home / grpo-gsm8k-test / summaries

summaries: 22

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
22 hendrycks_math(0) grpo-gsm8k-test-30ep-success_global_step_550 5000 2561 0.5122 637 {"stop:-": 4437, "length:-": 558, "stop:Problem:": 5} 2m 34s 1 0.0 0.95 1024   /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-gsm8k-test-30ep-success/global_step_550/actor/huggingface
Powered by Datasette · Queries took 0.624ms