{ "epoch": 3.0, "eval_logits/chosen": -1.0257766246795654, "eval_logits/rejected": -0.9396774172782898, "eval_logps/chosen": -86.46468353271484, "eval_logps/rejected": -123.79679870605469, "eval_loss": 0.00656638341024518, "eval_rewards/accuracies": 0.9888268113136292, "eval_rewards/chosen": -0.4634130895137787, "eval_rewards/margins": 29.004287719726562, "eval_rewards/rejected": -29.467697143554688, "eval_runtime": 133.5357, "eval_samples": 2862, "eval_samples_per_second": 21.432, "eval_steps_per_second": 1.34, "train_loss": 0.022793083270943315, "train_runtime": 24920.2972, "train_samples": 140201, "train_samples_per_second": 16.878, "train_steps_per_second": 0.264 }