Upload folder using huggingface_hub
#335
by
DavidNguyen
- opened
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-10000.pth.json +112 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-100000.pth.json +112 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-20000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-30000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-40000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-50000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-60000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-70000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-80000.pth.json +1 -0
- Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-90000.pth.json +1 -0
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-10000.pth.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"val/loss": 3.0374574207124256,
|
| 3 |
+
"val/accuracy": 0.422272212921627,
|
| 4 |
+
"val/perplexity": 20.852157512569427,
|
| 5 |
+
"val/time_since_best_loss": 0,
|
| 6 |
+
"val/time_since_best_accuracy": 0,
|
| 7 |
+
"lambada/loss": 2.7999360457710596,
|
| 8 |
+
"lambada/accuracy/total": 0.15605590062111802,
|
| 9 |
+
"lambada/accuracy/openai_last_token": 0.717391304347826,
|
| 10 |
+
"lambada/perplexity": 25.65179397539376,
|
| 11 |
+
"lambada/lm_loss": 3.5712717276521566,
|
| 12 |
+
"lambada/lm_perplexity": 35.561789317765644,
|
| 13 |
+
"lambada/time_since_best_loss": 0,
|
| 14 |
+
"lambada/time_since_best_accuracy": 0,
|
| 15 |
+
"mean_accuracy": 0.28916405677137247,
|
| 16 |
+
"mean_loss": 2.9186967332417426,
|
| 17 |
+
"blimp/accuracy/passive_2": 0.861,
|
| 18 |
+
"blimp/accuracy/determiner_noun_agreement_2": 0.958,
|
| 19 |
+
"blimp/accuracy/ellipsis_n_bar_1": 0.628,
|
| 20 |
+
"blimp/accuracy/tough_vs_raising_2": 0.844,
|
| 21 |
+
"blimp/accuracy/tough_vs_raising_1": 0.528,
|
| 22 |
+
"blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.867,
|
| 23 |
+
"blimp/accuracy/principle_A_reconstruction": 0.39,
|
| 24 |
+
"blimp/accuracy/wh_vs_that_with_gap": 0.425,
|
| 25 |
+
"blimp/accuracy/principle_A_domain_2": 0.788,
|
| 26 |
+
"blimp/accuracy/determiner_noun_agreement_1": 0.975,
|
| 27 |
+
"blimp/accuracy/ellipsis_n_bar_2": 0.845,
|
| 28 |
+
"blimp/accuracy/principle_A_domain_3": 0.574,
|
| 29 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.869,
|
| 30 |
+
"blimp/accuracy/animate_subject_trans": 0.879,
|
| 31 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.769,
|
| 32 |
+
"blimp/accuracy/distractor_agreement_relative_clause": 0.463,
|
| 33 |
+
"blimp/accuracy/transitive": 0.816,
|
| 34 |
+
"blimp/accuracy/sentential_subject_island": 0.297,
|
| 35 |
+
"blimp/accuracy/adjunct_island": 0.648,
|
| 36 |
+
"blimp/accuracy/intransitive": 0.706,
|
| 37 |
+
"blimp/accuracy/existential_there_subject_raising": 0.866,
|
| 38 |
+
"blimp/accuracy/irregular_past_participle_adjectives": 0.959,
|
| 39 |
+
"blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.268,
|
| 40 |
+
"blimp/accuracy/principle_A_case_1": 1.0,
|
| 41 |
+
"blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.144,
|
| 42 |
+
"blimp/accuracy/only_npi_scope": 0.593,
|
| 43 |
+
"blimp/accuracy/superlative_quantifiers_2": 0.805,
|
| 44 |
+
"blimp/accuracy/passive_1": 0.896,
|
| 45 |
+
"blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.868,
|
| 46 |
+
"blimp/accuracy/inchoative": 0.551,
|
| 47 |
+
"blimp/accuracy/anaphor_gender_agreement": 0.936,
|
| 48 |
+
"blimp/accuracy/principle_A_c_command": 0.564,
|
| 49 |
+
"blimp/accuracy/only_npi_licensor_present": 0.508,
|
| 50 |
+
"blimp/accuracy/expletive_it_object_raising": 0.742,
|
| 51 |
+
"blimp/accuracy/left_branch_island_simple_question": 0.294,
|
| 52 |
+
"blimp/accuracy/wh_questions_subject_gap": 0.902,
|
| 53 |
+
"blimp/accuracy/existential_there_quantifiers_2": 0.404,
|
| 54 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.9,
|
| 55 |
+
"blimp/accuracy/sentential_negation_npi_scope": 0.467,
|
| 56 |
+
"blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.745,
|
| 57 |
+
"blimp/accuracy/wh_questions_subject_gap_long_distance": 0.908,
|
| 58 |
+
"blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.843,
|
| 59 |
+
"blimp/accuracy/principle_A_case_2": 0.903,
|
| 60 |
+
"blimp/accuracy/distractor_agreement_relational_noun": 0.731,
|
| 61 |
+
"blimp/accuracy/sentential_negation_npi_licensor_present": 0.995,
|
| 62 |
+
"blimp/accuracy/superlative_quantifiers_1": 0.607,
|
| 63 |
+
"blimp/accuracy/wh_island": 0.709,
|
| 64 |
+
"blimp/accuracy/principle_A_domain_1": 0.982,
|
| 65 |
+
"blimp/accuracy/complex_NP_island": 0.494,
|
| 66 |
+
"blimp/accuracy/determiner_noun_agreement_irregular_2": 0.922,
|
| 67 |
+
"blimp/accuracy/irregular_past_participle_verbs": 0.782,
|
| 68 |
+
"blimp/accuracy/drop_argument": 0.73,
|
| 69 |
+
"blimp/accuracy/wh_questions_object_gap": 0.725,
|
| 70 |
+
"blimp/accuracy/animate_subject_passive": 0.728,
|
| 71 |
+
"blimp/accuracy/existential_there_quantifiers_1": 0.957,
|
| 72 |
+
"blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.861,
|
| 73 |
+
"blimp/accuracy/npi_present_2": 0.649,
|
| 74 |
+
"blimp/accuracy/determiner_noun_agreement_irregular_1": 0.787,
|
| 75 |
+
"blimp/accuracy/anaphor_number_agreement": 0.969,
|
| 76 |
+
"blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.906,
|
| 77 |
+
"blimp/accuracy/existential_there_object_raising": 0.811,
|
| 78 |
+
"blimp/accuracy/matrix_question_npi_licensor_present": 0.071,
|
| 79 |
+
"blimp/accuracy/npi_present_1": 0.55,
|
| 80 |
+
"blimp/accuracy/wh_vs_that_no_gap": 0.947,
|
| 81 |
+
"blimp/accuracy/left_branch_island_echo_question": 0.516,
|
| 82 |
+
"blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.976,
|
| 83 |
+
"blimp/accuracy/causative": 0.621,
|
| 84 |
+
"blimp/accuracy/group_average": 0.7197313432835819,
|
| 85 |
+
"blimp/accuracy/seq_average": 0.7197313432835821,
|
| 86 |
+
"cbt/accuracy/NE": 0.6967147435897436,
|
| 87 |
+
"cbt/accuracy/V": 0.8544,
|
| 88 |
+
"cbt/accuracy/CN": 0.7352,
|
| 89 |
+
"cbt/accuracy/P": 0.8372,
|
| 90 |
+
"cbt/accuracy/group_average": 0.7808786858974359,
|
| 91 |
+
"cbt/accuracy/seq_average": 0.7809123649459784,
|
| 92 |
+
"hellaswag/accuracy/val": 0.2698665604461263,
|
| 93 |
+
"hellaswag/accuracy/group_average": 0.2698665604461263,
|
| 94 |
+
"hellaswag/accuracy/seq_average": 0.2698665604461263,
|
| 95 |
+
"piqa/accuracy/val": 0.5538628944504896,
|
| 96 |
+
"piqa/accuracy/group_average": 0.5538628944504896,
|
| 97 |
+
"piqa/accuracy/seq_average": 0.5538628944504896,
|
| 98 |
+
"ai2arc/accuracy/ARC-Easy": 0.30782241014799155,
|
| 99 |
+
"ai2arc/accuracy/ARC-Challenge": 0.1888412017167382,
|
| 100 |
+
"ai2arc/accuracy/group_average": 0.24833180593236487,
|
| 101 |
+
"ai2arc/accuracy/seq_average": 0.26855524079320114,
|
| 102 |
+
"race/accuracy/test/high": 0.2507146941109205,
|
| 103 |
+
"race/accuracy/test/middle": 0.32590529247910865,
|
| 104 |
+
"race/accuracy/group_average": 0.2883099932950146,
|
| 105 |
+
"race/accuracy/seq_average": 0.27259829752736114,
|
| 106 |
+
"siqa/accuracy/dev": 0.3633572159672467,
