Qwen2.5-1.5B-Open-R1-Distill / train_results.json
XiaoJie88's picture
Model save
2a9ff17 verified
raw
history blame contribute delete
212 Bytes
{
"total_flos": 77096571633664.0,
"train_loss": 0.7200509982950547,
"train_runtime": 16045.7979,
"train_samples": 16710,
"train_samples_per_second": 0.34,
"train_steps_per_second": 0.011
}