summaries: 92
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 92 | hendrycks_math(0) | grpo-gsm8k-train-13ep-success_global_step_2300 | 5000 | 2574 | 0.5148 | 586 | {"stop:-": 4490, "length:-": 507, "stop:Problem:": 3} | 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_2300/actor/huggingface |