llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.8-20260428-045924/all_results.json

{
    "epoch": 1.0,
    "total_flos": 0.0,
    "train_loss": 0.9160819085158965,
    "train_runtime": 1729.8503,
    "train_samples": 43598,
    "train_samples_per_second": 25.203,
    "train_steps_per_second": 0.394
}