Qwen2.5-1.5B-Open-R1-Distill / all_results.json
YangZhoumill's picture
Model save
3d86a5d verified
raw
history blame contribute delete
217 Bytes
{
"total_flos": 4.404961824525517e+16,
"train_loss": 0.30152319064507116,
"train_runtime": 336.0969,
"train_samples": 10016,
"train_samples_per_second": 3.868,
"train_steps_per_second": 0.967
}