| arc_easy |
1 |
none |
0 |
acc |
↑ |
0.5223 |
± |
0.0102 |
|
|
none |
0 |
acc_norm |
↑ |
0.4600 |
± |
0.0102 |
| blimp |
2 |
none |
|
acc |
↑ |
0.7631 |
± |
0.0014 |
| - blimp_adjunct_island |
1 |
none |
0 |
acc |
↑ |
0.8420 |
± |
0.0115 |
| - blimp_anaphor_gender_agreement |
1 |
none |
0 |
acc |
↑ |
0.8430 |
± |
0.0115 |
| - blimp_anaphor_number_agreement |
1 |
none |
0 |
acc |
↑ |
0.9620 |
± |
0.0060 |
| - blimp_animate_subject_passive |
1 |
none |
0 |
acc |
↑ |
0.7820 |
± |
0.0131 |
| - blimp_animate_subject_trans |
1 |
none |
0 |
acc |
↑ |
0.8040 |
± |
0.0126 |
| - blimp_causative |
1 |
none |
0 |
acc |
↑ |
0.6980 |
± |
0.0145 |
| - blimp_complex_NP_island |
1 |
none |
0 |
acc |
↑ |
0.4940 |
± |
0.0158 |
| - blimp_coordinate_structure_constraint_complex_left_branch |
1 |
none |
0 |
acc |
↑ |
0.7420 |
± |
0.0138 |
| - blimp_coordinate_structure_constraint_object_extraction |
1 |
none |
0 |
acc |
↑ |
0.7520 |
± |
0.0137 |
| - blimp_determiner_noun_agreement_1 |
1 |
none |
0 |
acc |
↑ |
0.9790 |
± |
0.0045 |
| - blimp_determiner_noun_agreement_2 |
1 |
none |
0 |
acc |
↑ |
0.9680 |
± |
0.0056 |
| - blimp_determiner_noun_agreement_irregular_1 |
1 |
none |
0 |
acc |
↑ |
0.8990 |
± |
0.0095 |
| - blimp_determiner_noun_agreement_irregular_2 |
1 |
none |
0 |
acc |
↑ |
0.9650 |
± |
0.0058 |
| - blimp_determiner_noun_agreement_with_adj_2 |
1 |
none |
0 |
acc |
↑ |
0.9340 |
± |
0.0079 |
| - blimp_determiner_noun_agreement_with_adj_irregular_1 |
1 |
none |
0 |
acc |
↑ |
0.8740 |
± |
0.0105 |
| - blimp_determiner_noun_agreement_with_adj_irregular_2 |
1 |
none |
0 |
acc |
↑ |
0.9270 |
± |
0.0082 |
| - blimp_determiner_noun_agreement_with_adjective_1 |
1 |
none |
0 |
acc |
↑ |
0.9410 |
± |
0.0075 |
| - blimp_distractor_agreement_relational_noun |
1 |
none |
0 |
acc |
↑ |
0.8780 |
± |
0.0104 |
| - blimp_distractor_agreement_relative_clause |
1 |
none |
0 |
acc |
↑ |
0.7210 |
± |
0.0142 |
| - blimp_drop_argument |
1 |
none |
0 |
acc |
↑ |
0.7500 |
± |
0.0137 |
| - blimp_ellipsis_n_bar_1 |
1 |
none |
0 |
acc |
↑ |
0.8060 |
± |
0.0125 |
| - blimp_ellipsis_n_bar_2 |
1 |
none |
0 |
acc |
↑ |
0.8820 |
± |
0.0102 |
| - blimp_existential_there_object_raising |
1 |
none |
0 |
acc |
↑ |
0.8750 |
± |
0.0105 |
| - blimp_existential_there_quantifiers_1 |
1 |
none |
0 |
acc |
↑ |
0.9730 |
± |
0.0051 |
| - blimp_existential_there_quantifiers_2 |
1 |
none |
0 |
acc |
↑ |
0.2070 |
± |
0.0128 |
| - blimp_existential_there_subject_raising |
1 |
none |
0 |
acc |
↑ |
0.8810 |
± |
0.0102 |
| - blimp_expletive_it_object_raising |
1 |
none |
0 |
acc |
↑ |
0.7830 |
± |
0.0130 |
| - blimp_inchoative |
1 |
none |
0 |
acc |
↑ |
0.6330 |
± |
0.0152 |
| - blimp_intransitive |
1 |
none |
0 |
acc |
↑ |
0.7310 |
± |
0.0140 |
| - blimp_irregular_past_participle_adjectives |
1 |
none |
0 |
acc |
↑ |
0.8620 |
± |
0.0109 |
| - blimp_irregular_past_participle_verbs |
1 |
none |
0 |
acc |
↑ |
0.8930 |
± |
0.0098 |
| - blimp_irregular_plural_subject_verb_agreement_1 |
1 |
none |
0 |
acc |
↑ |
0.8990 |
± |
0.0095 |
| - blimp_irregular_plural_subject_verb_agreement_2 |
1 |
none |
0 |
acc |
↑ |
0.9030 |
± |
0.0094 |
| - blimp_left_branch_island_echo_question |
1 |
none |
0 |
acc |
↑ |
0.3810 |
± |
0.0154 |
| - blimp_left_branch_island_simple_question |
1 |
none |
0 |
acc |
↑ |
0.6470 |
± |
0.0151 |
| - blimp_matrix_question_npi_licensor_present |
1 |
none |
0 |
acc |
↑ |
