vanilla_dpo_iter_4 / all_results.json
ShenaoZ's picture
Model save
2cbbc30 verified
{
"epoch": 1.0,
"train_loss": 0.6200787784197391,
"train_runtime": 14536.4272,
"train_samples": 20000,
"train_samples_per_second": 1.376,
"train_steps_per_second": 0.011
}