": 0.8221153846153846, "cbt/accuracy/V": 0.9408, "cbt/accuracy/CN": 0.8912, "cbt/accuracy/P": 0.9248, "cbt/accuracy/group_average": 0.8947288461538461, "cbt/accuracy/seq_average": 0.8947579031612645, "hellaswag/accuracy/val": 0.3652658832901812, "hellaswag/accuracy/group_average": 0.3652658832901812, "hellaswag/accuracy/seq_average": 0.3652658832901812, "piqa/accuracy/val": 0.6381936887921654, "piqa/accuracy/group_average": 0.6381936887921654, "piqa/accuracy/seq_average": 0.6381936887921654, "ai2arc/accuracy/ARC-Easy": 0.3843551797040169, "ai2arc/accuracy/ARC-Challenge": 0.2317596566523605, "ai2arc/accuracy/group_average": 0.3080574181781887, "ai2arc/accuracy/seq_average": 0.3339943342776204, "race/accuracy/test/high": 0.29845626072041165, "race/accuracy/test/middle": 0.37604456824512533, "race/accuracy/group_average": 0.3372504144827685, "race/accuracy/seq_average": 0.3210376976084313, "siqa/accuracy/dev": 0.38024564994882293, "siqa/accuracy/group_average": 0.38024564994882293, "siqa/accuracy/seq_average": 0.38024564994882293, "commonsenseqa/accuracy/dev_rand_split": 0.276003276003276, "commonsenseqa/accuracy/group_average": 0.276003276003276, "commonsenseqa/accuracy/seq_average": 0.276003276003276}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-300000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.2694525340246776, "val/accuracy": 0.5252239893353174, "val/perplexity": 9.674103121751093, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.3882260529891304, "lambada/accuracy/total": 0.36374223602484473, "lambada/accuracy/openai_last_token": 0.7994953416149069, "lambada/perplexity": 6.5221847930328165, "lambada/lm_loss": 2.8694239339735113, "lambada/lm_perplexity": 17.626861038722442, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4444831126800811, "mean_loss": 2.328839293506904, "blimp/accuracy/passive_2": 0.898, "blimp/accuracy/determiner_noun_agreement_2": 0.981, "blimp/accuracy/ellipsis_n_bar_1": 0.858, "blimp/accuracy/tough_vs_raising_2": 0.871, "blimp/accuracy/tough_vs_raising_1": 0.64, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.927, "blimp/accuracy/principle_A_reconstruction": 0.381, "blimp/accuracy/wh_vs_that_with_gap": 0.501, "blimp/accuracy/principle_A_domain_2": 0.896, "blimp/accuracy/determiner_noun_agreement_1": 0.992, "blimp/accuracy/ellipsis_n_bar_2": 0.893, "blimp/accuracy/principle_A_domain_3": 0.637, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.93, "blimp/accuracy/animate_subject_trans": 0.909, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.9, "blimp/accuracy/distractor_agreement_relative_clause": 0.648, "blimp/accuracy/transitive": 0.877, "blimp/accuracy/sentential_subject_island": 0.433, "blimp/accuracy/adjunct_island": 0.886, "blimp/accuracy/intransitive": 0.783, "blimp/accuracy/existential_there_subject_raising": 0.906, "blimp/accuracy/irregular_past_participle_adjectives": 0.918, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.711, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.409, "blimp/accuracy/only_npi_scope": 0.789, "blimp/accuracy/superlative_quantifiers_2": 0.823, "blimp/accuracy/passive_1": 0.9, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.923, "blimp/accuracy/inchoative": 0.654, "blimp/accuracy/anaphor_gender_agreement": 0.984, "blimp/accuracy/principle_A_c_command": 0.711, "blimp/accuracy/only_npi_licensor_present": 0.744, "blimp/accuracy/expletive_it_object_raising": 0.811, "blimp/accuracy/left_branch_island_simple_question": 0.797, "blimp/accuracy/wh_questions_subject_gap": 0.943, "blimp/accuracy/existential_there_quantifiers_2": 0.412, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.939, "blimp/accuracy/sentential_negation_npi_scope": 0.739, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.794, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.894, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.905, "blimp/accuracy/principle_A_case_2": 0.951, "blimp/accuracy/distractor_agreement_relational_noun": 0.843, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.981, "blimp/accuracy/superlative_quantifiers_1": 0.825, "blimp/accuracy/wh_island": 0.741, "blimp/accuracy/principle_A_domain_1": 0.99, "blimp/accuracy/complex_NP_island": 0.575, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.974, "blimp/accuracy/irregular_past_participle_verbs": 0.889, "blimp/accuracy/drop_argument": 0.73, "blimp/accuracy/wh_questions_object_gap": 0.869, "blimp/accuracy/animate_subject_passive": 0.794, "blimp/accuracy/existential_there_quantifiers_1": 0.987, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.902, "blimp/accuracy/npi_present_2": 0.551, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.958, "blimp/accuracy/anaphor_number_agreement": 0.992, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.949, "blimp/accuracy/existential_there_object_raising": 0.861, "blimp/accuracy/matrix_question_npi_licensor_present": 0.29, "blimp/accuracy/npi_present_1": 0.534, "blimp/accuracy/wh_vs_that_no_gap": 0.976, "blimp/accuracy/left_branch_island_echo_question": 0.528, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.963, "blimp/accuracy/causative": 0.757, "blimp/accuracy/group_average": 0.805328358208955, "blimp/accuracy/seq_average": 0.8053283582089552, "cbt/accuracy/NE": 0.8241185897435898, "cbt/accuracy/V": 0.9412, "cbt/accuracy/CN": 0.8848, "cbt/accuracy/P": 0.9208, "cbt/accuracy/group_average": 0.8927296474358974, "cbt/accuracy/seq_average": 0.8927571028411364, "hellaswag/accuracy/val": 0.36895040828520215, "hellaswag/accuracy/group_average": 0.36895040828520215, "hellaswag/accuracy/seq_average": 0.36895040828520215, "piqa/accuracy/val": 0.6441784548422198, "piqa/accuracy/group_average": 0.6441784548422198, "piqa/accuracy/seq_average": 0.6441784548422198, "ai2arc/accuracy/ARC-Easy": 0.3758985200845666, "ai2arc/accuracy/ARC-Challenge": 0.23776824034334765, "ai2arc/accuracy/group_average": 0.3068333802139571, "ai2arc/accuracy/seq_average": 0.33031161473087817, "race/accuracy/test/high": 0.30417381360777584, "race/accuracy/test/middle": 0.3864902506963788, "race/accuracy/group_average": 0.3453320321520773, "race/accuracy/seq_average": 0.3281313336035671, "siqa/accuracy/dev": 0.38178096212896623, "siqa/accuracy/group_average": 0.38178096212896623, "siqa/accuracy/seq_average": 0.38178096212896623, "commonsenseqa/accuracy/dev_rand_split": 0.2784602784602785, "commonsenseqa/accuracy/group_average": 