ALM-AHME's picture
End of training
c7616b1
raw
history blame contribute delete
209 Bytes
{
"epoch": 4.96,
"total_flos": 8.138660625246413e+18,
"train_loss": 0.23329446437538312,
"train_runtime": 4933.7001,
"train_samples_per_second": 6.065,
"train_steps_per_second": 0.094
}