home / grpo-gsm8k-test / summaries

summaries: 68

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
68 hendrycks_math(0) Qwen_Qwen2.5-1.5B-Instruct 5000 2457 0.4914 604 {"stop:-": 4475, "length:-": 519, "stop:Problem:": 6} 2m 30s 1 0.0 0.95 1024   /mnt/2data/Documents/safetensors/Qwen_Qwen2.5-1.5B-Instruct
Powered by Datasette · Queries took 0.663ms