Weili's picture
End of training
b6625d7
raw
history blame contribute delete
207 Bytes
{
"epoch": 3.0,
"total_flos": 5.649571096410931e+18,
"train_loss": 0.2564373242227655,
"train_runtime": 2758.982,
"train_samples_per_second": 26.423,
"train_steps_per_second": 0.207
}