home / grpo-one-example / summaries

summaries: 83

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
83 TOTAL 41 models 259079 140807 0.5434905955326368 25911 {} 2h 06m 20s 1 0.0 0.95 1024   Models: dsr-one-example-grpo_global_step_50, dsr-one-example-grpo_global_step_100, dsr-one-example-grpo_global_step_150, dsr-one-example-grpo_global_step_200, dsr-one-example-grpo_global_step_250, dsr-one-example-grpo_global_step_300, dsr-one-example-grpo_global_step_350, dsr-one-example-grpo_global_step_400, dsr-one-example-grpo_global_step_450, dsr-one-example-grpo_global_step_500, dsr-one-example-grpo_global_step_550, dsr-one-example-grpo_global_step_600, dsr-one-example-grpo_global_step_650, dsr-one-example-grpo_global_step_700, dsr-one-example-grpo_global_step_750, dsr-one-example-grpo_global_step_800, dsr-one-example-grpo_global_step_850, dsr-one-example-grpo_global_step_900, dsr-one-example-grpo_global_step_950, dsr-one-example-grpo_global_step_1000, grpo-one-example-gsm8k_global_step_50, grpo-one-example-gsm8k_global_step_100, grpo-one-example-gsm8k_global_step_150, grpo-one-example-gsm8k_global_step_200, grpo-one-example-gsm8k_global_step_250, grpo-one-example-gsm8k_global_step_300, grpo-one-example-gsm8k_global_step_350, grpo-one-example-gsm8k_global_step_400, grpo-one-example-gsm8k_global_step_450, grpo-one-example-gsm8k_global_step_500, grpo-one-example-gsm8k_global_step_550, grpo-one-example-gsm8k_global_step_600, grpo-one-example-gsm8k_global_step_650, grpo-one-example-gsm8k_global_step_700, grpo-one-example-gsm8k_global_step_750, grpo-one-example-gsm8k_global_step_800, grpo-one-example-gsm8k_global_step_850, grpo-one-example-gsm8k_global_step_900, grpo-one-example-gsm8k_global_step_950, grpo-one-example-gsm8k_global_step_1000, Qwen_Qwen2.5-1.5B-Instruct | Tasks: gsm8k_main(0), hendrycks_math(0)
Powered by Datasette · Queries took 0.606ms