summaries: 74
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 74 | hendrycks_math(0) | grpo-one-example-gsm8k_global_step_850 | 5000 | 2439 | 0.4878 | 627 | {"stop:-": 4449, "length:-": 547, "stop:Problem:": 4} | 2m 36s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-one-example-gsm8k/global_step_850/actor/huggingface |