0.2784602784602785, "commonsenseqa/accuracy/seq_average": 0.2784602784602785}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-320000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.2622167193700395, "val/accuracy": 0.5265648251488095, "val/perplexity": 9.604355748458559, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.3591458338388005, "lambada/accuracy/total": 0.3643245341614907, "lambada/accuracy/openai_last_token": 0.7998835403726708, "lambada/perplexity": 6.682216879745231, "lambada/lm_loss": 2.8653095882144646, "lambada/lm_perplexity": 17.554487025713833, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4454446796551501, "mean_loss": 2.31068127660442, "blimp/accuracy/passive_2": 0.905, "blimp/accuracy/determiner_noun_agreement_2": 0.989, "blimp/accuracy/ellipsis_n_bar_1": 0.866, "blimp/accuracy/tough_vs_raising_2": 0.898, "blimp/accuracy/tough_vs_raising_1": 0.635, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.932, "blimp/accuracy/principle_A_reconstruction": 0.394, "blimp/accuracy/wh_vs_that_with_gap": 0.488, "blimp/accuracy/principle_A_domain_2": 0.9, "blimp/accuracy/determiner_noun_agreement_1": 0.994, "blimp/accuracy/ellipsis_n_bar_2": 0.898, "blimp/accuracy/principle_A_domain_3": 0.661, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.934, "blimp/accuracy/animate_subject_trans": 0.914, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.912, "blimp/accuracy/distractor_agreement_relative_clause": 0.67, "blimp/accuracy/transitive": 0.892, "blimp/accuracy/sentential_subject_island": 0.429, "blimp/accuracy/adjunct_island": 0.888, "blimp/accuracy/intransitive": 0.782, "blimp/accuracy/existential_there_subject_raising": 0.912, "blimp/accuracy/irregular_past_participle_adjectives": 0.93, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.77, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.383, "blimp/accuracy/only_npi_scope": 0.76, "blimp/accuracy/superlative_quantifiers_2": 0.832, "blimp/accuracy/passive_1": 0.909, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.933, "blimp/accuracy/inchoative": 0.667, "blimp/accuracy/anaphor_gender_agreement": 0.987, "blimp/accuracy/principle_A_c_command": 0.705, "blimp/accuracy/only_npi_licensor_present": 0.697, "blimp/accuracy/expletive_it_object_raising": 0.806, "blimp/accuracy/left_branch_island_simple_question": 0.847, "blimp/accuracy/wh_questions_subject_gap": 0.948, "blimp/accuracy/existential_there_quantifiers_2": 0.445, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.948, "blimp/accuracy/sentential_negation_npi_scope": 0.739, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.812, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.881, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.9, "blimp/accuracy/principle_A_case_2": 0.949, "blimp/accuracy/distractor_agreement_relational_noun": 0.848, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.985, "blimp/accuracy/superlative_quantifiers_1": 0.836, "blimp/accuracy/wh_island": 0.812, "blimp/accuracy/principle_A_domain_1": 0.987, "blimp/accuracy/complex_NP_island": 0.582, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.968, "blimp/accuracy/irregular_past_participle_verbs": 0.894, "blimp/accuracy/drop_argument": 0.752, "blimp/accuracy/wh_questions_object_gap": 0.873, "blimp/accuracy/animate_subject_passive": 0.787, "blimp/accuracy/existential_there_quantifiers_1": 0.98, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.915, "blimp/accuracy/npi_present_2": 0.616, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.968, "blimp/accuracy/anaphor_number_agreement": 0.988, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.964, "blimp/accuracy/existential_there_object_raising": 0.856, "blimp/accuracy/matrix_question_npi_licensor_present": 0.319, "blimp/accuracy/npi_present_1": 0.575, "blimp/accuracy/wh_vs_that_no_gap": 0.973, "blimp/accuracy/left_branch_island_echo_question": 0.576, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.964, "blimp/accuracy/causative": 0.766, "blimp/accuracy/group_average": 0.8138059701492537, "blimp/accuracy/seq_average": 0.8138059701492537, "cbt/accuracy/NE": 0.828125, "cbt/accuracy/V": 0.94, "cbt/accuracy/CN": 0.884, "cbt/accuracy/P": 0.9252, "cbt/accuracy/group_average": 0.89433125, "cbt/accuracy/seq_average": 0.8943577430972389, "hellaswag/accuracy/val": 0.37183827922724555, "hellaswag/accuracy/group_average": 0.37183827922724555, "hellaswag/accuracy/seq_average": 0.37183827922724555, "piqa/accuracy/val": 0.6392818280739935, "piqa/accuracy/group_average": 0.6392818280739935, "piqa/accuracy/seq_average": 0.6392818280739935, "ai2arc/accuracy/ARC-Easy": 0.3843551797040169, "ai2arc/accuracy/ARC-Challenge": 0.2240343347639485, "ai2arc/accuracy/group_average": 0.3041947572339827, "ai2arc/accuracy/seq_average": 0.3314447592067989, "race/accuracy/test/high": 0.29874213836477986, "race/accuracy/test/middle": 0.37952646239554316, "race/accuracy/group_average": 0.3391343003801615, "race/accuracy/seq_average": 0.3222537494933117, "siqa/accuracy/dev": 0.3797338792221085, "siqa/accuracy/group_average": 0.3797338792221085, "siqa/accuracy/seq_average": 0.3797338792221085, "commonsenseqa/accuracy/dev_rand_split": 0.2841932841932842, "commonsenseqa/accuracy/group_average": 0.2841932841932842, "commonsenseqa/accuracy/seq_average": 0.2841932841932842}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-340000.pth.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"val/loss": 2.2525106763082836,
|
| 3 |
+
"val/accuracy": 0.5279996357266865,
|
| 4 |
+
"val/perplexity": 9.511586397933575,
|
| 5 |
+
"val/time_since_best_loss": 0,
|
| 6 |
+
"val/time_since_best_accuracy": 0,
|
| 7 |
+
"lambada/loss": 2.3803108167944487,
|
| 8 |
+
"lambada/accuracy/total": 0.3955745341614907,
|
| 9 |
+
"lambada/accuracy/openai_last_token": 0.8064829192546584,
|
| 10 |
+
"lambada/perplexity": 6.173536739694737,
|
| 11 |
+
"lambada/lm_loss": 2.8554266725055157,
|
| 12 |
+
"lambada/lm_perplexity": 17.381851984039695,
|
| 13 |
+
"lambada/time_since_best_loss": 0,
|
| 14 |
+
"lambada/time_since_best_accuracy": 0,
|
| 15 |
+
"mean_accuracy": 0.4617870849440886,
|
| 16 |
+
"mean_loss": 2.316410746551366,
|
| 17 |
+
"blimp/accuracy/passive_2": 0.916,
|
| 18 |
+
"blimp/accuracy/determiner_noun_agreement_2": 0.987,
|
| 19 |
+
"blimp/accuracy/ellipsis_n_bar_1": 0.855,
|
| 20 |
+
"blimp/accuracy/tough_vs_raising_2": 0.889,
