{ "epoch": 3.0, "eval_logits/chosen": -13.625, "eval_logits/rejected": -13.375, "eval_logps/chosen": -660.0, "eval_logps/rejected": -652.0, "eval_loss": 1.0084375143051147, "eval_rewards/accuracies": 0.505859375, "eval_rewards/chosen": -3.40625, "eval_rewards/margins": 0.2373046875, "eval_rewards/rejected": -3.640625, "eval_runtime": 46.5887, "eval_samples": 2000, "eval_samples_per_second": 42.929, "eval_steps_per_second": 0.687, "total_flos": 0.0, "train_loss": 0.06693936966889477, "train_runtime": 12411.6425, "train_samples": 61118, "train_samples_per_second": 14.773, "train_steps_per_second": 0.231 }