eval
Browse files
README.md
CHANGED
@@ -133,4 +133,53 @@ CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable
|
|
133 |
```
|
134 |
|
135 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
```
|
|
|
133 |
```
|
134 |
|
135 |
```
|
136 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
137 |
+
|-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
|
138 |
+
|leaderboard | N/A| | | | | | | |
|
139 |
+
| - leaderboard_bbh | N/A| | | | | | | |
|
140 |
+
| - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.5040|± |0.0317|
|
141 |
+
| - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5187|± |0.0366|
|
142 |
+
| - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.2000|± |0.0253|
|
143 |
+
| - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.3560|± |0.0303|
|
144 |
+
| - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.5320|± |0.0316|
|
145 |
+
| - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.0880|± |0.0180|
|
146 |
+
| - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5160|± |0.0317|
|
147 |
+
| - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.2000|± |0.0253|
|
148 |
+
| - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1160|± |0.0203|
|
149 |
+
| - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3400|± |0.0300|
|
150 |
+
| - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2760|± |0.0283|
|
151 |
+
| - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.4200|± |0.0313|
|
152 |
+
| - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0600|± |0.0151|
|
153 |
+
| - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.2055|± |0.0336|
|
154 |
+
| - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.1560|± |0.0230|
|
155 |
+
| - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2280|± |0.0266|
|
156 |
+
| - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.1120|± |0.0200|
|
157 |
+
| - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.5449|± |0.0374|
|
158 |
+
| - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
|
159 |
+
| - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2840|± |0.0286|
|
160 |
+
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.1720|± |0.0239|
|
161 |
+
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1400|± |0.0220|
|
162 |
+
| - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3320|± |0.0298|
|
163 |
+
| - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317|
|
164 |
+
| - leaderboard_gpqa | N/A| | | | | | | |
|
165 |
+
| - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2071|± |0.0289|
|
166 |
+
| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2637|± |0.0189|
|
167 |
+
| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2612|± |0.0208|
|
168 |
+
| - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.2314|± | N/A|
|
169 |
+
| | |none | 0|inst_level_strict_acc |↑ |0.2206|± | N/A|
|
170 |
+
| | |none | 0|prompt_level_loose_acc |↑ |0.1165|± |0.0138|
|
171 |
+
| | |none | 0|prompt_level_strict_acc|↑ |0.1109|± |0.0135|
|
172 |
+
| - leaderboard_math_hard | N/A| | | | | | | |
|
173 |
+
| - leaderboard_math_algebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
174 |
+
| - leaderboard_math_counting_and_prob_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
175 |
+
| - leaderboard_math_geometry_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
176 |
+
| - leaderboard_math_intermediate_algebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
177 |
+
| - leaderboard_math_num_theory_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
178 |
+
| - leaderboard_math_prealgebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
179 |
+
| - leaderboard_math_precalculus_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
180 |
+
| - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1096|± |0.0028|
|
181 |
+
| - leaderboard_musr | N/A| | | | | | | |
|
182 |
+
| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.4920|± |0.0317|
|
183 |
+
| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2227|± |0.0261|
|
184 |
+
| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.3960|± |0.0310|
|
185 |
```
|