Qwen2.5-1.5B-Open-R1-Distill / train_results.json
lucy666's picture
Model save
c78630b verified
raw
history blame contribute delete
212 Bytes
{
"total_flos": 488621249396736.0,
"train_loss": 0.5792782279982496,
"train_runtime": 6428.403,
"train_samples": 93733,
"train_samples_per_second": 5.336,
"train_steps_per_second": 0.042
}