|
| 21 |
+
"blimp/accuracy/tough_vs_raising_1": 0.635,
|
| 22 |
+
"blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.922,
|
| 23 |
+
"blimp/accuracy/principle_A_reconstruction": 0.389,
|
| 24 |
+
"blimp/accuracy/wh_vs_that_with_gap": 0.481,
|
| 25 |
+
"blimp/accuracy/principle_A_domain_2": 0.912,
|
| 26 |
+
"blimp/accuracy/determiner_noun_agreement_1": 0.993,
|
| 27 |
+
"blimp/accuracy/ellipsis_n_bar_2": 0.906,
|
| 28 |
+
"blimp/accuracy/principle_A_domain_3": 0.645,
|
| 29 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.935,
|
| 30 |
+
"blimp/accuracy/animate_subject_trans": 0.917,
|
| 31 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.918,
|
| 32 |
+
"blimp/accuracy/distractor_agreement_relative_clause": 0.662,
|
| 33 |
+
"blimp/accuracy/transitive": 0.877,
|
| 34 |
+
"blimp/accuracy/sentential_subject_island": 0.399,
|
| 35 |
+
"blimp/accuracy/adjunct_island": 0.899,
|
| 36 |
+
"blimp/accuracy/intransitive": 0.771,
|
| 37 |
+
"blimp/accuracy/existential_there_subject_raising": 0.901,
|
| 38 |
+
"blimp/accuracy/irregular_past_participle_adjectives": 0.93,
|
| 39 |
+
"blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.757,
|
| 40 |
+
"blimp/accuracy/principle_A_case_1": 1.0,
|
| 41 |
+
"blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.406,
|
| 42 |
+
"blimp/accuracy/only_npi_scope": 0.745,
|
| 43 |
+
"blimp/accuracy/superlative_quantifiers_2": 0.833,
|
| 44 |
+
"blimp/accuracy/passive_1": 0.915,
|
| 45 |
+
"blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.93,
|
| 46 |
+
"blimp/accuracy/inchoative": 0.644,
|
| 47 |
+
"blimp/accuracy/anaphor_gender_agreement": 0.986,
|
| 48 |
+
"blimp/accuracy/principle_A_c_command": 0.698,
|
| 49 |
+
"blimp/accuracy/only_npi_licensor_present": 0.766,
|
| 50 |
+
"blimp/accuracy/expletive_it_object_raising": 0.809,
|
| 51 |
+
"blimp/accuracy/left_branch_island_simple_question": 0.838,
|
| 52 |
+
"blimp/accuracy/wh_questions_subject_gap": 0.941,
|
| 53 |
+
"blimp/accuracy/existential_there_quantifiers_2": 0.481,
|
| 54 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.948,
|
| 55 |
+
"blimp/accuracy/sentential_negation_npi_scope": 0.766,
|
| 56 |
+
"blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.817,
|
| 57 |
+
"blimp/accuracy/wh_questions_subject_gap_long_distance": 0.896,
|
| 58 |
+
"blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.912,
|
| 59 |
+
"blimp/accuracy/principle_A_case_2": 0.965,
|
| 60 |
+
"blimp/accuracy/distractor_agreement_relational_noun": 0.875,
|
| 61 |
+
"blimp/accuracy/sentential_negation_npi_licensor_present": 0.986,
|
| 62 |
+
"blimp/accuracy/superlative_quantifiers_1": 0.875,
|
| 63 |
+
"blimp/accuracy/wh_island": 0.795,
|
| 64 |
+
"blimp/accuracy/principle_A_domain_1": 0.98,
|
| 65 |
+
"blimp/accuracy/complex_NP_island": 0.602,
|
| 66 |
+
"blimp/accuracy/determiner_noun_agreement_irregular_2": 0.977,
|
| 67 |
+
"blimp/accuracy/irregular_past_participle_verbs": 0.885,
|
| 68 |
+
"blimp/accuracy/drop_argument": 0.722,
|
| 69 |
+
"blimp/accuracy/wh_questions_object_gap": 0.871,
|
| 70 |
+
"blimp/accuracy/animate_subject_passive": 0.794,
|
| 71 |
+
"blimp/accuracy/existential_there_quantifiers_1": 0.989,
|
| 72 |
+
"blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.914,
|
| 73 |
+
"blimp/accuracy/npi_present_2": 0.574,
|
| 74 |
+
"blimp/accuracy/determiner_noun_agreement_irregular_1": 0.965,
|
| 75 |
+
"blimp/accuracy/anaphor_number_agreement": 0.994,
|
| 76 |
+
"blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.96,
|
| 77 |
+
"blimp/accuracy/existential_there_object_raising": 0.856,
|
| 78 |
+
"blimp/accuracy/matrix_question_npi_licensor_present": 0.346,
|
| 79 |
+
"blimp/accuracy/npi_present_1": 0.558,
|
| 80 |
+
"blimp/accuracy/wh_vs_that_no_gap": 0.978,
|
| 81 |
+
"blimp/accuracy/left_branch_island_echo_question": 0.543,
|
| 82 |
+
"blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.964,
|
| 83 |
+
"blimp/accuracy/causative": 0.79,
|
| 84 |
+
"blimp/accuracy/group_average": 0.8147014925373133,
|
| 85 |
+
"blimp/accuracy/seq_average": 0.8147014925373134,
|
| 86 |
+
"cbt/accuracy/NE": 0.8277243589743589,
|
| 87 |
+
"cbt/accuracy/V": 0.9488,
|
| 88 |
+
"cbt/accuracy/CN": 0.8916,
|
| 89 |
+
"cbt/accuracy/P": 0.9292,
|
| 90 |
+
"cbt/accuracy/group_average": 0.8993310897435898,
|
| 91 |
+
"cbt/accuracy/seq_average": 0.899359743897559,
|
| 92 |
+
"hellaswag/accuracy/val": 0.3730332603067118,
|
| 93 |
+
"hellaswag/accuracy/group_average": 0.3730332603067118,
|
| 94 |
+
"hellaswag/accuracy/seq_average": 0.3730332603067118,
|
| 95 |
+
"piqa/accuracy/val": 0.6458106637649619,
|
| 96 |
+
"piqa/accuracy/group_average": 0.6458106637649619,
|
| 97 |
+
"piqa/accuracy/seq_average": 0.6458106637649619,
|
| 98 |
+
"ai2arc/accuracy/ARC-Easy": 0.39027484143763214,
|
| 99 |
+
"ai2arc/accuracy/ARC-Challenge": 0.22918454935622318,
|
| 100 |
+
"ai2arc/accuracy/group_average": 0.30972969539692763,
|
| 101 |
+
"ai2arc/accuracy/seq_average": 0.3371104815864023,
|
| 102 |
+
"race/accuracy/test/high": 0.2947398513436249,
|
| 103 |
+
"race/accuracy/test/middle": 0.37186629526462395,
|
| 104 |
+
"race/accuracy/group_average": 0.33330307330412445,
|
| 105 |
+
"race/accuracy/seq_average": 0.3171868666396433,
|
| 106 |
+
"siqa/accuracy/dev": 0.3766632548618219,
|
| 107 |
+
"siqa/accuracy/group_average": 0.3766632548618219,
|
| 108 |
+
"siqa/accuracy/seq_average": 0.3766632548618219,
|
| 109 |
+
"commonsenseqa/accuracy/dev_rand_split": 0.28992628992628994,
|
| 110 |
+
"commonsenseqa/accuracy/group_average": 0.28992628992628994,
|
| 111 |
+
"commonsenseqa/accuracy/seq_average": 0.28992628992628994
|
| 112 |
+
