phi-2-gpo-iter-1 / train_results.json
lole25's picture
Model save
44ca9b5 verified
{
"epoch": 1.98,
"train_loss": 0.010306676939850854,
"train_runtime": 2255.3236,
"train_samples": 61135,
"train_samples_per_second": 0.887,
"train_steps_per_second": 0.055
}