Qwen2.5-1.5B-Open-R1-GRPO / train_results.json
yolay's picture
Model save
c9313e0 verified
{
"total_flos": 0.0,
"train_loss": 0.13680233840041295,
"train_runtime": 51841.8905,
"train_samples": 72441,
"train_samples_per_second": 1.397,
"train_steps_per_second": 0.012
}