home / grpo-gsm8k-test / summaries

summaries: 12

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
12 hendrycks_math(0) grpo-gsm8k-test-30ep-success_global_step_300 5000 2516 0.5032 659 {"stop:-": 4405, "length:-": 595} 2m 37s 1 0.0 0.95 1024   /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/finished-models/grpo-gsm8k-test-30ep-success/global_step_300/actor/huggingface
Powered by Datasette · Queries took 0.641ms