Qwen2.5-1.5B-Open-R1-Distill / train_results.json
lewtun's picture
lewtun HF Staff
Model save
22d8b46 verified
{
"total_flos": 1.0371853292601868e+19,
"train_loss": 0.5346580615310357,
"train_runtime": 5110.5186,
"train_samples": 93733,
"train_samples_per_second": 18.341,
"train_steps_per_second": 0.143
}