Qwen2.5-1.5B-Open-R1-Distill / train_results.json
AggarwalAnkit's picture
Model save
63b1717 verified
{
"epoch": 1.0,
"total_flos": 76916824473600.0,
"train_loss": 0.8026797080181054,
"train_runtime": 1042.2023,
"train_samples": 16610,
"train_samples_per_second": 20.735,
"train_steps_per_second": 0.162
}