|
| 107 |
+
"siqa/accuracy/group_average": 0.3633572159672467,
|
| 108 |
+
"siqa/accuracy/seq_average": 0.3633572159672467,
|
| 109 |
+
"commonsenseqa/accuracy/dev_rand_split": 0.23095823095823095,
|
| 110 |
+
"commonsenseqa/accuracy/group_average": 0.23095823095823095,
|
| 111 |
+
"commonsenseqa/accuracy/seq_average": 0.23095823095823095
|
| 112 |
+
}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-100000.pth.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"val/loss": 2.6058492509145585,
|
| 3 |
+
"val/accuracy": 0.4792848617311508,
|
| 4 |
+
"val/perplexity": 13.542721589136015,
|
| 5 |
+
"val/time_since_best_loss": 0,
|
| 6 |
+
"val/time_since_best_accuracy": 0,
|
| 7 |
+
"lambada/loss": 2.479829965911297,
|
| 8 |
+
"lambada/accuracy/total": 0.2544642857142857,
|
| 9 |
+
"lambada/accuracy/openai_last_token": 0.7639751552795031,
|
| 10 |
+
"lambada/perplexity": 12.094706473652733,
|
| 11 |
+
"lambada/lm_loss": 3.1711393084027555,
|
| 12 |
+
"lambada/lm_perplexity": 23.83462388061275,
|
| 13 |
+
"lambada/time_since_best_loss": 0,
|
| 14 |
+
"lambada/time_since_best_accuracy": 0,
|
| 15 |
+
"mean_accuracy": 0.36687457372271826,
|
| 16 |
+
"mean_loss": 2.542839608412928,
|
| 17 |
+
"blimp/accuracy/passive_2": 0.896,
|
| 18 |
+
"blimp/accuracy/determiner_noun_agreement_2": 0.979,
|
| 19 |
+
"blimp/accuracy/ellipsis_n_bar_1": 0.812,
|
| 20 |
+
"blimp/accuracy/tough_vs_raising_2": 0.86,
|
| 21 |
+
"blimp/accuracy/tough_vs_raising_1": 0.625,
|
| 22 |
+
"blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.924,
|
| 23 |
+
"blimp/accuracy/principle_A_reconstruction": 0.338,
|
| 24 |
+
"blimp/accuracy/wh_vs_that_with_gap": 0.542,
|
| 25 |
+
"blimp/accuracy/principle_A_domain_2": 0.817,
|
| 26 |
+
"blimp/accuracy/determiner_noun_agreement_1": 0.989,
|
| 27 |
+
"blimp/accuracy/ellipsis_n_bar_2": 0.902,
|
| 28 |
+
"blimp/accuracy/principle_A_domain_3": 0.597,
|
| 29 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.905,
|
| 30 |
+
"blimp/accuracy/animate_subject_trans": 0.897,
|
| 31 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.89,
|
| 32 |
+
"blimp/accuracy/distractor_agreement_relative_clause": 0.673,
|
| 33 |
+
"blimp/accuracy/transitive": 0.856,
|
| 34 |
+
"blimp/accuracy/sentential_subject_island": 0.306,
|
| 35 |
+
"blimp/accuracy/adjunct_island": 0.884,
|
| 36 |
+
"blimp/accuracy/intransitive": 0.794,
|
| 37 |
+
"blimp/accuracy/existential_there_subject_raising": 0.863,
|
| 38 |
+
"blimp/accuracy/irregular_past_participle_adjectives": 0.905,
|
| 39 |
+
"blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.515,
|
| 40 |
+
"blimp/accuracy/principle_A_case_1": 1.0,
|
| 41 |
+
"blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.206,
|
| 42 |
+
"blimp/accuracy/only_npi_scope": 0.718,
|
| 43 |
+
"blimp/accuracy/superlative_quantifiers_2": 0.706,
|
| 44 |
+
"blimp/accuracy/passive_1": 0.886,
|
| 45 |
+
"blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.902,
|
| 46 |
+
"blimp/accuracy/inchoative": 0.631,
|
| 47 |
+
"blimp/accuracy/anaphor_gender_agreement": 0.968,
|
| 48 |
+
"blimp/accuracy/principle_A_c_command": 0.678,
|
| 49 |
+
"blimp/accuracy/only_npi_licensor_present": 0.496,
|
| 50 |
+
"blimp/accuracy/expletive_it_object_raising": 0.776,
|
| 51 |
+
"blimp/accuracy/left_branch_island_simple_question": 0.568,
|
| 52 |
+
"blimp/accuracy/wh_questions_subject_gap": 0.888,
|
| 53 |
+
"blimp/accuracy/existential_there_quantifiers_2": 0.492,
|
| 54 |
+
"blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.931,
|
| 55 |
+
"blimp/accuracy/sentential_negation_npi_scope": 0.67,
|
| 56 |
+
"blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.837,
|
| 57 |
+
"blimp/accuracy/wh_questions_subject_gap_long_distance": 0.865,
|
| 58 |
+
"blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.901,
|
| 59 |
+
"blimp/accuracy/principle_A_case_2": 0.967,
|
| 60 |
+
"blimp/accuracy/distractor_agreement_relational_noun": 0.811,
|
| 61 |
+
"blimp/accuracy/sentential_negation_npi_licensor_present": 0.986,
|
| 62 |
+
"blimp/accuracy/superlative_quantifiers_1": 0.528,
|
| 63 |
+
"blimp/accuracy/wh_island": 0.841,
|
| 64 |
+
"blimp/accuracy/principle_A_domain_1": 0.985,
|
| 65 |
+
"blimp/accuracy/complex_NP_island": 0.598,
|
| 66 |
+
"blimp/accuracy/determiner_noun_agreement_irregular_2": 0.971,
|
| 67 |
+
"blimp/accuracy/irregular_past_participle_verbs": 0.868,
|
| 68 |
+
"blimp/accuracy/drop_argument": 0.777,
|
| 69 |
+
"blimp/accuracy/wh_questions_object_gap": 0.735,
|
| 70 |
+
"blimp/accuracy/animate_subject_passive": 0.801,
|
| 71 |
+
"blimp/accuracy/existential_there_quantifiers_1": 0.981,
|
| 72 |
+
"blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.886,
|
| 73 |
+
"blimp/accuracy/npi_present_2": 0.532,
|
| 74 |
+
"blimp/accuracy/determiner_noun_agreement_irregular_1": 0.916,
|
| 75 |
+
"blimp/accuracy/anaphor_number_agreement": 0.985,
|
| 76 |
+
"blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.953,
|
| 77 |
+
"blimp/accuracy/existential_there_object_raising": 0.891,
|
| 78 |
+
"blimp/accuracy/matrix_question_npi_licensor_present": 0.205,
|
| 79 |
+
"blimp/accuracy/npi_present_1": 0.574,
|
| 80 |
+
"blimp/accuracy/wh_vs_that_no_gap": 0.955,
|
| 81 |
+
"blimp/accuracy/left_branch_island_echo_question": 0.406,
|
| 82 |
+
"blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.985,
|
| 83 |
+
"blimp/accuracy/causative": 0.721,
|
| 84 |
+
"blimp/accuracy/group_average": 0.7723283582089551,
|
| 85 |
+
"blimp/accuracy/seq_average": 0.7723283582089552,
|
| 86 |
+
"cbt/accuracy/NE": 0.7624198717948718,
|
| 87 |
+
"cbt/accuracy/V": 0.9108,
|
| 88 |
+
"cbt/accuracy/CN": 0.826,
|
| 89 |
+
"cbt/accuracy/P": 0.894,
|
| 90 |
+
"cbt/accuracy/group_average": 0.848304967948718,
|
| 91 |
+
"cbt/accuracy/seq_average": 0.8483393357342938,
|
| 92 |
+
"hellaswag/accuracy/val": 0.2927703644692292,
|
| 93 |
+
"hellaswag/accuracy/group_average": 0.2927703644692292,
|
| 94 |
+
"hellaswag/accuracy/seq_average": 0.2927703644692292,
|
| 95 |
+
"piqa/accuracy/val": 0.5848748639825898,
|
| 96 |
+
"piqa/accuracy/group_average": 0.5848748639825898,
|
| 97 |
+
"piqa/accuracy/seq_average": 0.5848748639825898,
|
| 98 |
+
"ai2arc/accuracy/ARC-Easy": 0.33488372093023255,
|
| 99 |
+
"ai2arc/accuracy/ARC-Challenge": 0.2111587982832618,
|
| 100 |
+
"ai2arc/accuracy/group_average": 0.27302125960674717,
|
| 101 |
+
"ai2arc/accuracy/seq_average": 0.29405099150141645,
|
| 102 |
+
"race/accuracy/test/high": 0.2687249857061178,
|
| 103 |
+
"race/accuracy/test/middle": 0.33356545961002787,
|
| 104 |
+
"race/accuracy/group_average": 0.30114522265807286,
|
| 105 |
+
"race/accuracy/seq_average": 0.2875962707742197,
|
| 106 |
+
"siqa/accuracy/dev": 0.3561924257932446,
|
| 107 |
+
"siqa/accuracy/group_average": 0.3561924257932446,
|
| 108 |
+
"siqa/accuracy/seq_average": 0.3561924257932446,
|
| 109 |
+
"commonsenseqa/accuracy/dev_rand_split": 0.24488124488124488,
|
| 110 |
+
"commonsenseqa/accuracy/group_average": 0.24488124488124488,
|
| 111 |
+
"commonsenseqa/accuracy/seq_average": 0.24488124488124488
