home / grpo-gsm8k-test / summaries

summaries: 1

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
1 gsm8k_main(0) grpo-gsm8k-test-30ep-success_global_step_50 1319 981 0.7437452615617892 7 {"stop:-": 1312, "length:-": 7} 26s 1 0.0 0.95 1024   /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-gsm8k-test-30ep-success/global_step_50/actor/huggingface
Powered by Datasette · Queries took 1.071ms