{ "epoch": 3.0, "eval_logits/chosen": -1.9102067947387695, "eval_logits/rejected": -1.8216071128845215, "eval_logps/chosen": -283.6626281738281, "eval_logps/rejected": -237.35032653808594, "eval_loss": 0.5380748510360718, "eval_rewards/accuracies": 0.7182539701461792, "eval_rewards/chosen": -0.09773208945989609, "eval_rewards/margins": 0.6768320798873901, "eval_rewards/rejected": -0.7745641469955444, "eval_runtime": 873.0984, "eval_samples": 2000, "eval_samples_per_second": 2.291, "eval_steps_per_second": 0.072, "train_loss": 0.5707186016333662, "train_runtime": 142661.7128, "train_samples": 61966, "train_samples_per_second": 1.303, "train_steps_per_second": 0.02 }