{ "epoch": 1.0, "eval_logits/chosen": -2.255185127258301, "eval_logits/rejected": -2.2027812004089355, "eval_logps/chosen": -259.245849609375, "eval_logps/rejected": -253.8891143798828, "eval_loss": 2121.045166015625, "eval_rewards/accuracies": 0.7599206566810608, "eval_rewards/chosen": 0.057787273079156876, "eval_rewards/margins": 0.14896924793720245, "eval_rewards/rejected": -0.09118196368217468, "eval_runtime": 547.839, "eval_samples": 2000, "eval_samples_per_second": 3.651, "eval_steps_per_second": 0.115, "train_loss": 2164.5614415454666, "train_runtime": 32346.8016, "train_samples": 61135, "train_samples_per_second": 1.89, "train_steps_per_second": 0.015 }