{ "epoch": 2.0, "eval_logits/chosen": 3.998190402984619, "eval_logits/rejected": 4.15942907333374, "eval_logps/chosen": -399.73858642578125, "eval_logps/rejected": -601.5961303710938, "eval_loss": 0.669053852558136, "eval_rewards/accuracies": 0.3075396716594696, "eval_rewards/chosen": -0.3145403265953064, "eval_rewards/margins": 0.18879380822181702, "eval_rewards/rejected": -0.503334105014801, "eval_runtime": 113.5521, "eval_samples": 2000, "eval_samples_per_second": 17.613, "eval_steps_per_second": 0.555, "total_flos": 0.0, "train_loss": 0.6542075766871372, "train_runtime": 2362.1376, "train_samples": 6113, "train_samples_per_second": 5.176, "train_steps_per_second": 0.081 }