}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-360000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.2470446389818948, "val/accuracy": 0.5295313275049603, "val/perplexity": 9.459737544626108, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.289222480347438, "lambada/accuracy/total": 0.3848990683229814, "lambada/accuracy/openai_last_token": 0.8060947204968945, "lambada/perplexity": 6.196964677209961, "lambada/lm_loss": 2.8456956646544986, "lambada/lm_perplexity": 17.213529348600296, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.45721519791397086, "mean_loss": 2.2681335596646663, "blimp/accuracy/passive_2": 0.91, "blimp/accuracy/determiner_noun_agreement_2": 0.985, "blimp/accuracy/ellipsis_n_bar_1": 0.87, "blimp/accuracy/tough_vs_raising_2": 0.898, "blimp/accuracy/tough_vs_raising_1": 0.638, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.916, "blimp/accuracy/principle_A_reconstruction": 0.379, "blimp/accuracy/wh_vs_that_with_gap": 0.489, "blimp/accuracy/principle_A_domain_2": 0.91, "blimp/accuracy/determiner_noun_agreement_1": 0.993, "blimp/accuracy/ellipsis_n_bar_2": 0.905, "blimp/accuracy/principle_A_domain_3": 0.651, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.934, "blimp/accuracy/animate_subject_trans": 0.907, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.917, "blimp/accuracy/distractor_agreement_relative_clause": 0.641, "blimp/accuracy/transitive": 0.883, "blimp/accuracy/sentential_subject_island": 0.386, "blimp/accuracy/adjunct_island": 0.896, "blimp/accuracy/intransitive": 0.785, "blimp/accuracy/existential_there_subject_raising": 0.904, "blimp/accuracy/irregular_past_participle_adjectives": 0.95, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.702, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.401, "blimp/accuracy/only_npi_scope": 0.72, "blimp/accuracy/superlative_quantifiers_2": 0.899, "blimp/accuracy/passive_1": 0.901, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.917, "blimp/accuracy/inchoative": 0.663, "blimp/accuracy/anaphor_gender_agreement": 0.986, "blimp/accuracy/principle_A_c_command": 0.705, "blimp/accuracy/only_npi_licensor_present": 0.674, "blimp/accuracy/expletive_it_object_raising": 0.797, "blimp/accuracy/left_branch_island_simple_question": 0.808, "blimp/accuracy/wh_questions_subject_gap": 0.938, "blimp/accuracy/existential_there_quantifiers_2": 0.466, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.945, "blimp/accuracy/sentential_negation_npi_scope": 0.7, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.822, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.883, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.912, "blimp/accuracy/principle_A_case_2": 0.959, "blimp/accuracy/distractor_agreement_relational_noun": 0.858, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.977, "blimp/accuracy/superlative_quantifiers_1": 0.848, "blimp/accuracy/wh_island": 0.796, "blimp/accuracy/principle_A_domain_1": 0.992, "blimp/accuracy/complex_NP_island": 0.599, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.974, "blimp/accuracy/irregular_past_participle_verbs": 0.892, "blimp/accuracy/drop_argument": 0.738, "blimp/accuracy/wh_questions_object_gap": 0.86, "blimp/accuracy/animate_subject_passive": 0.791, "blimp/accuracy/existential_there_quantifiers_1": 0.994, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.905, "blimp/accuracy/npi_present_2": 0.578, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.964, "blimp/accuracy/anaphor_number_agreement": 0.993, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.962, "blimp/accuracy/existential_there_object_raising": 0.85, "blimp/accuracy/matrix_question_npi_licensor_present": 0.342, "blimp/accuracy/npi_present_1": 0.55, "blimp/accuracy/wh_vs_that_no_gap": 0.972, "blimp/accuracy/left_branch_island_echo_question": 0.556, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.961, "blimp/accuracy/causative": 0.772, "blimp/accuracy/group_average": 0.8099850746268654, "blimp/accuracy/seq_average": 0.8099850746268656, "cbt/accuracy/NE": 0.828125, "cbt/accuracy/V": 0.9468, "cbt/accuracy/CN": 0.8948, "cbt/accuracy/P": 0.926, "cbt/accuracy/group_average": 0.8989312500000001, "cbt/accuracy/seq_average": 0.8989595838335334, "hellaswag/accuracy/val": 0.3770165305715993, "hellaswag/accuracy/group_average": 0.3770165305715993, "hellaswag/accuracy/seq_average": 0.3770165305715993, "piqa/accuracy/val": 0.6447225244831338, "piqa/accuracy/group_average": 0.6447225244831338, "piqa/accuracy/seq_average": 0.6447225244831338, "ai2arc/accuracy/ARC-Easy": 0.38816067653276953, "ai2arc/accuracy/ARC-Challenge": 0.2257510729613734, "ai2arc/accuracy/group_average": 0.3069558747470715, "ai2arc/accuracy/seq_average": 0.33456090651558074, "race/accuracy/test/high": 0.29845626072041165, "race/accuracy/test/middle": 0.38231197771587744, "race/accuracy/group_average": 0.34038411921814454, "race/accuracy/seq_average": 0.32286177543575195, "siqa/accuracy/dev": 0.37717502558853633, "siqa/accuracy/group_average": 0.37717502558853633, "siqa/accuracy/seq_average": 0.37717502558853633, "commonsenseqa/accuracy/dev_rand_split": 0.28173628173628174, "commonsenseqa/accuracy/group_average": 0.28173628173628174, "commonsenseqa/accuracy/seq_average": 0.28173628173628174}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-380000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.2426869225880455, "val/accuracy": 0.5297696552579365, "val/perplexity": 9.418604379672162, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.299776254973797, "lambada/accuracy/total": 0.3856754658385093, "lambada/accuracy/openai_last_token": 0.8045419254658385, "lambada/perplexity": 6.220014884741214, "lambada/lm_loss": 2.841343766434859, "lambada/lm_perplexity": 17.13878058834505, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4577225605482229, "mean_loss": 2.271231588780921, "blimp/accuracy/passive_2": 0.906, "blimp/accuracy/determiner_noun_agreement_2": 0.985, "blimp/accuracy/ellipsis_n_bar_1": 0.867, "blimp/accuracy/tough_vs_raising_2": 0.895, "blimp/accuracy/tough_vs_raising_1": 0.635, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.931, "blimp/accuracy/principle_A_reconstruction": 0.369, "blimp/accuracy/wh_vs_that_with_gap": 0.448, "blimp/accuracy/principle_A_domain_2": 0.908, "blimp/accuracy/determiner_noun_agreement_1": 0.991, "blimp/accuracy/ellipsis_n_bar_2": 0.91, "blimp/accuracy/principle_A_domain_3": 0.653, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.932, "blimp/accuracy/animate_subject_trans": 0.917, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.915, "blimp/accuracy/distractor_agreement_relative_clause": 0.657, "blimp/accuracy/transitive": 0.882, "blimp/accuracy/sentential_subject_island": 0.419, "blimp/accuracy/adjunct_island": 0.887, "blimp/accuracy/intransitive": 0.774, "blimp/accuracy/existential_there_subject_raising": 0.898, "blimp/accuracy/irregular_past_participle_adjectives": 0.961, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.695, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.392, "blimp/accuracy/only_npi_scope": 0.763, "blimp/accuracy/superlative_quantifiers_2": 0.825, "blimp/accuracy/passive_1": 