Mistral-Nemo-12B-Instruct-SAA / train_results.json
chchen's picture
End of training
fdf211e verified
raw
history blame contribute delete
218 Bytes
{
"epoch": 2.986666666666667,
"total_flos": 4.410496642646016e+16,
"train_loss": 0.4940077399923688,
"train_runtime": 519.2548,
"train_samples_per_second": 5.2,
"train_steps_per_second": 0.324
}