Llama-3.2-3B-Open-R1-Distill / train_results.json
rkumar1999's picture
Model save
e4f5dc0 verified
raw
history blame contribute delete
213 Bytes
{
"total_flos": 456093583015936.0,
"train_loss": 13.683566497093024,
"train_runtime": 13295.3238,
"train_samples": 5000,
"train_samples_per_second": 0.518,
"train_steps_per_second": 0.032
}