chchen's picture
End of training
b0ae814 verified
raw
history blame contribute delete
223 Bytes
{
"epoch": 4.938271604938271,
"total_flos": 1.6732379190126182e+17,
"train_loss": 0.09858836162090301,
"train_runtime": 5549.9172,
"train_samples_per_second": 0.365,
"train_steps_per_second": 0.023
}