{ "epoch": 2.888888888888889, "eval_logits/chosen": -2.4385855197906494, "eval_logits/rejected": -2.4530792236328125, "eval_logps/chosen": -270.9550476074219, "eval_logps/rejected": -195.91143798828125, "eval_loss": 0.7199638485908508, "eval_rewards/accuracies": 0.7708333134651184, "eval_rewards/chosen": 2.151623010635376, "eval_rewards/margins": 1.9589000940322876, "eval_rewards/rejected": 0.1927231401205063, "eval_runtime": 25.777, "eval_samples_per_second": 14.742, "eval_steps_per_second": 0.233, "total_flos": 459455468666880.0, "train_loss": 0.4058258105547, "train_runtime": 1363.3295, "train_samples_per_second": 7.523, "train_steps_per_second": 0.029 }