0.911, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.913, "blimp/accuracy/inchoative": 0.664, "blimp/accuracy/anaphor_gender_agreement": 0.988, "blimp/accuracy/principle_A_c_command": 0.698, "blimp/accuracy/only_npi_licensor_present": 0.779, "blimp/accuracy/expletive_it_object_raising": 0.803, "blimp/accuracy/left_branch_island_simple_question": 0.79, "blimp/accuracy/wh_questions_subject_gap": 0.939, "blimp/accuracy/existential_there_quantifiers_2": 0.502, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.944, "blimp/accuracy/sentential_negation_npi_scope": 0.703, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.814, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.888, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.891, "blimp/accuracy/principle_A_case_2": 0.965, "blimp/accuracy/distractor_agreement_relational_noun": 0.848, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.977, "blimp/accuracy/superlative_quantifiers_1": 0.866, "blimp/accuracy/wh_island": 0.82, "blimp/accuracy/principle_A_domain_1": 0.991, "blimp/accuracy/complex_NP_island": 0.591, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.976, "blimp/accuracy/irregular_past_participle_verbs": 0.912, "blimp/accuracy/drop_argument": 0.722, "blimp/accuracy/wh_questions_object_gap": 0.873, "blimp/accuracy/animate_subject_passive": 0.796, "blimp/accuracy/existential_there_quantifiers_1": 0.996, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.9, "blimp/accuracy/npi_present_2": 0.574, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.97, "blimp/accuracy/anaphor_number_agreement": 0.993, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.96, "blimp/accuracy/existential_there_object_raising": 0.868, "blimp/accuracy/matrix_question_npi_licensor_present": 0.356, "blimp/accuracy/npi_present_1": 0.546, "blimp/accuracy/wh_vs_that_no_gap": 0.974, "blimp/accuracy/left_branch_island_echo_question": 0.518, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.971, "blimp/accuracy/causative": 0.772, "blimp/accuracy/group_average": 0.811597014925373, "blimp/accuracy/seq_average": 0.8115970149253732, "cbt/accuracy/NE": 0.8313301282051282, "cbt/accuracy/V": 0.946, "cbt/accuracy/CN": 0.8948, "cbt/accuracy/P": 0.93, "cbt/accuracy/group_average": 0.9005325320512821, "cbt/accuracy/seq_average": 0.9005602240896359, "hellaswag/accuracy/val": 0.3760207130053774, "hellaswag/accuracy/group_average": 0.3760207130053774, "hellaswag/accuracy/seq_average": 0.3760207130053774, "piqa/accuracy/val": 0.6479869423286181, "piqa/accuracy/group_average": 0.6479869423286181, "piqa/accuracy/seq_average": 0.6479869423286181, "ai2arc/accuracy/ARC-Easy": 0.3945031712473573, "ai2arc/accuracy/ARC-Challenge": 0.2429184549356223, "ai2arc/accuracy/group_average": 0.3187108130914898, "ai2arc/accuracy/seq_average": 0.3444759206798867, "race/accuracy/test/high": 0.2950257289879931, "race/accuracy/test/middle": 0.38231197771587744, "race/accuracy/group_average": 0.3386688533519353, "race/accuracy/seq_average": 0.32042967166599107, "siqa/accuracy/dev": 0.37563971340839303, "siqa/accuracy/group_average": 0.37563971340839303, "siqa/accuracy/seq_average": 0.37563971340839303, "commonsenseqa/accuracy/dev_rand_split": 0.2882882882882883, "commonsenseqa/accuracy/group_average": 0.2882882882882883, "commonsenseqa/accuracy/seq_average": 0.2882882882882883}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-40000.pth.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"val/loss": 2.5821024576822915,
|
| 3 |
+
"val/accuracy": 0.48042418464781744,
|
| 4 |
+
"val/perplexity": 13.224913772460209,
|
| 5 |
+
"val/time_since_best_loss": 0,
|
| 6 |
+
"val/time_since_best_accuracy": 0,
|
| 7 |
+
"lambada/loss": 2.685775282960501,
|
| 8 |
+
"lambada/accuracy/total": 0.27212732919254656,
|
| 9 |
+
"lambada/accuracy/openai_last_token": 0.7620341614906833,
|
| 10 |
+
"lambada/perplexity": 10.52323568334199,
|
| 11 |
+
"lambada/lm_loss": 3.1517991652401296,
|
| 12 |
+
"lambada/lm_perplexity": 23.378087809208203,
|
| 13 |
+
"lambada/time_since_best_loss": 0,
|
| 14 |
+
"lambada/time_since_best_accuracy": 0,
|
| 15 |
+
"mean_accuracy": 0.376275756920182,
|
| 16 |
+
"mean_loss": 2.633938870321396,
|
| 17 |
+
"blimp/accuracy/passive_2": 0.899,
|
| 18 |
+
"blimp/accuracy/determiner_noun_agreement_2": 0.982,
|
| 19 |
+
"blimp/accuracy/ellipsis_n_bar_1": 0.832,
|
| 20 |
+
"blimp/accuracy/tough_vs_raising_2": 0.861,
|
| 21 |
+
"blimp/accuracy/tough_vs_raising_1": 0.687,
|
| 22 |
+
"blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.902,
|
| 23 |
+
"blimp/accuracy/principle_A_reconstruction": 0.316,
|
| 24 |
+
"blimp/accuracy/wh_vs_that_with_gap": 0.514,
|
| 25 |
+
"blimp/accuracy/principle_A_domain_2": 0.873,
|
| 26 |
+
"blimp/accuracy/determiner_noun_agreement_1": 0.997,
|
| 27 |
+
"blimp/accuracy/ellipsis_n_bar_2": 0.899,
|
| 28 |
+
"blimp/accuracy/principle_A_domain_3": 0.612,
|
| 29 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.927,
|
| 30 |
+
"blimp/accuracy/animate_subject_trans": 0.902,
|
| 31 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.907,
|
| 32 |
+
"blimp/accuracy/distractor_agreement_relative_clause": 0.569,
|
| 33 |
+
"blimp/accuracy/transitive": 0.839,
|
| 34 |
+
"blimp/accuracy/sentential_subject_island": 0.396,
|
| 35 |
+
"blimp/accuracy/adjunct_island": 0.843,
|
| 36 |
+
"blimp/accuracy/intransitive": 0.752,
|
| 37 |
+
"blimp/accuracy/existential_there_subject_raising": 0.886,
|
| 38 |
+
"blimp/accuracy/irregular_past_participle_adjectives": 0.913,
|
| 39 |
+
"blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.465,
|
| 40 |
+
"blimp/accuracy/principle_A_case_1": 1.0,
|
| 41 |
+
"blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.241,
|
| 42 |
+
"blimp/accuracy/only_npi_scope": 0.567,
|
| 43 |
+
"blimp/accuracy/superlative_quantifiers_2": 0.672,
|
| 44 |
+
"blimp/accuracy/passive_1": 0.873,
|
| 45 |
+
"blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.914,
|
| 46 |
+
"blimp/accuracy/inchoative": 0.625,
|
| 47 |
+
"blimp/accuracy/anaphor_gender_agreement": 0.95,
|
| 48 |
+
"blimp/accuracy/principle_A_c_command": 0.632,
|
| 49 |
+
"blimp/accuracy/only_npi_licensor_present": 0.636,
|
| 50 |
+
"blimp/accuracy/expletive_it_object_raising": 0.766,
|
| 51 |
+
"blimp/accuracy/left_branch_island_simple_question": 0.481,
|
| 52 |
+
"blimp/accuracy/wh_questions_subject_gap": 0.957,
|
| 53 |
+
"blimp/accuracy/existential_there_quantifiers_2": 0.399,
