summaries: 7
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7 | gsm8k_main(0) | grpo-gsm8k-train-13ep-success_global_step_200 | 1319 | 1003 | 0.7604245640636846 | 4 | {"stop:-": 1315, "length:-": 4} | 24s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-gsm8k-train-13ep-success/global_step_200/actor/huggingface |