summaries: 36
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 36 | hendrycks_math(0) | dsr-one-example-grpo_global_step_900 | 5000 | 2439 | 0.4878 | 599 | {"stop:-": 4469, "length:-": 516, "stop:Problem:": 15} | 2m 30s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/dsr-one-example-grpo/global_step_900/actor/huggingface |