Qwen2.5-3B-Open-R1-GRPO / train_results.json
Yukang's picture
Model save
7e03ccf verified
{
"total_flos": 0.0,
"train_loss": 0.00015187089497744325,
"train_runtime": 1302.9313,
"train_samples": 93733,
"train_samples_per_second": 71.94,
"train_steps_per_second": 2.249
}