summaries: 20
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 20 | hendrycks_math(0) | dsr-one-example-grpo_global_step_500 | 5000 | 2428 | 0.4856 | 613 | {"stop:-": 4456, "length:-": 531, "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_500/actor/huggingface |