Qwen2.5-1.5B-Open-R1-Distill / train_results.json
lukehg's picture
Model save
6cdf1d9 verified
raw
history blame contribute delete
230 Bytes
{
"epoch": 1.0,
"total_flos": 76874092904448.0,
"train_loss": 0.7988722336724632,
"train_runtime": 576.3913,
"train_samples": 16610,
"train_samples_per_second": 37.492,
"train_steps_per_second": 0.335
}