{ "epoch": 1.0, "eval_logits/chosen": -1.3398174047470093, "eval_logits/rejected": 0.48268866539001465, "eval_logps/chosen": -252.1617889404297, "eval_logps/rejected": -355.7885437011719, "eval_loss": 0.5094775557518005, "eval_rewards/accuracies": 0.7480158805847168, "eval_rewards/chosen": -0.5198203921318054, "eval_rewards/margins": 0.7899001836776733, "eval_rewards/rejected": -1.309720516204834, "eval_runtime": 410.0254, "eval_samples": 4022, "eval_samples_per_second": 9.809, "eval_steps_per_second": 0.307, "train_loss": 0.35703677506673903, "train_runtime": 4562.5722, "train_samples": 16118, "train_samples_per_second": 3.533, "train_steps_per_second": 0.055 }