sdgroeve's picture
End of training
8034e8a
raw
history blame
210 Bytes
{
"epoch": 3.0,
"total_flos": 1.8124066505760768e+18,
"train_loss": 0.32973566536317794,
"train_runtime": 250.3967,
"train_samples_per_second": 291.138,
"train_steps_per_second": 2.276
}