|
| 112 |
+
}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-20000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.886287386455233, "val/accuracy": 0.44113401382688494, "val/perplexity": 17.92663124867483, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.6340335822253493, "lambada/accuracy/total": 0.18866459627329193, "lambada/accuracy/openai_last_token": 0.734472049689441, "lambada/perplexity": 18.43311456970658, "lambada/lm_loss": 3.411311579141454, "lambada/lm_perplexity": 30.304965565605883, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.31489930505008845, "mean_loss": 2.7601604843402914, "blimp/accuracy/passive_2": 0.874, "blimp/accuracy/determiner_noun_agreement_2": 0.954, "blimp/accuracy/ellipsis_n_bar_1": 0.722, "blimp/accuracy/tough_vs_raising_2": 0.844, "blimp/accuracy/tough_vs_raising_1": 0.575, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.879, "blimp/accuracy/principle_A_reconstruction": 0.618, "blimp/accuracy/wh_vs_that_with_gap": 0.46, "blimp/accuracy/principle_A_domain_2": 0.799, "blimp/accuracy/determiner_noun_agreement_1": 0.969, "blimp/accuracy/ellipsis_n_bar_2": 0.875, "blimp/accuracy/principle_A_domain_3": 0.589, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.862, "blimp/accuracy/animate_subject_trans": 0.873, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.804, "blimp/accuracy/distractor_agreement_relative_clause": 0.527, "blimp/accuracy/transitive": 0.843, "blimp/accuracy/sentential_subject_island": 0.294, "blimp/accuracy/adjunct_island": 0.769, "blimp/accuracy/intransitive": 0.711, "blimp/accuracy/existential_there_subject_raising": 0.852, "blimp/accuracy/irregular_past_participle_adjectives": 0.882, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.308, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.108, "blimp/accuracy/only_npi_scope": 0.773, "blimp/accuracy/superlative_quantifiers_2": 0.798, "blimp/accuracy/passive_1": 0.907, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.859, "blimp/accuracy/inchoative": 0.54, "blimp/accuracy/anaphor_gender_agreement": 0.951, "blimp/accuracy/principle_A_c_command": 0.618, "blimp/accuracy/only_npi_licensor_present": 0.666, "blimp/accuracy/expletive_it_object_raising": 0.72, "blimp/accuracy/left_branch_island_simple_question": 0.458, "blimp/accuracy/wh_questions_subject_gap": 0.895, "blimp/accuracy/existential_there_quantifiers_2": 0.283, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.899, "blimp/accuracy/sentential_negation_npi_scope": 0.536, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.854, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.924, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.841, "blimp/accuracy/principle_A_case_2": 0.954, "blimp/accuracy/distractor_agreement_relational_noun": 0.737, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.985, "blimp/accuracy/superlative_quantifiers_1": 0.432, "blimp/accuracy/wh_island": 0.791, "blimp/accuracy/principle_A_domain_1": 0.997, "blimp/accuracy/complex_NP_island": 0.57, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.931, "blimp/accuracy/irregular_past_participle_verbs": 0.851, "blimp/accuracy/drop_argument": 0.718, "blimp/accuracy/wh_questions_object_gap": 0.78, "blimp/accuracy/animate_subject_passive": 0.744, "blimp/accuracy/existential_there_quantifiers_1": 0.983, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.845, "blimp/accuracy/npi_present_2": 0.599, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.864, "blimp/accuracy/anaphor_number_agreement": 0.949, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.922, "blimp/accuracy/existential_there_object_raising": 0.762, "blimp/accuracy/matrix_question_npi_licensor_present": 0.11, "blimp/accuracy/npi_present_1": 0.569, "blimp/accuracy/wh_vs_that_no_gap": 0.947, "blimp/accuracy/left_branch_island_echo_question": 0.385, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.991, "blimp/accuracy/causative": 0.648, "blimp/accuracy/group_average": 0.7399552238805966, "blimp/accuracy/seq_average": 0.739955223880597, "cbt/accuracy/NE": 0.7099358974358975, "cbt/accuracy/V": 0.88, "cbt/accuracy/CN": 0.7648, "cbt/accuracy/P": 0.8584, "cbt/accuracy/group_average": 0.8032839743589744, "cbt/accuracy/seq_average": 0.8033213285314126, "hellaswag/accuracy/val": 0.2731527584146584, "hellaswag/accuracy/group_average": 0.2731527584146584, "hellaswag/accuracy/seq_average": 0.2731527584146584, "piqa/accuracy/val": 0.5500544069640914, "piqa/accuracy/group_average": 0.5500544069640914, "piqa/accuracy/seq_average": 0.5500544069640914, "ai2arc/accuracy/ARC-Easy": 0.3086680761099366, "ai2arc/accuracy/ARC-Challenge": 0.192274678111588, "ai2arc/accuracy/group_average": 0.2504713771107623, "ai2arc/accuracy/seq_average": 0.27025495750708217, "race/accuracy/test/high": 0.25900514579759865, "race/accuracy/test/middle": 0.32520891364902504, "race/accuracy/group_average": 0.2921070297233118, "race/accuracy/seq_average": 0.2782732063234698, "siqa/accuracy/dev": 0.3577277379733879, "siqa/accuracy/group_average": 0.3577277379733879, "siqa/accuracy/seq_average": 0.3577277379733879, "commonsenseqa/accuracy/dev_rand_split": 0.23832923832923833, "commonsenseqa/accuracy/group_average": 0.23832923832923833, "commonsenseqa/accuracy/seq_average": 0.23832923832923833}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-30000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.806854005843874, "val/accuracy": 0.45171344091021826, "val/perplexity": 16.55774562350715, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.7897740713557844, "lambada/accuracy/total": 0.19934006211180125, "lambada/accuracy/openai_last_token": 0.7368012422360248, "lambada/perplexity": 17.015342251321886, "lambada/lm_loss": 3.364889675069981, "lambada/lm_perplexity": 28.9303053890623, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.32552675151100974, "mean_loss": 2.798314038599829, "blimp/accuracy/passive_2": 0.879, "blimp/accuracy/determiner_noun_agreement_2": 0.972, "blimp/accuracy/ellipsis_n_bar_1": 0.761, "blimp/accuracy/tough_vs_raising_2": 0.862, "blimp/accuracy/tough_vs_raising_1": 0.612, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.909, "blimp/accuracy/principle_A_reconstruction": 0.518, "blimp/accuracy/wh_vs_that_with_gap": 0.576, "blimp/accuracy/principle_A_domain_2": 0.793, "blimp/accuracy/determiner_noun_agreement_1": 0.98, "blimp/accuracy/ellipsis_n_bar_2": 0.878, "blimp/accuracy/principle_A_domain_3": 0.554, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.899, "blimp/accuracy/animate_subject_trans": 0.888, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.863, "blimp/accuracy/distractor_agreement_relative_clause": 0.629, "blimp/accuracy/transitive": 0.838, "blimp/accuracy/sentential_subject_island": 0.292, "blimp/accuracy/adjunct_island": 0.847, "blimp/accuracy/intransitive": 0.778, "blimp/accuracy/existential_there_subject_raising": 0.86, "blimp/accuracy/irregular_past_participle_adjectives": 