{ "epoch": 1.98, "eval_logits/chosen": -0.0055040339939296246, "eval_logits/rejected": 0.09165824949741364, "eval_logps/chosen": -306.3620910644531, "eval_logps/rejected": -278.66876220703125, "eval_loss": 0.010676206089556217, "eval_rewards/accuracies": 0.5084999799728394, "eval_rewards/chosen": -2.4409100660705008e-05, "eval_rewards/margins": 0.00048807679559104145, "eval_rewards/rejected": -0.0005124859162606299, "eval_runtime": 433.0135, "eval_samples": 2000, "eval_samples_per_second": 4.619, "eval_steps_per_second": 1.155, "train_loss": 0.010321829197627882, "train_runtime": 1406.1718, "train_samples": 61135, "train_samples_per_second": 1.422, "train_steps_per_second": 0.088 }