Qwen2.5-1.5B-Open-R1-Distill / all_results.json
figure1's picture
Model save
b35ee5d verified
raw
history blame contribute delete
246 Bytes
{
"epoch": 0.9948186528497409,
"total_flos": 76517996494848.0,
"train_loss": 0.8114807903766632,
"train_runtime": 1619.7988,
"train_samples": 16610,
"train_samples_per_second": 13.341,
"train_steps_per_second": 0.104
}