Qwen2.5-0.5B-Open-R1-Distill / all_results.json
xdrshjr's picture
Model save
13e16a8 verified
raw
history blame contribute delete
252 Bytes
{
"epoch": 0.9994447529150472,
"total_flos": 1.8998720188121088e+17,
"train_loss": 0.9762679852379693,
"train_runtime": 18617.8565,
"train_samples": 16610,
"train_samples_per_second": 2.321,
"train_steps_per_second": 0.024
}