summaries: 48
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 48 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1150 | 5000 | 1695 | 0.339 | 832 | {"stop:-": 4251, "length:-": 744, "stop:Problem:": 5} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1150/huggingface |