llama-160m-mnli / train_results.json
Cheng98's picture
End of training
d96c0b8
raw
history blame contribute delete
198 Bytes
{
"epoch": 4.0,
"train_loss": 1.0949462632001457,
"train_runtime": 12056.6812,
"train_samples": 392702,
"train_samples_per_second": 130.285,
"train_steps_per_second": 1.018
}