Qwen2.5-1.5B-Open-R1-Distill / train_results.json
JeffP111's picture
Model save
12d1642 verified
raw
history blame contribute delete
230 Bytes
{
"epoch": 1.0,
"total_flos": 76874092904448.0,
"train_loss": 0.7989139248052409,
"train_runtime": 2563.2883,
"train_samples": 16610,
"train_samples_per_second": 8.431,
"train_steps_per_second": 0.075
}