all_results.json

{
    "epoch": 2.9806329711856403,
    "eval_dpo_loss": 245.87562561035156,
    "eval_logits": -0.5435077548027039,
    "eval_logps": -82.8267593383789,
    "eval_loss": 486.1625671386719,
    "eval_objective": 489.7927551269531,
    "eval_ranking_idealized": 0.5212215185165405,
    "eval_ranking_idealized_expo": 0.5212215185165405,
    "eval_ranking_simple": 0.5253623127937317,
    "eval_regularize": 489.7927551269531,
    "eval_runtime": 308.4786,
    "eval_samples": 5790,
    "eval_samples_per_second": 18.77,
    "eval_steps_per_second": 1.566,
    "eval_wo_beta": 14.046432495117188,
    "total_flos": 0.0,
    "train_loss": 38.77721726190476,
    "train_runtime": 6898.2426,
    "train_samples": 50802,
    "train_samples_per_second": 36.822,
    "train_steps_per_second": 0.255
}