0.962, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.356, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.197, "blimp/accuracy/only_npi_scope": 0.708, "blimp/accuracy/superlative_quantifiers_2": 0.605, "blimp/accuracy/passive_1": 0.88, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.869, "blimp/accuracy/inchoative": 0.601, "blimp/accuracy/anaphor_gender_agreement": 0.953, "blimp/accuracy/principle_A_c_command": 0.643, "blimp/accuracy/only_npi_licensor_present": 0.698, "blimp/accuracy/expletive_it_object_raising": 0.742, "blimp/accuracy/left_branch_island_simple_question": 0.436, "blimp/accuracy/wh_questions_subject_gap": 0.887, "blimp/accuracy/existential_there_quantifiers_2": 0.447, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.926, "blimp/accuracy/sentential_negation_npi_scope": 0.554, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.829, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.911, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.869, "blimp/accuracy/principle_A_case_2": 0.946, "blimp/accuracy/distractor_agreement_relational_noun": 0.803, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.989, "blimp/accuracy/superlative_quantifiers_1": 0.494, "blimp/accuracy/wh_island": 0.671, "blimp/accuracy/principle_A_domain_1": 0.968, "blimp/accuracy/complex_NP_island": 0.535, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.939, "blimp/accuracy/irregular_past_participle_verbs": 0.842, "blimp/accuracy/drop_argument": 0.798, "blimp/accuracy/wh_questions_object_gap": 0.7, "blimp/accuracy/animate_subject_passive": 0.797, "blimp/accuracy/existential_there_quantifiers_1": 0.975, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.86, "blimp/accuracy/npi_present_2": 0.549, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.9, "blimp/accuracy/anaphor_number_agreement": 0.969, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.945, "blimp/accuracy/existential_there_object_raising": 0.845, "blimp/accuracy/matrix_question_npi_licensor_present": 0.143, "blimp/accuracy/npi_present_1": 0.539, "blimp/accuracy/wh_vs_that_no_gap": 0.944, "blimp/accuracy/left_branch_island_echo_question": 0.433, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.989, "blimp/accuracy/causative": 0.705, "blimp/accuracy/group_average": 0.7543134328358208, "blimp/accuracy/seq_average": 0.7543134328358209, "cbt/accuracy/NE": 0.7379807692307693, "cbt/accuracy/V": 0.8916, "cbt/accuracy/CN": 0.7912, "cbt/accuracy/P": 0.8644, "cbt/accuracy/group_average": 0.8212951923076922, "cbt/accuracy/seq_average": 0.821328531412565, "hellaswag/accuracy/val": 0.2773351921927903, "hellaswag/accuracy/group_average": 0.2773351921927903, "hellaswag/accuracy/seq_average": 0.2773351921927903, "piqa/accuracy/val": 0.5647442872687704, "piqa/accuracy/group_average": 0.5647442872687704, "piqa/accuracy/seq_average": 0.5647442872687704, "ai2arc/accuracy/ARC-Easy": 0.31797040169133195, "ai2arc/accuracy/ARC-Challenge": 0.18798283261802576, "ai2arc/accuracy/group_average": 0.25297661715467884, "ai2arc/accuracy/seq_average": 0.27507082152974505, "race/accuracy/test/high": 0.25900514579759865, "race/accuracy/test/middle": 0.3398328690807799, "race/accuracy/group_average": 0.29941900743918926, "race/accuracy/seq_average": 0.28252938792055127, "siqa/accuracy/dev": 0.3541453428863869, "siqa/accuracy/group_average": 0.3541453428863869, "siqa/accuracy/seq_average": 0.3541453428863869, "commonsenseqa/accuracy/dev_rand_split": 0.2416052416052416, "commonsenseqa/accuracy/group_average": 0.2416052416052416, "commonsenseqa/accuracy/seq_average": 0.2416052416052416}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-40000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.752811492435516, "val/accuracy": 0.45919654482886907, "val/perplexity": 15.686672906893072, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.5765560932040956, "lambada/accuracy/total": 0.1983695652173913, "lambada/accuracy/openai_last_token": 0.7410714285714286, "lambada/perplexity": 16.176579592375163, "lambada/lm_loss": 3.291339110611978, "lambada/lm_perplexity": 26.87883329776551, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3287830550231302, "mean_loss": 2.6646837928198055, "blimp/accuracy/passive_2": 0.869, "blimp/accuracy/determiner_noun_agreement_2": 0.977, "blimp/accuracy/ellipsis_n_bar_1": 0.806, "blimp/accuracy/tough_vs_raising_2": 0.834, "blimp/accuracy/tough_vs_raising_1": 0.581, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.897, "blimp/accuracy/principle_A_reconstruction": 0.402, "blimp/accuracy/wh_vs_that_with_gap": 0.474, "blimp/accuracy/principle_A_domain_2": 0.79, "blimp/accuracy/determiner_noun_agreement_1": 0.986, "blimp/accuracy/ellipsis_n_bar_2": 0.892, "blimp/accuracy/principle_A_domain_3": 0.585, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.916, "blimp/accuracy/animate_subject_trans": 0.901, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.887, "blimp/accuracy/distractor_agreement_relative_clause": 0.689, "blimp/accuracy/transitive": 0.849, "blimp/accuracy/sentential_subject_island": 0.311, "blimp/accuracy/adjunct_island": 0.861, "blimp/accuracy/intransitive": 0.749, "blimp/accuracy/existential_there_subject_raising": 0.872, "blimp/accuracy/irregular_past_participle_adjectives": 0.877, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.408, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.164, "blimp/accuracy/only_npi_scope": 0.58, "blimp/accuracy/superlative_quantifiers_2": 0.706, "blimp/accuracy/passive_1": 0.893, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.883, "blimp/accuracy/inchoative": 0.594, "blimp/accuracy/anaphor_gender_agreement": 0.96, "blimp/accuracy/principle_A_c_command": 0.645, "blimp/accuracy/only_npi_licensor_present": 0.544, "blimp/accuracy/expletive_it_object_raising": 0.756, "blimp/accuracy/left_branch_island_simple_question": 0.484, "blimp/accuracy/wh_questions_subject_gap": 0.911, "blimp/accuracy/existential_there_quantifiers_2": 0.392, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.939, "blimp/accuracy/sentential_negation_npi_scope": 0.606, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.814, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.92, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.873, "blimp/accuracy/principle_A_case_2": 0.962, "blimp/accuracy/distractor_agreement_relational_noun": 0.811, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.998, "blimp/accuracy/superlative_quantifiers_1": 0.643, "blimp/accuracy/wh_island": 0.791, "blimp/accuracy/principle_A_domain_1": 0.989, "blimp/accuracy/complex_NP_island": 0.547, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.953, "blimp/accuracy/irregular_past_participle_verbs": 0.848, "blimp/accuracy/drop_argument": 0.777, "blimp/accuracy/wh_questions_object_gap": 0.734, "blimp/accuracy/animate_subject_passive": 0.785, "blimp/accuracy/existential_there_quantifiers_1": 0.983, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.86, "blimp/accuracy/npi_present_2": 0.455, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.916, "blimp/accuracy/anaphor_number_agreement": 