all_results.json

{
    "epoch": 2.99,
    "eval_log_odds_chosen": 0.3599511682987213,
    "eval_log_odds_ratio": -0.6241087913513184,
    "eval_logits/chosen": -2.9335391521453857,
    "eval_logits/rejected": -2.9442245960235596,
    "eval_logps/chosen": -0.7882003784179688,
    "eval_logps/rejected": -0.9709375500679016,
    "eval_loss": 0.8561599850654602,
    "eval_nll_loss": 0.8317307829856873,
    "eval_rewards/accuracies": 0.6614583134651184,
    "eval_rewards/chosen": -0.03941002115607262,
    "eval_rewards/margins": 0.009136858396232128,
    "eval_rewards/rejected": -0.04854688048362732,
    "eval_runtime": 32.31,
    "eval_samples": 750,
    "eval_samples_per_second": 23.213,
    "eval_steps_per_second": 0.743,
    "train_loss": 0.8898289559379456,
    "train_runtime": 3406.8155,
    "train_samples": 6750,
    "train_samples_per_second": 5.944,
    "train_steps_per_second": 0.092
}