0.1260 |
± |
0.0105 |
| - blimp_npi_present_1 |
1 |
none |
0 |
acc |
↑ |
0.5710 |
± |
0.0157 |
| - blimp_npi_present_2 |
1 |
none |
0 |
acc |
↑ |
0.6190 |
± |
0.0154 |
| - blimp_only_npi_licensor_present |
1 |
none |
0 |
acc |
↑ |
0.6250 |
± |
0.0153 |
| - blimp_only_npi_scope |
1 |
none |
0 |
acc |
↑ |
0.5360 |
± |
0.0158 |
| - blimp_passive_1 |
1 |
none |
0 |
acc |
↑ |
0.8770 |
± |
0.0104 |
| - blimp_passive_2 |
1 |
none |
0 |
acc |
↑ |
0.8840 |
± |
0.0101 |
| - blimp_principle_A_c_command |
1 |
none |
0 |
acc |
↑ |
0.5560 |
± |
0.0157 |
| - blimp_principle_A_case_1 |
1 |
none |
0 |
acc |
↑ |
1.0000 |
± |
0 |
| - blimp_principle_A_case_2 |
1 |
none |
0 |
acc |
↑ |
0.9650 |
± |
0.0058 |
| - blimp_principle_A_domain_1 |
1 |
none |
0 |
acc |
↑ |
0.9430 |
± |
0.0073 |
| - blimp_principle_A_domain_2 |
1 |
none |
0 |
acc |
↑ |
0.8040 |
± |
0.0126 |
| - blimp_principle_A_domain_3 |
1 |
none |
0 |
acc |
↑ |
0.5200 |
± |
0.0158 |
| - blimp_principle_A_reconstruction |
1 |
none |
0 |
acc |
↑ |
0.2920 |
± |
0.0144 |
| - blimp_regular_plural_subject_verb_agreement_1 |
1 |
none |
0 |
acc |
↑ |
0.8930 |
± |
0.0098 |
| - blimp_regular_plural_subject_verb_agreement_2 |
1 |
none |
0 |
acc |
↑ |
0.9110 |
± |
0.0090 |
| - blimp_sentential_negation_npi_licensor_present |
1 |
none |
0 |
acc |
↑ |
0.9930 |
± |
0.0026 |
| - blimp_sentential_negation_npi_scope |
1 |
none |
0 |
acc |
↑ |
0.7100 |
± |
0.0144 |
| - blimp_sentential_subject_island |
1 |
none |
0 |
acc |
↑ |
0.3310 |
± |
0.0149 |
| - blimp_superlative_quantifiers_1 |
1 |
none |
0 |
acc |
↑ |
0.7800 |
± |
0.0131 |
| - blimp_superlative_quantifiers_2 |
1 |
none |
0 |
acc |
↑ |
0.7450 |
± |
0.0138 |
| - blimp_tough_vs_raising_1 |
1 |
none |
0 |
acc |
↑ |
0.5390 |
± |
0.0158 |
| - blimp_tough_vs_raising_2 |
1 |
none |
0 |
acc |
↑ |
0.8780 |
± |
0.0104 |
| - blimp_transitive |
1 |
none |
0 |
acc |
↑ |
0.8430 |
± |
0.0115 |
| - blimp_wh_island |
1 |
none |
0 |
acc |
↑ |
0.7190 |
± |
0.0142 |
| - blimp_wh_questions_object_gap |
1 |
none |
0 |
acc |
↑ |
0.7590 |
± |
0.0135 |
| - blimp_wh_questions_subject_gap |
1 |
none |
0 |
acc |
↑ |
0.9280 |
± |
0.0082 |
| - blimp_wh_questions_subject_gap_long_distance |
1 |
none |
0 |
acc |
↑ |
0.8550 |
± |
0.0111 |
| - blimp_wh_vs_that_no_gap |
1 |
none |
0 |
acc |
↑ |
0.9490 |
± |
0.0070 |
| - blimp_wh_vs_that_no_gap_long_distance |
1 |
none |
0 |
acc |
↑ |
0.9490 |
± |
0.0070 |
| - blimp_wh_vs_that_with_gap |
1 |
none |
0 |
acc |
↑ |
0.5920 |
± |
0.0155 |
| - blimp_wh_vs_that_with_gap_long_distance |
1 |
none |
0 |
acc |
↑ |
0.3280 |
± |
0.0149 |
| hellaswag |
1 |
none |
0 |
acc |
↑ |
0.2914 |
± |
0.0045 |
|
|
none |
0 |
acc_norm |
↑ |
0.3178 |
± |
0.0046 |
| lambada_openai |
1 |
none |
0 |
acc |
↑ |
0.2591 |
± |
0.0061 |
|
|
none |
0 |
perplexity |
↓ |
95.5121 |
± |
4.1325 |
| lambada_standard |
1 |
none |
0 |
acc |
↑ |
0.1716 |
± |
0.0053 |
|
|
none |
0 |
perplexity |
↓ |
488.2170 |
± |
23.4634 |
| piqa |
1 |
none |
0 |
acc |
↑ |
0.6224 |
± |
0.0113 |
|
|
none |
0 |
acc_norm |
↑ |
0.6208 |
± |
0.0113 |
| sciq |
1 |
none |
0 |
acc |
↑ |
0.7720 |
± |
0.0133 |
|
|
none |
0 |
acc_norm |
↑ |
0.6810 |
± |
0.0147 |
| wikitext |
2 |
none |
0 |
bits_per_byte |
↓ |
1.0267 |
± |
N/A |
|
|
none |
0 |
byte_perplexity |
↓ |
2.0374 |
± |
N/A |
|
|
none |
0 |
word_perplexity |
↓ |
44.9548 |
± |
N/A |
| winogrande |
1 |
none |
0 |
acc |
↑ |
0.5099 |
± |
0.0140 |