0.968, "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": 0.141, "blimp/accuracy/npi_present_1": 0.416, "blimp/accuracy/wh_vs_that_no_gap": 0.969, "blimp/accuracy/left_branch_island_echo_question": 0.373, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.988, "blimp/accuracy/causative": 0.666, "blimp/accuracy/group_average": 0.7533432835820894, "blimp/accuracy/seq_average": 0.7533432835820896, "cbt/accuracy/NE": 0.7435897435897436, "cbt/accuracy/V": 0.8952, "cbt/accuracy/CN": 0.7944, "cbt/accuracy/P": 0.8724, "cbt/accuracy/group_average": 0.8263974358974359, "cbt/accuracy/seq_average": 0.8264305722288916, "hellaswag/accuracy/val": 0.28231428002389963, "hellaswag/accuracy/group_average": 0.28231428002389963, "hellaswag/accuracy/seq_average": 0.28231428002389963, "piqa/accuracy/val": 0.5756256800870512, "piqa/accuracy/group_average": 0.5756256800870512, "piqa/accuracy/seq_average": 0.5756256800870512, "ai2arc/accuracy/ARC-Easy": 0.3230443974630021, "ai2arc/accuracy/ARC-Challenge": 0.19742489270386265, "ai2arc/accuracy/group_average": 0.2602346450834324, "ai2arc/accuracy/seq_average": 0.28158640226628895, "race/accuracy/test/high": 0.26615208690680386, "race/accuracy/test/middle": 0.3307799442896936, "race/accuracy/group_average": 0.2984660155982487, "race/accuracy/seq_average": 0.2849614916903121, "siqa/accuracy/dev": 0.36284544524053225, "siqa/accuracy/group_average": 0.36284544524053225, "siqa/accuracy/seq_average": 0.36284544524053225, "commonsenseqa/accuracy/dev_rand_split": 0.24488124488124488, "commonsenseqa/accuracy/group_average": 0.24488124488124488, "commonsenseqa/accuracy/seq_average": 0.24488124488124488}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-50000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.709512135339162, "val/accuracy": 0.46539500403025796, "val/perplexity": 15.021945050756285, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.57704778635724, "lambada/accuracy/total": 0.22243788819875776, "lambada/accuracy/openai_last_token": 0.749611801242236, "lambada/perplexity": 14.467359368821795, "lambada/lm_loss": 3.2781914715298615, "lambada/lm_perplexity": 26.527753093831077, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3439164461145079, "mean_loss": 2.6432799608482007, "blimp/accuracy/passive_2": 0.883, "blimp/accuracy/determiner_noun_agreement_2": 0.971, "blimp/accuracy/ellipsis_n_bar_1": 0.807, "blimp/accuracy/tough_vs_raising_2": 0.85, "blimp/accuracy/tough_vs_raising_1": 0.572, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.931, "blimp/accuracy/principle_A_reconstruction": 0.527, "blimp/accuracy/wh_vs_that_with_gap": 0.486, "blimp/accuracy/principle_A_domain_2": 0.817, "blimp/accuracy/determiner_noun_agreement_1": 0.98, "blimp/accuracy/ellipsis_n_bar_2": 0.894, "blimp/accuracy/principle_A_domain_3": 0.589, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.884, "blimp/accuracy/animate_subject_trans": 0.896, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.848, "blimp/accuracy/distractor_agreement_relative_clause": 0.607, "blimp/accuracy/transitive": 0.845, "blimp/accuracy/sentential_subject_island": 0.295, "blimp/accuracy/adjunct_island": 0.847, "blimp/accuracy/intransitive": 0.755, "blimp/accuracy/existential_there_subject_raising": 0.86, "blimp/accuracy/irregular_past_participle_adjectives": 0.867, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.508, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.122, "blimp/accuracy/only_npi_scope": 0.7, "blimp/accuracy/superlative_quantifiers_2": 0.682, "blimp/accuracy/passive_1": 0.871, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.892, "blimp/accuracy/inchoative": 0.612, "blimp/accuracy/anaphor_gender_agreement": 0.961, "blimp/accuracy/principle_A_c_command": 0.658, "blimp/accuracy/only_npi_licensor_present": 0.479, "blimp/accuracy/expletive_it_object_raising": 0.769, "blimp/accuracy/left_branch_island_simple_question": 0.537, "blimp/accuracy/wh_questions_subject_gap": 0.906, "blimp/accuracy/existential_there_quantifiers_2": 0.49, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.902, "blimp/accuracy/sentential_negation_npi_scope": 0.548, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.849, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.912, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.879, "blimp/accuracy/principle_A_case_2": 0.962, "blimp/accuracy/distractor_agreement_relational_noun": 0.825, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.993, "blimp/accuracy/superlative_quantifiers_1": 0.614, "blimp/accuracy/wh_island": 0.833, "blimp/accuracy/principle_A_domain_1": 0.986, "blimp/accuracy/complex_NP_island": 0.576, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.951, "blimp/accuracy/irregular_past_participle_verbs": 0.843, "blimp/accuracy/drop_argument": 0.747, "blimp/accuracy/wh_questions_object_gap": 0.782, "blimp/accuracy/animate_subject_passive": 0.792, "blimp/accuracy/existential_there_quantifiers_1": 0.984, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.891, "blimp/accuracy/npi_present_2": 0.537, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.899, "blimp/accuracy/anaphor_number_agreement": 0.972, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.933, "blimp/accuracy/existential_there_object_raising": 0.836, "blimp/accuracy/matrix_question_npi_licensor_present": 0.144, "blimp/accuracy/npi_present_1": 0.53, "blimp/accuracy/wh_vs_that_no_gap": 0.974, "blimp/accuracy/left_branch_island_echo_question": 0.378, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.99, "blimp/accuracy/causative": 0.701, "blimp/accuracy/group_average": 0.7606119402985073, "blimp/accuracy/seq_average": 0.7606119402985074, "cbt/accuracy/NE": 0.7443910256410257, "cbt/accuracy/V": 0.9008, "cbt/accuracy/CN": 0.7936, "cbt/accuracy/P": 0.8728, "cbt/accuracy/group_average": 0.8278977564102565, "cbt/accuracy/seq_average": 0.8279311724689876, "hellaswag/accuracy/val": 0.2822146982672774, "hellaswag/accuracy/group_average": 0.2822146982672774, "hellaswag/accuracy/seq_average": 0.2822146982672774, "piqa/accuracy/val": 0.5696409140369967, "piqa/accuracy/group_average": 0.5696409140369967, "piqa/accuracy/seq_average": 0.5696409140369967, "ai2arc/accuracy/ARC-Easy": 0.32558139534883723, "ai2arc/accuracy/ARC-Challenge": 0.20686695278969958, "ai2arc/accuracy/group_average": 0.2662241740692684, "ai2arc/accuracy/seq_average": 0.2864022662889518, "race/accuracy/test/high": 0.2644368210405946, "race/accuracy/test/middle": 0.3279944289693593, "race/accuracy/group_average": 0.296215625004977, "race/accuracy/seq_average": 0.28293473854884477, "siqa/accuracy/dev": 0.36438075742067555, "siqa/accuracy/group_average": 0.36438075742067555, "siqa/accuracy/seq_average": 0.36438075742067555, "commonsenseqa/accuracy/dev_rand_split": 0.24406224406224405, "commonsenseqa/accuracy/group_average": 0.24406224406224405, "commonsenseqa/accuracy/seq_average": 0.24406224406224405}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-60000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.675106714642237, "val/accuracy": 