home / grpo-gsm8k-test / summaries

summaries: 14

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
14 hendrycks_math(0) grpo-gsm8k-test-30ep-success_global_step_350 5000 2540 0.508 662 {"stop:-": 4407, "length:-": 591, "stop:Problem:": 2} 2m 33s 1 0.0 0.95 1024   /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-gsm8k-test-30ep-success/global_step_350/actor/huggingface
Powered by Datasette · Queries took 0.728ms