Qwen2.5-1.5B-Open-R1-Distill / train_results.json
Rano23's picture
Model save
0e6ade2 verified
raw
history blame
214 Bytes
{
"total_flos": 488621249396736.0,
"train_loss": 0.5792123831030148,
"train_runtime": 3418.6445,
"train_samples": 93733,
"train_samples_per_second": 10.034,
"train_steps_per_second": 0.078
}