summaries: 25
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 25 | gsm8k_main(0) | dsr-one-example-grpo_global_step_650 | 1319 | 960 | 0.7278241091736164 | 7 | {"stop:-": 1312, "length:-": 7} | 24s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/dsr-one-example-grpo/global_step_650/actor/huggingface |