sl82's picture
End of training
38e0caf
{
"epoch": 3.0,
"total_flos": 1.8124066505760768e+18,
"train_loss": 0.3388945644361931,
"train_runtime": 1188.1189,
"train_samples_per_second": 61.357,
"train_steps_per_second": 0.48
}