all_results.json

{
    "epoch": 0.9919697685403873,
    "eval_dpo_loss": 0.6835533380508423,
    "eval_logits": -1.6164112091064453,
    "eval_logps": -90.96741485595703,
    "eval_loss": 0.6808017492294312,
    "eval_objective": 0.6835533380508423,
    "eval_ranking_idealized": 0.6030020713806152,
    "eval_ranking_idealized_expo": 0.5222567319869995,
    "eval_ranking_simple": 0.5331262946128845,
    "eval_regularize": 0.6835533380508423,
    "eval_runtime": 307.5247,
    "eval_samples": 5790,
    "eval_samples_per_second": 18.828,
    "eval_steps_per_second": 1.571,
    "eval_wo_beta": 7.86433744430542,
    "total_flos": 0.0,
    "train_loss": 0.5958910301753453,
    "train_runtime": 9674.8125,
    "train_samples": 50802,
    "train_samples_per_second": 26.255,
    "train_steps_per_second": 0.182
}