Qwen2.5-7B-Open-R1-Distill / train_results.json
tenacioustommy's picture
Model save
a4c0407 verified
raw
history blame contribute delete
214 Bytes
{
"total_flos": 176018430099456.0,
"train_loss": 0.6783329638696852,
"train_runtime": 1805.4988,
"train_samples": 16610,
"train_samples_per_second": 11.976,
"train_steps_per_second": 0.047
}