eval
Browse files
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 |↑ |0.4600|± |0.0316|
|
173 |
+
| - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5241|± |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 |↑ |0.3120|± |0.0294|
|
176 |
+
| - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.5360|± |0.0316|
|
177 |
+
| - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.0840|± |0.0176|
|
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 |↑ |0.1720|± |0.0239|
|
180 |
+
| - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1440|± |0.0222|
|
181 |
+
| - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3560|± |0.0303|
|
182 |
+
| - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2480|± |0.0274|
|
183 |
+
| - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.5800|± |0.0313|
|
184 |
+
| - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0840|± |0.0176|
|
185 |
+
| - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.1986|± |0.0331|
|
186 |
+
| - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.1720|± |0.0239|
|
187 |
+
| - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2840|± |0.0286|
|
188 |
+
| - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.1240|± |0.0209|
|
189 |
+
| - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.5056|± |0.0376|
|
190 |
+
| - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
|
191 |
+
| - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2840|± |0.0286|
|
192 |
+
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.2200|± |0.0263|
|
193 |
+
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1240|± |0.0209|
|
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 |↑ |0.1970|± |0.0283|
|
198 |
+
| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2564|± |0.0187|
|
199 |
+
| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2656|± |0.0209|
|
200 |
+
| - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.2422|± | N/A|
|
201 |
+
| | |none | 0|inst_level_strict_acc |↑ |0.2362|± | N/A|
|
202 |
+
| | |none | 0|prompt_level_loose_acc |↑ |0.1220|± |0.0141|
|
203 |
+
| | |none | 0|prompt_level_strict_acc|↑ |0.1146|± |0.0137|
|
204 |
+
| - leaderboard_math_hard | N/A| | | | | | | |
|
205 |
+
| - leaderboard_math_algebra_hard | 2|none | 4|exact_match |↑ |0.0008|± |0.0008|
|
206 |
+
| - leaderboard_math_counting_and_prob_hard | 2|none | 4|exact_match |↑ |0.0021|± |0.0021|
|
207 |
+
| - leaderboard_math_geometry_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
208 |
+
| - leaderboard_math_intermediate_algebra_hard | 2|none | 4|exact_match |↑ |0.0011|± |0.0011|
|
209 |
+
| - leaderboard_math_num_theory_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
210 |
+
| - leaderboard_math_prealgebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
211 |
+
| - leaderboard_math_precalculus_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
212 |
+
| - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1115|± |0.0029|
|
213 |
+
| - leaderboard_musr | N/A| | | | | | | |
|
214 |
+
| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.4840|± |0.0317|
|
215 |
+
| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2188|± |0.0259|
|
216 |
+
| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.3560|± |0.0303|
|
217 |
```
|