summaries: 31
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 31 | gsm8k_main(0) | dsr-one-example-grpo_global_step_800 | 1319 | 972 | 0.7369219105382866 | 4 | {"stop:-": 1315, "length:-": 4} | 23s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/dsr-one-example-grpo/global_step_800/actor/huggingface |