{ "epoch": 4.0, "eval_logits/chosen": -2.223268747329712, "eval_logits/rejected": -2.218452215194702, "eval_logps/chosen": -34.1085205078125, "eval_logps/rejected": -37.61680603027344, "eval_loss": 0.9893841743469238, "eval_rewards/accuracies": 0.5124584436416626, "eval_rewards/chosen": -0.02958693355321884, "eval_rewards/margins": 0.010487398132681847, "eval_rewards/rejected": -0.04007433354854584, "eval_runtime": 145.4187, "eval_samples": 343, "eval_samples_per_second": 2.359, "eval_steps_per_second": 0.296, "train_loss": 0.2625940967689861, "train_runtime": 10748.6274, "train_samples": 3079, "train_samples_per_second": 1.146, "train_steps_per_second": 0.143 }