summaries: 26
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 26 | hendrycks_math(0) | grpo-gsm8k-train-13ep-success_global_step_650 | 5000 | 2557 | 0.5114 | 628 | {"stop:-": 4442, "length:-": 557, "stop:Problem:": 1} | 2m 33s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-gsm8k-train-13ep-success/global_step_650/actor/huggingface |