{ "epoch": 1.0, "eval_logits/chosen": -2.671875, "eval_logits/rejected": -2.625, "eval_logps/chosen": -536.0, "eval_logps/rejected": -848.0, "eval_loss": 0.27069464325904846, "eval_rewards/accuracies": 0.8784698843955994, "eval_rewards/chosen": -3.421875, "eval_rewards/margins": 3.296875, "eval_rewards/rejected": -6.71875, "eval_runtime": 2786.9904, "eval_samples": 95033, "eval_samples_per_second": 33.905, "eval_steps_per_second": 0.53, "total_flos": 0.0, "train_loss": 0.2561736330384371, "train_runtime": 125157.49, "train_samples": 1701200, "train_samples_per_second": 13.592, "train_steps_per_second": 0.106 }