chchen's picture
End of training
17adf66 verified
raw
history blame contribute delete
223 Bytes
{
"epoch": 4.994228549442093,
"total_flos": 8.777347846375342e+17,
"train_loss": 0.04924881559766496,
"train_runtime": 36995.9986,
"train_samples_per_second": 1.405,
"train_steps_per_second": 0.088
}