home / grpo-gsm8k-train / summaries

summaries: 85

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
85 gsm8k_main(0) grpo-gsm8k-train-13ep-success_global_step_2150 1319 1060 0.8036391205458681 5 {"stop:-": 1314, "length:-": 5} 24s 1 0.0 0.95 1024   /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-gsm8k-train-13ep-success/global_step_2150/actor/huggingface
Powered by Datasette · Queries took 3.465ms