llama-3-8b-base-beta-dpo-ultrafeedback-8xh200/train_results.json

{
    "epoch": 0.9989528795811519,
    "total_flos": 0.0,
    "train_loss": 1.1642480231431045,
    "train_runtime": 4421.8255,
    "train_samples": 61135,
    "train_samples_per_second": 13.826,
    "train_steps_per_second": 0.108
}