0.4702807229662698, "val/perplexity": 14.51389860244843, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.464170278229328, "lambada/accuracy/total": 0.21991459627329193, "lambada/accuracy/openai_last_token": 0.7544642857142857, "lambada/perplexity": 14.145908030602392, "lambada/lm_loss": 3.2310163282153574, "lambada/lm_perplexity": 25.305362460011295, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3450976596197809, "mean_loss": 2.5696384964357826, "blimp/accuracy/passive_2": 0.886, "blimp/accuracy/determiner_noun_agreement_2": 0.984, "blimp/accuracy/ellipsis_n_bar_1": 0.813, "blimp/accuracy/tough_vs_raising_2": 0.856, "blimp/accuracy/tough_vs_raising_1": 0.599, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.908, "blimp/accuracy/principle_A_reconstruction": 0.398, "blimp/accuracy/wh_vs_that_with_gap": 0.479, "blimp/accuracy/principle_A_domain_2": 0.819, "blimp/accuracy/determiner_noun_agreement_1": 0.991, "blimp/accuracy/ellipsis_n_bar_2": 0.901, "blimp/accuracy/principle_A_domain_3": 0.582, "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": 0.886, "blimp/accuracy/distractor_agreement_relative_clause": 0.685, "blimp/accuracy/transitive": 0.843, "blimp/accuracy/sentential_subject_island": 0.296, "blimp/accuracy/adjunct_island": 0.866, "blimp/accuracy/intransitive": 0.785, "blimp/accuracy/existential_there_subject_raising": 0.842, "blimp/accuracy/irregular_past_participle_adjectives": 0.92, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.441, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.183, "blimp/accuracy/only_npi_scope": 0.76, "blimp/accuracy/superlative_quantifiers_2": 0.686, "blimp/accuracy/passive_1": 0.89, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.881, "blimp/accuracy/inchoative": 0.639, "blimp/accuracy/anaphor_gender_agreement": 0.967, "blimp/accuracy/principle_A_c_command": 0.645, "blimp/accuracy/only_npi_licensor_present": 0.475, "blimp/accuracy/expletive_it_object_raising": 0.745, "blimp/accuracy/left_branch_island_simple_question": 0.475, "blimp/accuracy/wh_questions_subject_gap": 0.909, "blimp/accuracy/existential_there_quantifiers_2": 0.418, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.93, "blimp/accuracy/sentential_negation_npi_scope": 0.698, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.847, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.893, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.889, "blimp/accuracy/principle_A_case_2": 0.973, "blimp/accuracy/distractor_agreement_relational_noun": 0.767, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.995, "blimp/accuracy/superlative_quantifiers_1": 0.529, "blimp/accuracy/wh_island": 0.819, "blimp/accuracy/principle_A_domain_1": 0.986, "blimp/accuracy/complex_NP_island": 0.617, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.962, "blimp/accuracy/irregular_past_participle_verbs": 0.841, "blimp/accuracy/drop_argument": 0.766, "blimp/accuracy/wh_questions_object_gap": 0.79, "blimp/accuracy/animate_subject_passive": 0.82, "blimp/accuracy/existential_there_quantifiers_1": 0.967, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.86, "blimp/accuracy/npi_present_2": 0.523, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.909, "blimp/accuracy/anaphor_number_agreement": 0.982, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.954, "blimp/accuracy/existential_there_object_raising": 0.844, "blimp/accuracy/matrix_question_npi_licensor_present": 0.168, "blimp/accuracy/npi_present_1": 0.489, "blimp/accuracy/wh_vs_that_no_gap": 0.97, "blimp/accuracy/left_branch_island_echo_question": 0.416, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.98, "blimp/accuracy/causative": 0.697, "blimp/accuracy/group_average": 0.7635671641791044, "blimp/accuracy/seq_average": 0.7635671641791045, "cbt/accuracy/NE": 0.7483974358974359, "cbt/accuracy/V": 0.9, "cbt/accuracy/CN": 0.8156, "cbt/accuracy/P": 0.8844, "cbt/accuracy/group_average": 0.8370993589743589, "cbt/accuracy/seq_average": 0.8371348539415766, "hellaswag/accuracy/val": 0.28579964150567616, "hellaswag/accuracy/group_average": 0.28579964150567616, "hellaswag/accuracy/seq_average": 0.28579964150567616, "piqa/accuracy/val": 0.5772578890097932, "piqa/accuracy/group_average": 0.5772578890097932, "piqa/accuracy/seq_average": 0.5772578890097932, "ai2arc/accuracy/ARC-Easy": 0.3285412262156448, "ai2arc/accuracy/ARC-Challenge": 0.2111587982832618, "ai2arc/accuracy/group_average": 0.2698500122494533, "ai2arc/accuracy/seq_average": 0.2898016997167139, "race/accuracy/test/high": 0.26815323041738137, "race/accuracy/test/middle": 0.33008356545961004, "race/accuracy/group_average": 0.2991183979384957, "race/accuracy/seq_average": 0.28617754357519254, "siqa/accuracy/dev": 0.3602865916069601, "siqa/accuracy/group_average": 0.3602865916069601, "siqa/accuracy/seq_average": 0.3602865916069601, "commonsenseqa/accuracy/dev_rand_split": 0.24242424242424243, "commonsenseqa/accuracy/group_average": 0.24242424242424243, "commonsenseqa/accuracy/seq_average": 0.24242424242424243}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-70000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.6470811631944446, "val/accuracy": 0.47430613684275796, "val/perplexity": 14.11278555124352, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.4958698912436916, "lambada/accuracy/total": 0.23563664596273293, "lambada/accuracy/openai_last_token": 0.7556288819875776, "lambada/perplexity": 13.064173073689936, "lambada/lm_loss": 3.2101778440805244, "lambada/lm_perplexity": 24.78349343027965, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3549713914027455, "mean_loss": 2.571475527219068, "blimp/accuracy/passive_2": 0.895, "blimp/accuracy/determiner_noun_agreement_2": 0.98, "blimp/accuracy/ellipsis_n_bar_1": 0.815, "blimp/accuracy/tough_vs_raising_2": 0.837, "blimp/accuracy/tough_vs_raising_1": 0.605, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.911, "blimp/accuracy/principle_A_reconstruction": 0.345, "blimp/accuracy/wh_vs_that_with_gap": 0.487, "blimp/accuracy/principle_A_domain_2": 0.814, "blimp/accuracy/determiner_noun_agreement_1": 0.991, "blimp/accuracy/ellipsis_n_bar_2": 0.892, "blimp/accuracy/principle_A_domain_3": 0.617, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.901, "blimp/accuracy/animate_subject_trans": 0.904, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.894, "blimp/accuracy/distractor_agreement_relative_clause": 0.666, "blimp/accuracy/transitive": 0.852, "blimp/accuracy/sentential_subject_island": 0.286, "blimp/accuracy/adjunct_island": 0.835, "blimp/accuracy/intransitive": 0.762, "blimp/accuracy/existential_there_subject_raising": 0.872, "blimp/accuracy/irregular_past_participle_adjectives": 0.84, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.369, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.188, "blimp/accuracy/only_npi_scope": 0.742, "blimp/accuracy/superlative_quantifiers_2": 0.652, "blimp/accuracy/passive_1": 