|
| 54 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.95,
|
| 55 |
+
"blimp/accuracy/sentential_negation_npi_scope": 0.713,
|
| 56 |
+
"blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.77,
|
| 57 |
+
"blimp/accuracy/wh_questions_subject_gap_long_distance": 0.915,
|
| 58 |
+
"blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.87,
|
| 59 |
+
"blimp/accuracy/principle_A_case_2": 0.954,
|
| 60 |
+
"blimp/accuracy/distractor_agreement_relational_noun": 0.838,
|
| 61 |
+
"blimp/accuracy/sentential_negation_npi_licensor_present": 0.988,
|
| 62 |
+
"blimp/accuracy/superlative_quantifiers_1": 0.542,
|
| 63 |
+
"blimp/accuracy/wh_island": 0.741,
|
| 64 |
+
"blimp/accuracy/principle_A_domain_1": 0.964,
|
| 65 |
+
"blimp/accuracy/complex_NP_island": 0.599,
|
| 66 |
+
"blimp/accuracy/determiner_noun_agreement_irregular_2": 0.966,
|
| 67 |
+
"blimp/accuracy/irregular_past_participle_verbs": 0.918,
|
| 68 |
+
"blimp/accuracy/drop_argument": 0.765,
|
| 69 |
+
"blimp/accuracy/wh_questions_object_gap": 0.873,
|
| 70 |
+
"blimp/accuracy/animate_subject_passive": 0.791,
|
| 71 |
+
"blimp/accuracy/existential_there_quantifiers_1": 0.975,
|
| 72 |
+
"blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.898,
|
| 73 |
+
"blimp/accuracy/npi_present_2": 0.575,
|
| 74 |
+
"blimp/accuracy/determiner_noun_agreement_irregular_1": 0.937,
|
| 75 |
+
"blimp/accuracy/anaphor_number_agreement": 0.983,
|
| 76 |
+
"blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.957,
|
| 77 |
+
"blimp/accuracy/existential_there_object_raising": 0.802,
|
| 78 |
+
"blimp/accuracy/matrix_question_npi_licensor_present": 0.287,
|
| 79 |
+
"blimp/accuracy/npi_present_1": 0.527,
|
| 80 |
+
"blimp/accuracy/wh_vs_that_no_gap": 0.981,
|
| 81 |
+
"blimp/accuracy/left_branch_island_echo_question": 0.452,
|
| 82 |
+
"blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.983,
|
| 83 |
+
"blimp/accuracy/causative": 0.718,
|
| 84 |
+
"blimp/accuracy/group_average": 0.7719104477611939,
|
| 85 |
+
"blimp/accuracy/seq_average": 0.771910447761194,
|
| 86 |
+
"cbt/accuracy/NE": 0.7704326923076923,
|
| 87 |
+
"cbt/accuracy/V": 0.9196,
|
| 88 |
+
"cbt/accuracy/CN": 0.832,
|
| 89 |
+
"cbt/accuracy/P": 0.8976,
|
| 90 |
+
"cbt/accuracy/group_average": 0.854908173076923,
|
| 91 |
+
"cbt/accuracy/seq_average": 0.8549419767907163,
|
| 92 |
+
"hellaswag/accuracy/val": 0.3027285401314479,
|
| 93 |
+
"hellaswag/accuracy/group_average": 0.3027285401314479,
|
| 94 |
+
"hellaswag/accuracy/seq_average": 0.3027285401314479,
|
| 95 |
+
"piqa/accuracy/val": 0.6006528835690969,
|
| 96 |
+
"piqa/accuracy/group_average": 0.6006528835690969,
|
| 97 |
+
"piqa/accuracy/seq_average": 0.6006528835690969,
|
| 98 |
+
"ai2arc/accuracy/ARC-Easy": 0.3361522198731501,
|
| 99 |
+
"ai2arc/accuracy/ARC-Challenge": 0.21802575107296138,
|
| 100 |
+
"ai2arc/accuracy/group_average": 0.2770889854730557,
|
| 101 |
+
"ai2arc/accuracy/seq_average": 0.2971671388101983,
|
| 102 |
+
"race/accuracy/test/high": 0.27901658090337333,
|
| 103 |
+
"race/accuracy/test/middle": 0.34540389972144847,
|
| 104 |
+
"race/accuracy/group_average": 0.3122102403124109,
|
| 105 |
+
"race/accuracy/seq_average": 0.29833806242399674,
|
| 106 |
+
"siqa/accuracy/dev": 0.3638689866939611,
|
| 107 |
+
"siqa/accuracy/group_average": 0.3638689866939611,
|
| 108 |
+
"siqa/accuracy/seq_average": 0.3638689866939611,
|
| 109 |
+
"commonsenseqa/accuracy/dev_rand_split": 0.25061425061425063,
|
| 110 |
+
"commonsenseqa/accuracy/group_average": 0.25061425061425063,
|
| 111 |
+
"commonsenseqa/accuracy/seq_average": 0.25061425061425063
|
| 112 |
+
}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-400000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.238520788767981, "val/accuracy": 0.5304081023685516, "val/perplexity": 9.379446837844892, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.2897871503178377, "lambada/accuracy/total": 0.3880046583850932, "lambada/accuracy/openai_last_token": 0.811141304347826, "lambada/perplexity": 6.201509009762254, "lambada/lm_loss": 2.8390284811519018, "lambada/lm_perplexity": 17.09914532305978, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.4592063803768224, "mean_loss": 2.2641539695429094, "blimp/accuracy/passive_2": 0.912, "blimp/accuracy/determiner_noun_agreement_2": 0.986, "blimp/accuracy/ellipsis_n_bar_1": 0.853, "blimp/accuracy/tough_vs_raising_2": 0.893, "blimp/accuracy/tough_vs_raising_1": 0.631, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.935, "blimp/accuracy/principle_A_reconstruction": 0.382, "blimp/accuracy/wh_vs_that_with_gap": 0.456, "blimp/accuracy/principle_A_domain_2": 0.9, "blimp/accuracy/determiner_noun_agreement_1": 0.994, "blimp/accuracy/ellipsis_n_bar_2": 0.912, "blimp/accuracy/principle_A_domain_3": 0.667, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.94, "blimp/accuracy/animate_subject_trans": 0.911, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.915, "blimp/accuracy/distractor_agreement_relative_clause": 0.644, "blimp/accuracy/transitive": 0.883, "blimp/accuracy/sentential_subject_island": 0.42, "blimp/accuracy/adjunct_island": 0.885, "blimp/accuracy/intransitive": 0.778, "blimp/accuracy/existential_there_subject_raising": 0.911, "blimp/accuracy/irregular_past_participle_adjectives": 0.935, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.706, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.387, "blimp/accuracy/only_npi_scope": 0.767, "blimp/accuracy/superlative_quantifiers_2": 0.805, "blimp/accuracy/passive_1": 0.916, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.917, "blimp/accuracy/inchoative": 0.658, "blimp/accuracy/anaphor_gender_agreement": 0.99, "blimp/accuracy/principle_A_c_command": 0.697, "blimp/accuracy/only_npi_licensor_present": 0.684, "blimp/accuracy/expletive_it_object_raising": 0.804, "blimp/accuracy/left_branch_island_simple_question": 0.804, "blimp/accuracy/wh_questions_subject_gap": 0.936, "blimp/accuracy/existential_there_quantifiers_2": 0.457, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.945, "blimp/accuracy/sentential_negation_npi_scope": 0.752, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.796, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.891, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.905, "blimp/accuracy/principle_A_case_2": 0.962, "blimp/accuracy/distractor_agreement_relational_noun": 