weight_decay_10 / all_results.json
sedrickkeh's picture
End of training
d35382b verified
raw
history blame contribute delete
221 Bytes
{
"epoch": 2.9878213802435725,
"total_flos": 7.10230108051551e+18,
"train_loss": 0.464179332813491,
"train_runtime": 60729.3117,
"train_samples_per_second": 2.336,
"train_steps_per_second": 0.005
}