evaluate/pretrain-core-0/leaderboard
Browse files
README.md
CHANGED
|
@@ -80,6 +80,15 @@ Total number of tokens in the optimized dataset '../core-data-7-65537-131073-131
|
|
| 80 |
real 292m54.341s
|
| 81 |
user 2118m1.154s
|
| 82 |
sys 12m2.746s
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
```
|
| 84 |
|
| 85 |
```bash
|
|
@@ -137,7 +146,7 @@ mv wandb wandb-pretrain-core-0
|
|
| 137 |
Copy config:
|
| 138 |
|
| 139 |
```bash
|
| 140 |
-
cp ../config-0.json ../out/pretrain-core-0/final
|
| 141 |
```
|
| 142 |
|
| 143 |
Chat with model:
|
|
@@ -147,8 +156,57 @@ CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable
|
|
| 147 |
```
|
| 148 |
|
| 149 |
```bash
|
| 150 |
-
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True time litgpt evaluate --tasks 'leaderboard' --out_dir '../evaluate/pretrain-core-0/leaderboard/' --batch_size
|
| 151 |
```
|
| 152 |
|
| 153 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 154 |
```
|
|
|
|
| 80 |
real 292m54.341s
|
| 81 |
user 2118m1.154s
|
| 82 |
sys 12m2.746s
|
| 83 |
+
|
| 84 |
+
20G tangled-alpha-0.9-core/core-data-0-0-1073741824-1025-16000
|
| 85 |
+
2.4G tangled-alpha-0.9-core/core-data-1-1025-2049-2049-8000
|
| 86 |
+
1.8G tangled-alpha-0.9-core/core-data-2-2049-4097-4097-4000
|
| 87 |
+
1.8G tangled-alpha-0.9-core/core-data-3-4097-8193-8193-2000
|
| 88 |
+
2.3G tangled-alpha-0.9-core/core-data-4-8193-16385-16385-1000
|
| 89 |
+
1.6G tangled-alpha-0.9-core/core-data-5-16385-32769-32769-500
|
| 90 |
+
709M tangled-alpha-0.9-core/core-data-6-32769-65537-65537-250
|
| 91 |
+
321M tangled-alpha-0.9-core/core-data-7-65537-131073-131073-125
|
| 92 |
```
|
| 93 |
|
| 94 |
```bash
|
|
|
|
| 146 |
Copy config:
|
| 147 |
|
| 148 |
```bash
|
| 149 |
+
cp ../config-0.json ../out/pretrain-core-0/final/config.json
|
| 150 |
```
|
| 151 |
|
| 152 |
Chat with model:
|
|
|
|
| 156 |
```
|
| 157 |
|
| 158 |
```bash
|
| 159 |
+
CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True time litgpt evaluate --tasks 'leaderboard' --out_dir '../evaluate/pretrain-core-0/leaderboard/' --batch_size '4' --dtype 'bfloat16' '../out/pretrain-core-0/final'
|
| 160 |
```
|
| 161 |
|
| 162 |
```
|
| 163 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 164 |
+
|-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
|
| 165 |
+
|leaderboard | N/A| | | | | | | |
|
| 166 |
+
| - leaderboard_bbh | N/A| | | | | | | |
|
| 167 |
+
| - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
|
| 168 |
+
| - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5134|± |0.0366|
|
| 169 |
+
| - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.1960|± |0.0252|
|
| 170 |
+
| - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.3320|± |0.0298|
|
| 171 |
+
| - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.4680|± |0.0316|
|
| 172 |
+
| - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.2400|± |0.0271|
|
| 173 |
+
| - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5160|± |0.0317|
|
| 174 |
+
| - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.2040|± |0.0255|
|
| 175 |
+
| - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1320|± |0.0215|
|
| 176 |
+
| - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3440|± |0.0301|
|
| 177 |
+
| - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2680|± |0.0281|
|
| 178 |
+
| - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.5720|± |0.0314|
|
| 179 |
+
| - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0680|± |0.0160|
|
| 180 |
+
| - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.2055|± |0.0336|
|
| 181 |
+
| - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.1760|± |0.0241|
|
| 182 |
+
| - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2120|± |0.0259|
|
| 183 |
+
| - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.2240|± |0.0264|
|
| 184 |
+
| - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.5393|± |0.0375|
|
| 185 |
+
| - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
|
| 186 |
+
| - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2760|± |0.0283|
|
| 187 |
+
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.1720|± |0.0239|
|
| 188 |
+
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1360|± |0.0217|
|
| 189 |
+
| - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3320|± |0.0298|
|
| 190 |
+
| - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317|
|
| 191 |
+
| - leaderboard_gpqa | N/A| | | | | | | |
|
| 192 |
+
| - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2071|± |0.0289|
|
| 193 |
+
| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2637|± |0.0189|
|
| 194 |
+
| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2612|± |0.0208|
|
| 195 |
+
| - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.2770|± | N/A|
|
| 196 |
+
| | |none | 0|inst_level_strict_acc |↑ |0.2710|± | N/A|
|
| 197 |
+
| | |none | 0|prompt_level_loose_acc |↑ |0.1534|± |0.0155|
|
| 198 |
+
| | |none | 0|prompt_level_strict_acc|↑ |0.1497|± |0.0154|
|
| 199 |
+
| - leaderboard_math_hard | N/A| | | | | | | |
|
| 200 |
+
| - leaderboard_math_algebra_hard | 2|none | 4|exact_match |↑ |0.0017|± |0.0012|
|
| 201 |
+
| - leaderboard_math_counting_and_prob_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 202 |
+
| - leaderboard_math_geometry_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 203 |
+
| - leaderboard_math_intermediate_algebra_hard | 2|none | 4|exact_match |↑ |0.0033|± |0.0019|
|
| 204 |
+
| - leaderboard_math_num_theory_hard | 2|none | 4|exact_match |↑ |0.0037|± |0.0026|
|
| 205 |
+
| - leaderboard_math_prealgebra_hard | 2|none | 4|exact_match |↑ |0.0046|± |0.0023|
|
| 206 |
+
| - leaderboard_math_precalculus_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 207 |
+
| - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1068|± |0.0028|
|
| 208 |
+
| - leaderboard_musr | N/A| | | | | | | |
|
| 209 |
+
| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5160|± |0.0317|
|
| 210 |
+
| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2344|± |0.0265|
|
| 211 |
+
| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.3200|± |0.0296|
|
| 212 |
```
|