all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.6333940029144287,
    "eval_logits/rejected": -2.5763978958129883,
    "eval_logps/chosen": -280.7647705078125,
    "eval_logps/rejected": -159.44223022460938,
    "eval_loss": 0.6931471228599548,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 5.9655,
    "eval_samples": 100,
    "eval_samples_per_second": 16.763,
    "eval_steps_per_second": 0.335,
    "total_flos": 0.0,
    "train_loss": 0.6931471824645996,
    "train_runtime": 29.6161,
    "train_samples": 100,
    "train_samples_per_second": 3.377,
    "train_steps_per_second": 0.034
}