mtasic85 commited on
Commit
ed5cf00
·
1 Parent(s): 4e1711e
Files changed (1) hide show
  1. README.md +49 -1
README.md CHANGED
@@ -165,5 +165,53 @@ CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable
165
  ```
166
 
167
  ```
168
- # ...
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
169
  ```
 
165
  ```
166
 
167
  ```
168
+ Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
169
+ |-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
170
+ |leaderboard | N/A| | | | | | | |
171
+ | - leaderboard_bbh | N/A| | | | | | | |
172
+ | - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.5640|± |0.0314|
173
+ | - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5187|± |0.0366|
174
+ | - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.2000|± |0.0253|
175
+ | - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.2960|± |0.0289|
176
+ | - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.4680|± |0.0316|
177
+ | - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.0880|± |0.0180|
178
+ | - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5160|± |0.0317|
179
+ | - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.1920|± |0.0250|
180
+ | - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1320|± |0.0215|
181
+ | - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3360|± |0.0299|
182
+ | - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2520|± |0.0275|
183
+ | - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.5520|± |0.0315|
184
+ | - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0760|± |0.0168|
185
+ | - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.1918|± |0.0327|
186
+ | - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.0680|± |0.0160|
187
+ | - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2080|± |0.0257|
188
+ | - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.1880|± |0.0248|
189
+ | - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.4607|± |0.0375|
190
+ | - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
191
+ | - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2720|± |0.0282|
192
+ | - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.2080|± |0.0257|
193
+ | - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1520|± |0.0228|
194
+ | - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3320|± |0.0298|
195
+ | - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317|
196
+ | - leaderboard_gpqa | N/A| | | | | | | |
197
+ | - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2020|± |0.0286|
198
+ | - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2656|± |0.0189|
199
+ | - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2567|± |0.0207|
200
+ | - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.2350|± | N/A|
201
+ | | |none | 0|inst_level_strict_acc |↑ |0.2242|± | N/A|
202
+ | | |none | 0|prompt_level_loose_acc |↑ |0.1109|± |0.0135|
203
+ | | |none | 0|prompt_level_strict_acc|↑ |0.1054|± |0.0132|
204
+ | - leaderboard_math_hard | N/A| | | | | | | |
205
+ | - leaderboard_math_algebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
206
+ | - leaderboard_math_counting_and_prob_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
207
+ | - leaderboard_math_geometry_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
208
+ | - leaderboard_math_intermediate_algebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
209
+ | - leaderboard_math_num_theory_hard | 2|none | 4|exact_match |↑ |0.0019|± |0.0019|
210
+ | - leaderboard_math_prealgebra_hard | 2|none | 4|exact_match |↑ |0.0011|± |0.0011|
211
+ | - leaderboard_math_precalculus_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
212
+ | - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1177|± |0.0029|
213
+ | - leaderboard_musr | N/A| | | | | | | |
214
+ | - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.4880|± |0.0317|
215
+ | - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2266|± |0.0262|
216
+ | - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.2560|± |0.0277|
217
  ```