summaries: 72
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 72 | hendrycks_math(0) | grpo-gsm8k-train-13ep-success_global_step_1800 | 5000 | 2591 | 0.5182 | 613 | {"stop:-": 4470, "length:-": 526, "stop:Problem:": 4} | 2m 35s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-gsm8k-train-13ep-success/global_step_1800/actor/huggingface |