smolm-autoreg-bpe-seed_111 / eval_results.json
kanishka's picture
End of training
259acde verified
{
"epoch": 10.0,
"eval_accuracy": 0.5000412022645466,
"eval_loss": 2.4759199619293213,
"eval_runtime": 3.3905,
"eval_samples": 4491,
"eval_samples_per_second": 1324.582,
"eval_steps_per_second": 10.618,
"perplexity": 11.892642860763285
}