train_svamp_101112_1760638001 / eval_results.json
rbelanec's picture
End of training
8da4692 verified
{
"epoch": 20.0,
"eval_loss": 0.2259398251771927,
"eval_runtime": 1.6777,
"eval_samples_per_second": 41.723,
"eval_steps_per_second": 10.729,
"num_input_tokens_seen": 1430592
}