qwen-3-8b-base-r-dpo-ultrafeedback-4xH200-batch-128-rerun-2-runpod/train_results.json

{
    "epoch": 0.9989528795811519,
    "total_flos": 0.0,
    "train_loss": 17.04746322311945,
    "train_runtime": 7166.7787,
    "train_samples": 61135,
    "train_samples_per_second": 8.53,
    "train_steps_per_second": 0.067
}