distilled-mt5-small-0.8-2 / train_results.json
Lvxue's picture
End of training
ea213f6
raw
history blame contribute delete
No virus
190 Bytes
{
"epoch": 5.0,
"train_loss": 272.008780625,
"train_runtime": 2750.9226,
"train_samples": 10000,
"train_samples_per_second": 18.176,
"train_steps_per_second": 4.544
}