dpo-selective-longerrun / train_results.json
wxzhang's picture
Model save
59c7c4d verified
raw
history blame contribute delete
194 Bytes
{
"epoch": 1.57,
"train_loss": 0.4390208276112874,
"train_runtime": 42485.337,
"train_samples": 61135,
"train_samples_per_second": 2.26,
"train_steps_per_second": 0.035
}