home / grpo-gsm8k-test / summaries

summaries: 33

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
33 gsm8k_main(0) grpo-gsm8k-test-30ep-success_global_step_850 1319 1187 0.8999241849886277 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-test-30ep-success/global_step_850/actor/huggingface
Powered by Datasette · Queries took 0.563ms