0.85, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.983, "blimp/accuracy/superlative_quantifiers_1": 0.781, "blimp/accuracy/wh_island": 0.825, "blimp/accuracy/principle_A_domain_1": 0.989, "blimp/accuracy/complex_NP_island": 0.594, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.973, "blimp/accuracy/irregular_past_participle_verbs": 0.896, "blimp/accuracy/drop_argument": 0.729, "blimp/accuracy/wh_questions_object_gap": 0.867, "blimp/accuracy/animate_subject_passive": 0.796, "blimp/accuracy/existential_there_quantifiers_1": 0.99, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.907, "blimp/accuracy/npi_present_2": 0.594, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.972, "blimp/accuracy/anaphor_number_agreement": 0.99, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.959, "blimp/accuracy/existential_there_object_raising": 0.865, "blimp/accuracy/matrix_question_npi_licensor_present": 0.327, "blimp/accuracy/npi_present_1": 0.557, "blimp/accuracy/wh_vs_that_no_gap": 0.978, "blimp/accuracy/left_branch_island_echo_question": 0.509, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.972, "blimp/accuracy/causative": 0.765, "blimp/accuracy/group_average": 0.8088059701492539, "blimp/accuracy/seq_average": 0.8088059701492537, "cbt/accuracy/NE": 0.8305288461538461, "cbt/accuracy/V": 0.9464, "cbt/accuracy/CN": 0.8884, "cbt/accuracy/P": 0.9252, "cbt/accuracy/group_average": 0.8976322115384616, "cbt/accuracy/seq_average": 0.8976590636254502, "hellaswag/accuracy/val": 0.3770165305715993, "hellaswag/accuracy/group_average": 0.3770165305715993, "hellaswag/accuracy/seq_average": 0.3770165305715993, "piqa/accuracy/val": 0.6463547334058759, "piqa/accuracy/group_average": 0.6463547334058759, "piqa/accuracy/seq_average": 0.6463547334058759, "ai2arc/accuracy/ARC-Easy": 0.39365750528541227, "ai2arc/accuracy/ARC-Challenge": 0.23776824034334765, "ai2arc/accuracy/group_average": 0.31571287281438, "ai2arc/accuracy/seq_average": 0.3422096317280453, "race/accuracy/test/high": 0.2967409948542024, "race/accuracy/test/middle": 0.38370473537604455, "race/accuracy/group_average": 0.34022286511512345, "race/accuracy/seq_average": 0.32205107417916495, "siqa/accuracy/dev": 0.3797338792221085, "siqa/accuracy/group_average": 0.3797338792221085, "siqa/accuracy/seq_average": 0.3797338792221085, "commonsenseqa/accuracy/dev_rand_split": 0.2833742833742834, "commonsenseqa/accuracy/group_average": 0.2833742833742834, "commonsenseqa/accuracy/seq_average": 0.2833742833742834}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_660M_standardlb_plus_plus/export/result-model-60000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.5145140148344494, "val/accuracy": 0.4897664388020833, "val/perplexity": 12.360600250843435, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.6118270210597827, "lambada/accuracy/total": 0.27445652173913043, "lambada/accuracy/openai_last_token": 0.7626164596273292, "lambada/perplexity": 10.315610267235181, "lambada/lm_loss": 3.0734778308815054, "lambada/lm_perplexity": 21.616952198501583, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3821114802706069, "mean_loss": 2.563170517947116, "blimp/accuracy/passive_2": 0.895, "blimp/accuracy/determiner_noun_agreement_2": 0.983, "blimp/accuracy/ellipsis_n_bar_1": 0.818, "blimp/accuracy/tough_vs_raising_2": 0.87, "blimp/accuracy/tough_vs_raising_1": 0.579, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.904, "blimp/accuracy/principle_A_reconstruction": 0.341, "blimp/accuracy/wh_vs_that_with_gap": 0.585, "blimp/accuracy/principle_A_domain_2": 0.884, "blimp/accuracy/determiner_noun_agreement_1": 0.992, "blimp/accuracy/ellipsis_n_bar_2": 0.903, "blimp/accuracy/principle_A_domain_3": 0.591, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.94, "blimp/accuracy/animate_subject_trans": 0.904, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.89, "blimp/accuracy/distractor_agreement_relative_clause": 0.649, "blimp/accuracy/transitive": 0.857, "blimp/accuracy/sentential_subject_island": 0.402, "blimp/accuracy/adjunct_island": 0.849, "blimp/accuracy/intransitive": 0.726, "blimp/accuracy/existential_there_subject_raising": 0.886, "blimp/accuracy/irregular_past_participle_adjectives": 0.883, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.544, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.325, "blimp/accuracy/only_npi_scope": 0.604, "blimp/accuracy/superlative_quantifiers_2": 0.541, "blimp/accuracy/passive_1": 0.883, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.933, "blimp/accuracy/inchoative": 0.627, "blimp/accuracy/anaphor_gender_agreement": 0.979, "blimp/accuracy/principle_A_c_command": 0.643, "blimp/accuracy/only_npi_licensor_present": 0.782, "blimp/accuracy/expletive_it_object_raising": 0.81, "blimp/accuracy/left_branch_island_simple_question": 0.648, "blimp/accuracy/wh_questions_subject_gap": 0.921, "blimp/accuracy/existential_there_quantifiers_2": 0.47, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.952, "blimp/accuracy/sentential_negation_npi_scope": 0.556, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.791, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.853, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.908, "blimp/accuracy/principle_A_case_2": 0.955, "blimp/accuracy/distractor_agreement_relational_noun": 0.85, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.99, "blimp/accuracy/superlative_quantifiers_1": 0.648, "blimp/accuracy/wh_island": 0.857, "blimp/accuracy/principle_A_domain_1": 0.971, "blimp/accuracy/complex_NP_island": 0.571, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.976, "blimp/accuracy/irregular_past_participle_verbs": 0.872, "blimp/accuracy/drop_argument": 0.714, "blimp/accuracy/wh_questions_object_gap": 0.817, "blimp/accuracy/animate_subject_passive": 0.798, "blimp/accuracy/existential_there_quantifiers_1": 0.983, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.921, "blimp/accuracy/npi_present_2": 0.568, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.957, "blimp/accuracy/anaphor_number_agreement": 0.995, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.969, "blimp/accuracy/existential_there_object_raising": 0.812, "blimp/accuracy/matrix_question_npi_licensor_present": 0.274, "blimp/accuracy/npi_present_1": 0.518, "blimp/accuracy/wh_vs_that_no_gap": 0.97, "blimp/accuracy/left_branch_island_echo_question": 