benchmarks
Browse files
README.md
CHANGED
@@ -154,6 +154,57 @@ litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_chal
|
|
154 |
litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-leaderboard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
155 |
```
|
156 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
```bash
|
158 |
litgpt evaluate --tasks 'bbh_zeroshot,bbh_fewshot,bbh_cot_fewshot,bbh_cot_zeroshot' --out_dir 'evaluate-bigbenchhard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
159 |
```
|
|
|
154 |
litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-leaderboard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
155 |
```
|
156 |
|
157 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
158 |
+
|-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
|
159 |
+
|leaderboard | N/A| | | | | | | |
|
160 |
+
| - leaderboard_bbh | N/A| | | | | | | |
|
161 |
+
| - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
|
162 |
+
| - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5027|± |0.0367|
|
163 |
+
| - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.1720|± |0.0239|
|
164 |
+
| - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.2960|± |0.0289|
|
165 |
+
| - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317|
|
166 |
+
| - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.0000|± | 0|
|
167 |
+
| - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5160|± |0.0317|
|
168 |
+
| - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.2000|± |0.0253|
|
169 |
+
| - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1480|± |0.0225|
|
170 |
+
| - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3160|± |0.0295|
|
171 |
+
| - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2360|± |0.0269|
|
172 |
+
| - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.4680|± |0.0316|
|
173 |
+
| - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0480|± |0.0135|
|
174 |
+
| - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.1918|± |0.0327|
|
175 |
+
| - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.1440|± |0.0222|
|
176 |
+
| - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2360|± |0.0269|
|
177 |
+
| - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.1360|± |0.0217|
|
178 |
+
| - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.5225|± |0.0375|
|
179 |
+
| - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4560|± |0.0316|
|
180 |
+
| - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2960|± |0.0289|
|
181 |
+
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.2120|± |0.0259|
|
182 |
+
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1840|± |0.0246|
|
183 |
+
| - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3160|± |0.0295|
|
184 |
+
| - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.5200|± |0.0317|
|
185 |
+
| - leaderboard_gpqa | N/A| | | | | | | |
|
186 |
+
| - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2172|± |0.0294|
|
187 |
+
| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2454|± |0.0184|
|
188 |
+
| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2478|± |0.0204|
|
189 |
+
| - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.1727|± | N/A|
|
190 |
+
| | |none | 0|inst_level_strict_acc |↑ |0.1559|± | N/A|
|
191 |
+
| | |none | 0|prompt_level_loose_acc |↑ |0.0832|± |0.0119|
|
192 |
+
| | |none | 0|prompt_level_strict_acc|↑ |0.0795|± |0.0116|
|
193 |
+
| - leaderboard_math_hard | N/A| | | | | | | |
|
194 |
+
| - leaderboard_math_algebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
195 |
+
| - leaderboard_math_counting_and_prob_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
196 |
+
| - leaderboard_math_geometry_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
197 |
+
| - leaderboard_math_intermediate_algebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
198 |
+
| - leaderboard_math_num_theory_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
199 |
+
| - leaderboard_math_prealgebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
200 |
+
| - leaderboard_math_precalculus_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
201 |
+
| - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1135|± |0.0029|
|
202 |
+
| - leaderboard_musr | N/A| | | | | | | |
|
203 |
+
| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5240|± |0.0316|
|
204 |
+
| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2734|± |0.0279|
|
205 |
+
| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.3000|± |0.0290|
|
206 |
+
|
207 |
+
|
208 |
```bash
|
209 |
litgpt evaluate --tasks 'bbh_zeroshot,bbh_fewshot,bbh_cot_fewshot,bbh_cot_zeroshot' --out_dir 'evaluate-bigbenchhard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
210 |
```
|