{ "epoch": 3.0, "eval_logits/chosen": -3.063735008239746, "eval_logits/rejected": -3.0579655170440674, "eval_logps/chosen": -63.48755645751953, "eval_logps/rejected": -69.37789154052734, "eval_loss": 0.6867183446884155, "eval_rewards/accuracies": 0.5936338305473328, "eval_rewards/chosen": -0.04775654152035713, "eval_rewards/margins": 0.01422115322202444, "eval_rewards/rejected": -0.061977699398994446, "eval_runtime": 382.4366, "eval_samples": 4304, "eval_samples_per_second": 11.254, "eval_steps_per_second": 1.407, "total_flos": 0.0, "train_loss": 0.6843596647285796, "train_runtime": 104656.3305, "train_samples": 92858, "train_samples_per_second": 2.662, "train_steps_per_second": 0.083 }