{ "epoch": 0.995910949568378, "eval_logits/chosen": -6.208152770996094, "eval_logits/rejected": -5.976426601409912, "eval_logps/chosen": -0.5618715286254883, "eval_logps/rejected": -0.6567398905754089, "eval_loss": 4.398404598236084, "eval_rewards/accuracies": 0.5840163826942444, "eval_rewards/chosen": -5.618715286254883, "eval_rewards/margins": 0.9486842155456543, "eval_rewards/rejected": -6.567399024963379, "eval_runtime": 87.0112, "eval_samples": 1941, "eval_samples_per_second": 22.307, "eval_steps_per_second": 1.402, "total_flos": 0.0, "train_loss": 4.762774154217574, "train_runtime": 2004.0235, "train_samples": 17605, "train_samples_per_second": 8.785, "train_steps_per_second": 0.068 }