shravankumar147's picture
End of training
4e905a1
raw
history blame
210 Bytes
{
"epoch": 3.0,
"total_flos": 1.8124066505760768e+18,
"train_loss": 0.33793828236429313,
"train_runtime": 1109.1978,
"train_samples_per_second": 65.723,
"train_steps_per_second": 0.514
}