marvind434's picture
End of training
b8c23fd
raw
history blame contribute delete
207 Bytes
{
"epoch": 20.0,
"total_flos": 1.73991922900992e+16,
"train_loss": 0.08395950198173523,
"train_runtime": 50.8586,
"train_samples_per_second": 13.764,
"train_steps_per_second": 0.393
}