summaries: 68
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 68 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1650 | 5000 | 1552 | 0.3104 | 952 | {"stop:-": 4125, "length:-": 873, "stop:Problem:": 2} | 2m 13s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1650/huggingface |