summaries: 18
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 18 | hendrycks_math(0) | dsr-one-example-grpo_global_step_450 | 5000 | 2462 | 0.4924 | 580 | {"stop:-": 4490, "length:-": 497, "stop:Problem:": 13} | 2m 28s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/dsr-one-example-grpo/global_step_450/actor/huggingface |