{ "epoch": 1.0, "eval_logits/chosen": -2.9815621376037598, "eval_logits/rejected": -3.0448005199432373, "eval_logps/chosen": -86.49230194091797, "eval_logps/rejected": -122.99235534667969, "eval_loss": 0.6931473016738892, "eval_rewards/accuracies": 0.0, "eval_rewards/chosen": 0.0, "eval_rewards/margins": 0.0, "eval_rewards/rejected": 0.0, "eval_runtime": 12.7004, "eval_samples": 20, "eval_samples_per_second": 1.575, "eval_steps_per_second": 0.157, "train_loss": 0.5198603868484497, "train_runtime": 25.1995, "train_samples": 20, "train_samples_per_second": 0.794, "train_steps_per_second": 0.04 }