all_results.json

{
    "epoch": 2.992914501653283,
    "eval_dpo_loss": 0.697369396686554,
    "eval_logits": -1.230570912361145,
    "eval_logps": -85.98023223876953,
    "eval_loss": 0.1381419599056244,
    "eval_objective": 0.1370057463645935,
    "eval_ranking_idealized": 0.6024844646453857,
    "eval_ranking_idealized_expo": 0.5232919454574585,
    "eval_ranking_simple": 0.5243270993232727,
    "eval_regularize": 0.1370057463645935,
    "eval_runtime": 536.0757,
    "eval_samples": 5790,
    "eval_samples_per_second": 10.801,
    "eval_steps_per_second": 0.901,
    "eval_wo_beta": 15.63470458984375,
    "total_flos": 0.0,
    "train_loss": 0.08480868444806247,
    "train_runtime": 47353.1169,
    "train_samples": 50802,
    "train_samples_per_second": 3.218,
    "train_steps_per_second": 0.022
}