0.892, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.881, "blimp/accuracy/inchoative": 0.617, "blimp/accuracy/anaphor_gender_agreement": 0.961, "blimp/accuracy/principle_A_c_command": 0.63, "blimp/accuracy/only_npi_licensor_present": 0.384, "blimp/accuracy/expletive_it_object_raising": 0.765, "blimp/accuracy/left_branch_island_simple_question": 0.469, "blimp/accuracy/wh_questions_subject_gap": 0.906, "blimp/accuracy/existential_there_quantifiers_2": 0.446, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.935, "blimp/accuracy/sentential_negation_npi_scope": 0.668, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.871, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.88, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.883, "blimp/accuracy/principle_A_case_2": 0.96, "blimp/accuracy/distractor_agreement_relational_noun": 0.841, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.995, "blimp/accuracy/superlative_quantifiers_1": 0.55, "blimp/accuracy/wh_island": 0.785, "blimp/accuracy/principle_A_domain_1": 0.98, "blimp/accuracy/complex_NP_island": 0.602, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.964, "blimp/accuracy/irregular_past_participle_verbs": 0.856, "blimp/accuracy/drop_argument": 0.759, "blimp/accuracy/wh_questions_object_gap": 0.749, "blimp/accuracy/animate_subject_passive": 0.806, "blimp/accuracy/existential_there_quantifiers_1": 0.967, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.869, "blimp/accuracy/npi_present_2": 0.498, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.913, "blimp/accuracy/anaphor_number_agreement": 0.973, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.962, "blimp/accuracy/existential_there_object_raising": 0.878, "blimp/accuracy/matrix_question_npi_licensor_present": 0.188, "blimp/accuracy/npi_present_1": 0.517, "blimp/accuracy/wh_vs_that_no_gap": 0.972, "blimp/accuracy/left_branch_island_echo_question": 0.392, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.981, "blimp/accuracy/causative": 0.692, "blimp/accuracy/group_average": 0.7580447761194028, "blimp/accuracy/seq_average": 0.758044776119403, "cbt/accuracy/NE": 0.7540064102564102, "cbt/accuracy/V": 0.9088, "cbt/accuracy/CN": 0.8156, "cbt/accuracy/P": 0.8812, "cbt/accuracy/group_average": 0.8399016025641026, "cbt/accuracy/seq_average": 0.8399359743897559, "hellaswag/accuracy/val": 0.28868751244771956, "hellaswag/accuracy/group_average": 0.28868751244771956, "hellaswag/accuracy/seq_average": 0.28868751244771956, "piqa/accuracy/val": 0.5783460282916213, "piqa/accuracy/group_average": 0.5783460282916213, "piqa/accuracy/seq_average": 0.5783460282916213, "ai2arc/accuracy/ARC-Easy": 0.32727272727272727, "ai2arc/accuracy/ARC-Challenge": 0.20515021459227467, "ai2arc/accuracy/group_average": 0.26621147093250097, "ai2arc/accuracy/seq_average": 0.2869688385269122, "race/accuracy/test/high": 0.27044025157232704, "race/accuracy/test/middle": 0.33147632311977715, "race/accuracy/group_average": 0.3009582873460521, "race/accuracy/seq_average": 0.2882042967166599, "siqa/accuracy/dev": 0.3572159672466735, "siqa/accuracy/group_average": 0.3572159672466735, "siqa/accuracy/seq_average": 0.3572159672466735, "commonsenseqa/accuracy/dev_rand_split": 0.24815724815724816, "commonsenseqa/accuracy/group_average": 0.24815724815724816, "commonsenseqa/accuracy/seq_average": 0.24815724815724816}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-80000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.6250242203000993, "val/accuracy": 0.47683570498511907, "val/perplexity": 13.804908541045696, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.496127869031444, "lambada/accuracy/total": 0.23990683229813664, "lambada/accuracy/openai_last_token": 0.7573757763975155, "lambada/perplexity": 12.694914993003175, "lambada/lm_loss": 3.1895224316532294, "lambada/lm_perplexity": 24.27683082826339, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3583712686416278, "mean_loss": 2.5605760446657717, "blimp/accuracy/passive_2": 0.889, "blimp/accuracy/determiner_noun_agreement_2": 0.984, "blimp/accuracy/ellipsis_n_bar_1": 0.819, "blimp/accuracy/tough_vs_raising_2": 0.862, "blimp/accuracy/tough_vs_raising_1": 0.618, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.917, "blimp/accuracy/principle_A_reconstruction": 0.354, "blimp/accuracy/wh_vs_that_with_gap": 0.492, "blimp/accuracy/principle_A_domain_2": 0.832, "blimp/accuracy/determiner_noun_agreement_1": 0.989, "blimp/accuracy/ellipsis_n_bar_2": 0.895, "blimp/accuracy/principle_A_domain_3": 0.588, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.906, "blimp/accuracy/animate_subject_trans": 0.907, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.891, "blimp/accuracy/distractor_agreement_relative_clause": 0.684, "blimp/accuracy/transitive": 0.848, "blimp/accuracy/sentential_subject_island": 0.299, "blimp/accuracy/adjunct_island": 0.86, "blimp/accuracy/intransitive": 0.789, "blimp/accuracy/existential_there_subject_raising": 0.875, "blimp/accuracy/irregular_past_participle_adjectives": 0.896, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.39, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.176, "blimp/accuracy/only_npi_scope": 0.781, "blimp/accuracy/superlative_quantifiers_2": 0.779, "blimp/accuracy/passive_1": 0.89, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.887, "blimp/accuracy/inchoative": 0.628, "blimp/accuracy/anaphor_gender_agreement": 0.967, "blimp/accuracy/principle_A_c_command": 0.665, "blimp/accuracy/only_npi_licensor_present": 0.525, "blimp/accuracy/expletive_it_object_raising": 0.758, "blimp/accuracy/left_branch_island_simple_question": 0.443, "blimp/accuracy/wh_questions_subject_gap": 0.9, "blimp/accuracy/existential_there_quantifiers_2": 0.469, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.93, "blimp/accuracy/sentential_negation_npi_scope": 0.69, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.845, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.895, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.898, "blimp/accuracy/principle_A_case_2": 0.967, "blimp/accuracy/distractor_agreement_relational_noun": 0.809, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.994, "blimp/accuracy/superlative_quantifiers_1": 0.539, "blimp/accuracy/wh_island": 0.854, "blimp/accuracy/principle_A_domain_1": 0.982, "blimp/accuracy/complex_NP_island": 0.572, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.97, "blimp/accuracy/irregular_past_participle_verbs": 0.863, "blimp/accuracy/drop_argument": 0.774, "blimp/accuracy/wh_questions_object_gap": 0.753, "blimp/accuracy/animate_subject_passive": 0.805, "blimp/accuracy/existential_there_quantifiers_1": 0.977, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.887, "blimp/accuracy/npi_present_2": 0.54, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.91, "blimp/accuracy/anaphor_number_agreement": 0.979, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.954, "blimp/accuracy/existential_there_object_raising": 0.883, "blimp/accuracy/matrix_question_npi_licensor_present": 