mtasic85 commited on
Commit
eee9c93
·
1 Parent(s): 2013daa

eval pretrain-core-3

Browse files
Files changed (1) hide show
  1. README.md +56 -0
README.md CHANGED
@@ -217,3 +217,59 @@ litgpt convert_pretrained_checkpoint ../out/pretrain-core-2/final ../out/pretrai
217
  ```bash
218
  CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain_core_model_3.yaml
219
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
217
  ```bash
218
  CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain_core_model_3.yaml
219
  ```
220
+
221
+ ```bash
222
+ 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-3/leaderboard/' --batch_size '4' --dtype 'bfloat16' '../out/pretrain-core-3/final'
223
+ ```
224
+
225
+ ```
226
+ | Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
227
+ |-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
228
+ |leaderboard | N/A| | | | | | | |
229
+ | - leaderboard_bbh | N/A| | | | | | | |
230
+ | - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.4680|± |0.0316|
231
+ | - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5187|± |0.0366|
232
+ | - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.2080|± |0.0257|
233
+ | - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.3760|± |0.0307|
234
+ | - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.5320|± |0.0316|
235
+ | - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.1160|± |0.0203|
236
+ | - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5160|± |0.0317|
237
+ | - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.2000|± |0.0253|
238
+ | - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1280|± |0.0212|
239
+ | - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3440|± |0.0301|
240
+ | - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2400|± |0.0271|
241
+ | - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.4200|± |0.0313|
242
+ | - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0560|± |0.0146|
243
+ | - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.2260|± |0.0347|
244
+ | - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.1520|± |0.0228|
245
+ | - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2080|± |0.0257|
246
+ | - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.2240|± |0.0264|
247
+ | - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.4831|± |0.0376|
248
+ | - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4640|± |0.0316|
249
+ | - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2520|± |0.0275|
250
+ | - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.1720|± |0.0239|
251
+ | - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1480|± |0.0225|
252
+ | - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3320|± |0.0298|
253
+ | - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317|
254
+ | - leaderboard_gpqa | N/A| | | | | | | |
255
+ | - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2071|± |0.0289|
256
+ | - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2619|± |0.0188|
257
+ | - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2545|± |0.0206|
258
+ | - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.2710|± | N/A|
259
+ | | |none | 0|inst_level_strict_acc |↑ |0.2626|± | N/A|
260
+ | | |none | 0|prompt_level_loose_acc |↑ |0.1165|± |0.0138|
261
+ | | |none | 0|prompt_level_strict_acc|↑ |0.1128|± |0.0136|
262
+ | - leaderboard_math_hard | N/A| | | | | | | |
263
+ | - leaderboard_math_algebra_hard | 2|none | 4|exact_match |↑ |0.0194|± |0.0040|
264
+ | - leaderboard_math_counting_and_prob_hard | 2|none | 4|exact_match |↑ |0.0148|± |0.0055|
265
+ | - leaderboard_math_geometry_hard | 2|none | 4|exact_match |↑ |0.0042|± |0.0029|
266
+ | - leaderboard_math_intermediate_algebra_hard | 2|none | 4|exact_match |↑ |0.0111|± |0.0035|
267
+ | - leaderboard_math_num_theory_hard | 2|none | 4|exact_match |↑ |0.0056|± |0.0032|
268
+ | - leaderboard_math_prealgebra_hard | 2|none | 4|exact_match |↑ |0.0161|± |0.0043|
269
+ | - leaderboard_math_precalculus_hard | 2|none | 4|exact_match |↑ |0.0092|± |0.0041|
270
+ | - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1184|± |0.0029|
271
+ | - leaderboard_musr | N/A| | | | | | | |
272
+ | - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5240|± |0.0316|
273
+ | - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2344|± |0.0265|
274
+ | - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.3000|± |0.0290|
275
+ ```