summaries: 45
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 45 | gsm8k_main(0) | grpo-one-example-gsm8k_global_step_150 | 1319 | 982 | 0.7445034116755117 | 5 | {"stop:-": 1314, "length:-": 5} | 23s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-one-example-gsm8k/global_step_150/actor/huggingface |