smolm-mlm-bpe-unmask-seed_111 / train_results.json
kanishka's picture
End of training
c7994a3
raw
history blame
No virus
199 Bytes
{
"epoch": 10.0,
"train_loss": 3.080881611061448,
"train_runtime": 7359.6812,
"train_samples": 763989,
"train_samples_per_second": 1038.074,
"train_steps_per_second": 16.221
}