qwen-2.5-3b-r1-countdown / train_results.json
khuang2's picture
Model save
ae384ed verified
raw
history blame contribute delete
203 Bytes
{
"total_flos": 0.0,
"train_loss": 0.0008345579063699067,
"train_runtime": 37446.2823,
"train_samples": 45000,
"train_samples_per_second": 0.673,
"train_steps_per_second": 0.012
}