smolm-autoreg-bpe-seed_555 / eval_results.json
kanishka's picture
End of training
17a5883
raw
history blame
267 Bytes
{
"epoch": 10.0,
"eval_accuracy": 0.5411096141763542,
"eval_loss": 2.2898333072662354,
"eval_runtime": 4.4554,
"eval_samples": 5038,
"eval_samples_per_second": 1130.761,
"eval_steps_per_second": 2.244,
"perplexity": 9.873291738002548
}