Upload folder using huggingface_hub
#308
by
DavidNguyen
- opened
Pretrain_language_model/save_final/slimpajama_moe_no_attmoe_154M_deepseek_highlb_shared_only/tmp/result-model-100000.pth.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"val/loss": 5.0535772414434526, "val/accuracy": 0.22954353453621032, "val/perplexity": 156.58159398682704, "val/time_since_best_loss": 0, "val/time_since_best_accuracy": 0, "mean_accuracy": 0.22954353453621032, "mean_loss": 5.0535772414434526, "blimp/accuracy/passive_2": 0.573, "blimp/accuracy/determiner_noun_agreement_2": 0.738, "blimp/accuracy/ellipsis_n_bar_1": 0.393, "blimp/accuracy/tough_vs_raising_2": 0.658, "blimp/accuracy/tough_vs_raising_1": 0.401, "blimp/accuracy/irregular_plural_subject_verb_agreement_2": 0.71, "blimp/accuracy/principle_A_reconstruction": 0.486, "blimp/accuracy/wh_vs_that_with_gap": 0.068, "blimp/accuracy/principle_A_domain_2": 0.594, "blimp/accuracy/determiner_noun_agreement_1": 0.755, "blimp/accuracy/ellipsis_n_bar_2": 0.883, "blimp/accuracy/principle_A_domain_3": 0.478, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_2": 0.65, "blimp/accuracy/animate_subject_trans": 0.577, "blimp/accuracy/determiner_noun_agreement_with_adj_irregular_1": 0.6, "blimp/accuracy/distractor_agreement_relative_clause": 0.496, "blimp/accuracy/transitive": 0.615, "blimp/accuracy/sentential_subject_island": 0.384, "blimp/accuracy/adjunct_island": 0.407, "blimp/accuracy/intransitive": 0.508, "blimp/accuracy/existential_there_subject_raising": 0.644, "blimp/accuracy/irregular_past_participle_adjectives": 0.678, "blimp/accuracy/coordinate_structure_constraint_complex_left_branch": 0.524, "blimp/accuracy/principle_A_case_1": 0.996, "blimp/accuracy/wh_vs_that_with_gap_long_distance": 0.107, "blimp/accuracy/only_npi_scope": 0.716, "blimp/accuracy/superlative_quantifiers_2": 0.714, "blimp/accuracy/passive_1": 0.603, "blimp/accuracy/regular_plural_subject_verb_agreement_1": 0.602, "blimp/accuracy/inchoative": 0.387, "blimp/accuracy/anaphor_gender_agreement": 0.847, "blimp/accuracy/principle_A_c_command": 0.658, "blimp/accuracy/only_npi_licensor_present": 0.414, "blimp/accuracy/expletive_it_object_raising": 0.63, "blimp/accuracy/left_branch_island_simple_question": 0.429, "blimp/accuracy/wh_questions_subject_gap": 0.886, "blimp/accuracy/existential_there_quantifiers_2": 0.442, "blimp/accuracy/determiner_noun_agreement_with_adj_2": 0.685, "blimp/accuracy/sentential_negation_npi_scope": 0.556, "blimp/accuracy/coordinate_structure_constraint_object_extraction": 0.625, "blimp/accuracy/wh_questions_subject_gap_long_distance": 0.871, "blimp/accuracy/irregular_plural_subject_verb_agreement_1": 0.63, "blimp/accuracy/principle_A_case_2": 0.504, "blimp/accuracy/distractor_agreement_relational_noun": 0.471, "blimp/accuracy/sentential_negation_npi_licensor_present": 0.891, "blimp/accuracy/superlative_quantifiers_1": 0.433, "blimp/accuracy/wh_island": 0.391, "blimp/accuracy/principle_A_domain_1": 0.992, "blimp/accuracy/complex_NP_island": 0.511, "blimp/accuracy/determiner_noun_agreement_irregular_2": 0.701, "blimp/accuracy/irregular_past_participle_verbs": 0.658, "blimp/accuracy/drop_argument": 0.643, "blimp/accuracy/wh_questions_object_gap": 0.814, "blimp/accuracy/animate_subject_passive": 0.638, "blimp/accuracy/existential_there_quantifiers_1": 0.929, "blimp/accuracy/regular_plural_subject_verb_agreement_2": 0.612, "blimp/accuracy/npi_present_2": 0.693, "blimp/accuracy/determiner_noun_agreement_irregular_1": 0.628, "blimp/accuracy/anaphor_number_agreement": 0.908, "blimp/accuracy/determiner_noun_agreement_with_adjective_1": 0.657, "blimp/accuracy/existential_there_object_raising": 0.686, "blimp/accuracy/matrix_question_npi_licensor_present": 0.212, "blimp/accuracy/npi_present_1": 0.556, "blimp/accuracy/wh_vs_that_no_gap": 0.948, "blimp/accuracy/left_branch_island_echo_question": 0.54, "blimp/accuracy/wh_vs_that_no_gap_long_distance": 0.899, "blimp/accuracy/causative": 0.476, "blimp/accuracy/group_average": 0.6120746268656717, "blimp/accuracy/seq_average": 0.6120746268656716, "boolq/accuracy/dev": 0.5623853211009174, "boolq/accuracy/group_average": 0.5623853211009174, "boolq/accuracy/seq_average": 0.5623853211009174}
|