summaries: 69
This data as json
| id | task_name | model_tag | total_examples | correct | accuracy | no_answer_count | stop_reason_counts | duration_human | pass_k | temperature | top_p | max_tokens | error | model |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 69 | TOTAL | 34 models | 214846 | 125885 | 0.585931318246558 | 21764 | {} | 1h 45m 38s | 1 | 0.0 | 0.95 | 1024 | Models: grpo-gsm8k-test-30ep-success_global_step_50, grpo-gsm8k-test-30ep-success_global_step_100, grpo-gsm8k-test-30ep-success_global_step_150, grpo-gsm8k-test-30ep-success_global_step_200, grpo-gsm8k-test-30ep-success_global_step_250, grpo-gsm8k-test-30ep-success_global_step_300, grpo-gsm8k-test-30ep-success_global_step_350, grpo-gsm8k-test-30ep-success_global_step_400, grpo-gsm8k-test-30ep-success_global_step_450, grpo-gsm8k-test-30ep-success_global_step_500, grpo-gsm8k-test-30ep-success_global_step_550, grpo-gsm8k-test-30ep-success_global_step_600, grpo-gsm8k-test-30ep-success_global_step_650, grpo-gsm8k-test-30ep-success_global_step_700, grpo-gsm8k-test-30ep-success_global_step_750, grpo-gsm8k-test-30ep-success_global_step_800, grpo-gsm8k-test-30ep-success_global_step_850, grpo-gsm8k-test-30ep-success_global_step_900, grpo-gsm8k-test-30ep-success_global_step_950, grpo-gsm8k-test-30ep-success_global_step_1000, grpo-gsm8k-test-30ep-success_global_step_1050, grpo-gsm8k-test-30ep-success_global_step_1100, grpo-gsm8k-test-30ep-success_global_step_1150, grpo-gsm8k-test-30ep-success_global_step_1200, grpo-gsm8k-test-30ep-success_global_step_1250, grpo-gsm8k-test-30ep-success_global_step_1300, grpo-gsm8k-test-30ep-success_global_step_1350, grpo-gsm8k-test-30ep-success_global_step_1400, grpo-gsm8k-test-30ep-success_global_step_1450, grpo-gsm8k-test-30ep-success_global_step_1500, grpo-gsm8k-test-30ep-success_global_step_1550, grpo-gsm8k-test-30ep-success_global_step_1600, grpo-gsm8k-test-30ep-success_global_step_1620, Qwen_Qwen2.5-1.5B-Instruct | Tasks: gsm8k_main(0), hendrycks_math(0) |