{ "epoch": 3.0, "eval_logits/chosen": -1.0022624731063843, "eval_logits/rejected": -0.5906034111976624, "eval_logps/chosen": -383.65380859375, "eval_logps/rejected": -424.4626770019531, "eval_loss": 1.148720145225525, "eval_rewards/accuracies": 0.728515625, "eval_rewards/chosen": -10.874195098876953, "eval_rewards/margins": 5.130314826965332, "eval_rewards/rejected": -16.0045108795166, "eval_runtime": 215.9812, "eval_samples": 2000, "eval_samples_per_second": 9.26, "eval_steps_per_second": 0.148, "total_flos": 0.0, "train_loss": 0.21746732159101023, "train_runtime": 62085.3048, "train_samples": 61134, "train_samples_per_second": 2.954, "train_steps_per_second": 0.092 }