ALM-AHME's picture
End of training
b185e6f
raw
history blame
212 Bytes
{
"epoch": 14.97,
"total_flos": 1.2584990004785971e+19,
"train_loss": 0.38356898541164675,
"train_runtime": 11197.9622,
"train_samples_per_second": 4.891,
"train_steps_per_second": 0.153
}