Qwen2.5-1.5B-Open-R1-GRPO / train_results.json
tenacioustommy's picture
Model save
225f871 verified
{
"total_flos": 0.0,
"train_loss": 0.7486699576652505,
"train_runtime": 29158.9846,
"train_samples": 72441,
"train_samples_per_second": 2.484,
"train_steps_per_second": 0.044
}