0.203, "blimp/accuracy/npi_present_1": 0.568, "blimp/accuracy/wh_vs_that_no_gap": 0.971, "blimp/accuracy/left_branch_island_echo_question": 0.333, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.983, "blimp/accuracy/causative": 0.716, "blimp/accuracy/group_average": 0.7685970149253728, "blimp/accuracy/seq_average": 0.7685970149253731, "cbt/accuracy/NE": 0.7540064102564102, "cbt/accuracy/V": 0.906, "cbt/accuracy/CN": 0.822, "cbt/accuracy/P": 0.886, "cbt/accuracy/group_average": 0.8420016025641026, "cbt/accuracy/seq_average": 0.8420368147258903, "hellaswag/accuracy/val": 0.2907787293367855, "hellaswag/accuracy/group_average": 0.2907787293367855, "hellaswag/accuracy/seq_average": 0.2907787293367855, "piqa/accuracy/val": 0.5810663764961915, "piqa/accuracy/group_average": 0.5810663764961915, "piqa/accuracy/seq_average": 0.5810663764961915, "ai2arc/accuracy/ARC-Easy": 0.3378435517970402, "ai2arc/accuracy/ARC-Challenge": 0.20429184549356222, "ai2arc/accuracy/group_average": 0.2710676986453012, "ai2arc/accuracy/seq_average": 0.29376770538243624, "race/accuracy/test/high": 0.27044025157232704, "race/accuracy/test/middle": 0.33913649025069637, "race/accuracy/group_average": 0.3047883709115117, "race/accuracy/seq_average": 0.290433725172274, "siqa/accuracy/dev": 0.36131013306038895, "siqa/accuracy/group_average": 0.36131013306038895, "siqa/accuracy/seq_average": 0.36131013306038895, "commonsenseqa/accuracy/dev_rand_split": 0.2538902538902539, "commonsenseqa/accuracy/group_average": 0.2538902538902539, "commonsenseqa/accuracy/seq_average": 0.2538902538902539}
|
Pretrain_language_model/save/slimpajama_moe_no_attmoe_154M_standard_lb_plus_plus/export/result-model-90000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 2.6128302680121527, "val/accuracy": 0.478790767609127, "val/perplexity": 13.637594328908518, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "lambada/loss": 2.502792453173525, "lambada/accuracy/total": 0.24437111801242237, "lambada/accuracy/openai_last_token": 0.7614518633540373, "lambada/perplexity": 12.350692714940648, "lambada/lm_loss": 3.166464301278935, "lambada/lm_perplexity": 23.72345689985998, "lambada/time_since_best_loss": 0, "lambada/time_since_best_accuracy": 0, "mean_accuracy": 0.3615809428107747, "mean_loss": 2.5578113605928388, "blimp/accuracy/passive_2": 0.897, "blimp/accuracy/determiner_noun_agreement_2": 0.985, "blimp/accuracy/ellipsis_n_bar_1": 0.803, "blimp/accuracy/tough_vs_raising_2": 0.859, "blimp/accuracy/tough_vs_raising_1": 0.613, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.93, "blimp/accuracy/principle_A_reconstruction": 0.37, "blimp/accuracy/wh_vs_that_with_gap": 0.519, "blimp/accuracy/principle_A_domain_2": 0.82, "blimp/accuracy/determiner_noun_agreement_1": 0.988, "blimp/accuracy/ellipsis_n_bar_2": 0.901, "blimp/accuracy/principle_A_domain_3": 0.589, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.905, "blimp/accuracy/animate_subject_trans": 0.897, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.887, "blimp/accuracy/distractor_agreement_relative_clause": 0.683, "blimp/accuracy/transitive": 0.856, "blimp/accuracy/sentential_subject_island": 0.305, "blimp/accuracy/adjunct_island": 0.869, "blimp/accuracy/intransitive": 0.785, "blimp/accuracy/existential_there_subject_raising": 0.862, "blimp/accuracy/irregular_past_participle_adjectives": 0.89, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.477, "blimp/accuracy/principle_A_case_1": 1.0, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.19, "blimp/accuracy/only_npi_scope": 0.733, "blimp/accuracy/superlative_quantifiers_2": 0.575, "blimp/accuracy/passive_1": 0.882, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.898, "blimp/accuracy/inchoative": 0.641, "blimp/accuracy/anaphor_gender_agreement": 0.964, "blimp/accuracy/principle_A_c_command": 0.677, "blimp/accuracy/only_npi_licensor_present": 0.397, "blimp/accuracy/expletive_it_object_raising": 0.767, "blimp/accuracy/left_branch_island_simple_question": 0.508, "blimp/accuracy/wh_questions_subject_gap": 0.907, "blimp/accuracy/existential_there_quantifiers_2": 0.448, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.928, "blimp/accuracy/sentential_negation_npi_scope": 0.644, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.847, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.883, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.902, "blimp/accuracy/principle_A_case_2": 0.968, "blimp/accuracy/distractor_agreement_relational_noun": 0.814, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.989, "blimp/accuracy/superlative_quantifiers_1": 0.628, "blimp/accuracy/wh_island": 0.837, "blimp/accuracy/principle_A_domain_1": 0.984, "blimp/accuracy/complex_NP_island": 0.596, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.963, "blimp/accuracy/irregular_past_participle_verbs": 0.887, "blimp/accuracy/drop_argument": 0.769, "blimp/accuracy/wh_questions_object_gap": 0.781, "blimp/accuracy/animate_subject_passive": 0.795, "blimp/accuracy/existential_there_quantifiers_1": 0.985, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.891, "blimp/accuracy/npi_present_2": 0.498, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.936, "blimp/accuracy/anaphor_number_agreement": 0.98, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.955, "blimp/accuracy/existential_there_object_raising": 0.876, "blimp/accuracy/matrix_question_npi_licensor_present": 0.213, "blimp/accuracy/npi_present_1": 0.535, "blimp/accuracy/wh_vs_that_no_gap": 0.964, "blimp/accuracy/left_branch_island_echo_question": 0.369, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.985, "blimp/accuracy/causative": 0.735, "blimp/accuracy/group_average": 0.767373134328358, "blimp/accuracy/seq_average": 0.7673731343283582, "cbt/accuracy/NE": 0.7576121794871795, "cbt/accuracy/V": 0.908, "cbt/accuracy/CN": 0.8284, "cbt/accuracy/P": 0.8904, "cbt/accuracy/group_average": 0.8461030448717949, "cbt/accuracy/seq_average": 0.8461384553821528, "hellaswag/accuracy/val": 0.28978291177056364, "hellaswag/accuracy/group_average": 0.28978291177056364, "hellaswag/accuracy/seq_average": 0.28978291177056364, "piqa/accuracy/val": 0.5848748639825898, "piqa/accuracy/group_average": 0.5848748639825898, "piqa/accuracy/seq_average": 0.5848748639825898, "ai2arc/accuracy/ARC-Easy": 0.3378435517970402, "ai2arc/accuracy/ARC-Challenge": 0.20085836909871244, "ai2arc/accuracy/group_average": 0.2693509604478763, "ai2arc/accuracy/seq_average": 0.2926345609065156, "race/accuracy/test/high": 0.2747284162378502, "race/accuracy/test/middle": 0.33774373259052926, "race/accuracy/group_average": 0.30623607441418976, "race/accuracy/seq_average": 0.2930685042561816, "siqa/accuracy/dev": 0.3577277379733879, "siqa/accuracy/group_average": 0.3577277379733879, "siqa/accuracy/seq_average": 0.3577277379733879, "commonsenseqa/accuracy/dev_rand_split": 0.24815724815724816, "commonsenseqa/accuracy/group_average": 0.24815724815724816, "commonsenseqa/accuracy/seq_average": 0.24815724815724816}
|