Qwen2.5-3B-Open-R1-Distill / train_results.json
tenacioustommy's picture
Model save
47b5143 verified
raw
history blame contribute delete
214 Bytes
{
"total_flos": 128380330573824.0,
"train_loss": 0.7332075143001489,
"train_runtime": 1234.0886,
"train_samples": 16610,
"train_samples_per_second": 17.521,
"train_steps_per_second": 0.137
}