0.41, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.968, "blimp/accuracy/causative": 0.725, "blimp/accuracy/group_average": 0.7789552238805969, "blimp/accuracy/seq_average": 0.778955223880597, "cbt/accuracy/NE": 0.7864583333333334, "cbt/accuracy/V": 0.918, "cbt/accuracy/CN": 0.8492, "cbt/accuracy/P": 0.8956, "cbt/accuracy/group_average": 0.8623145833333333, "cbt/accuracy/seq_average": 0.8623449379751901, "hellaswag/accuracy/val": 0.3181637124078869, "hellaswag/accuracy/group_average": 0.3181637124078869, "hellaswag/accuracy/seq_average": 0.3181637124078869, "piqa/accuracy/val": 0.5952121871599565, "piqa/accuracy/group_average": 0.5952121871599565, "piqa/accuracy/seq_average": 0.5952121871599565, "ai2arc/accuracy/ARC-Easy": 0.35391120507399576, "ai2arc/accuracy/ARC-Challenge": 0.21802575107296138, "ai2arc/accuracy/group_average": 0.2859684780734786, "ai2arc/accuracy/seq_average": 0.30906515580736543, "race/accuracy/test/high": 0.2830188679245283, "race/accuracy/test/middle": 0.3516713091922006, "race/accuracy/group_average": 0.3173450885583644, "race/accuracy/seq_average": 0.3029995946493717, "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_660M_standardlb_plus_plus/export/result-model-80000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.4662371438647073, "val/accuracy": 0.49671185205853174, "val/perplexity": 11.778044277617171, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.5461812463606366, "lambada/accuracy/total": 0.29289596273291924, "lambada/accuracy/openai_last_token": 0.7719332298136646, "lambada/perplexity": 9.328725176571004, "lambada/lm_loss": 3.044320689012138, "lambada/lm_perplexity": 20.99576370441097, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.39480390739572546, "mean_loss": 2.506209195112672, "blimp/accuracy/passive_2": 0.887, "blimp/accuracy/determiner_noun_agreement_2": 0.987, "blimp/accuracy/ellipsis_n_bar_1": 0.813, "blimp/accuracy/tough_vs_raising_2": 0.866, "blimp/accuracy/tough_vs_raising_1": 0.668, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.92, "blimp/accuracy/principle_A_reconstruction": 0.303, "blimp/accuracy/wh_vs_that_with_gap": 0.541, "blimp/accuracy/principle_A_domain_2": 0.888, "blimp/accuracy/determiner_noun_agreement_1": 0.991, "blimp/accuracy/ellipsis_n_bar_2": 0.913, "blimp/accuracy/principle_A_domain_3": 0.611, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.943, "blimp/accuracy/animate_subject_trans": 0.91, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.867, "blimp/accuracy/distractor_agreement_relative_clause": 0.635, "blimp/accuracy/transitive": 0.859, "blimp/accuracy/sentential_subject_island": 0.371, "blimp/accuracy/adjunct_island": 0.855, "blimp/accuracy/intransitive": 0.762, "blimp/accuracy/existential_there_subject_raising": 0.886, "blimp/accuracy/irregular_past_participle_adjectives": 0.906, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.598, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.404, "blimp/accuracy/only_npi_scope": 0.773, "blimp/accuracy/superlative_quantifiers_2": 0.733, "blimp/accuracy/passive_1": 0.908, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.912, "blimp/accuracy/inchoative": 0.646, "blimp/accuracy/anaphor_gender_agreement": 0.974, "blimp/accuracy/principle_A_c_command": 0.684, "blimp/accuracy/only_npi_licensor_present": 0.739, "blimp/accuracy/expletive_it_object_raising": 0.764, "blimp/accuracy/left_branch_island_simple_question": 0.624, "blimp/accuracy/wh_questions_subject_gap": 0.927, "blimp/accuracy/existential_there_quantifiers_2": 0.466, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.948, "blimp/accuracy/sentential_negation_npi_scope": 0.678, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.792, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.865, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.892, "blimp/accuracy/principle_A_case_2": 0.943, "blimp/accuracy/distractor_agreement_relational_noun": 0.855, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.982, "blimp/accuracy/superlative_quantifiers_1": 0.638, "blimp/accuracy/wh_island": 0.774, "blimp/accuracy/principle_A_domain_1": 0.964, "blimp/accuracy/complex_NP_island": 0.603, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.977, "blimp/accuracy/irregular_past_participle_verbs": 0.869, "blimp/accuracy/drop_argument": 0.727, "blimp/accuracy/wh_questions_object_gap": 0.85, "blimp/accuracy/animate_subject_passive": 0.795, "blimp/accuracy/existential_there_quantifiers_1": 0.984, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.916, "blimp/accuracy/npi_present_2": 0.561, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.948, "blimp/accuracy/anaphor_number_agreement": 0.99, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.955, "blimp/accuracy/existential_there_object_raising": 0.785, "blimp/accuracy/matrix_question_npi_licensor_present": 0.292, "blimp/accuracy/npi_present_1": 0.553, "blimp/accuracy/wh_vs_that_no_gap": 0.969, "blimp/accuracy/left_branch_island_echo_question": 0.452, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.948, "blimp/accuracy/causative": 0.734, "blimp/accuracy/group_average": 0.7876567164179102, "blimp/accuracy/seq_average": 0.7876567164179105, "cbt/accuracy/NE": 0.7992788461538461, "cbt/accuracy/V": 0.9304, "cbt/accuracy/CN": 0.856, "cbt/accuracy/P": 0.9052, "cbt/accuracy/group_average": 0.8727197115384615, "cbt/accuracy/seq_average": 0.8727490996398559, "hellaswag/accuracy/val": 0.32224656442939653, "hellaswag/accuracy/group_average": 0.32224656442939653, "hellaswag/accuracy/seq_average": 0.32224656442939653, "piqa/accuracy/val": 0.6153427638737758, "piqa/accuracy/group_average": 0.6153427638737758, "piqa/accuracy/seq_average": 0.6153427638737758, "ai2arc/accuracy/ARC-Easy": 0.35560253699788585, "ai2arc/accuracy/ARC-Challenge": 0.2240343347639485, "ai2arc/accuracy/group_average": 0.28981843588091716, "ai2arc/accuracy/seq_average": 0.31218130311614734, "race/accuracy/test/high": 0.2893081761006289, "race/accuracy/test/middle": 0.3544568245125348, "race/accuracy/group_average": 0.32188250030658183, "race/accuracy/seq_average": 0.30826915281718686, "siqa/accuracy/dev": 0.3694984646878199, "siqa/accuracy/group_average": 0.3694984646878199, "siqa/accuracy/seq_average": 0.3694984646878199, "commonsenseqa/accuracy/dev_rand_split": 0.257985257985258, "commonsenseqa/accuracy/group_average": 0.257985257985258, "commonsenseqa/accuracy/seq_average": 0.257985257985258}
|