{ "epoch": 1.0, "eval_logits/chosen": 98.69615173339844, "eval_logits/rejected": 98.67865753173828, "eval_logps/chosen": -32.57830810546875, "eval_logps/rejected": -36.26156234741211, "eval_loss": 0.9490477442741394, "eval_rewards/accuracies": 0.5689368844032288, "eval_rewards/chosen": -0.06756443530321121, "eval_rewards/margins": 0.07995220273733139, "eval_rewards/rejected": -0.1475166231393814, "eval_runtime": 103.72, "eval_samples": 343, "eval_samples_per_second": 3.307, "eval_steps_per_second": 0.415, "train_loss": 0.735349414874981, "train_runtime": 2550.735, "train_samples": 3079, "train_samples_per_second": 1.207, "train_steps_per_second": 0.151 }