llama-160m-boolq / train_results.json
Cheng98's picture
End of training
32cd7a0
raw
history blame contribute delete
195 Bytes
{
"epoch": 3.96,
"train_loss": 0.6814518758695419,
"train_runtime": 329.9402,
"train_samples": 9427,
"train_samples_per_second": 114.287,
"train_steps_per_second": 0.885
}