{ "epoch": 2.0, "eval_logits/chosen": -1.3352028131484985, "eval_logits/rejected": -1.3116942644119263, "eval_logps/chosen": -682.5323486328125, "eval_logps/rejected": -1058.265869140625, "eval_loss": 0.3361551761627197, "eval_rewards/accuracies": 0.875, "eval_rewards/chosen": -3.233959674835205, "eval_rewards/margins": 3.914942741394043, "eval_rewards/rejected": -7.148902893066406, "eval_runtime": 2.9627, "eval_samples": 200, "eval_samples_per_second": 67.507, "eval_steps_per_second": 1.35, "total_flos": 0.0, "train_loss": 0.2817063624168927, "train_runtime": 11455.6006, "train_samples": 209650, "train_samples_per_second": 36.602, "train_steps_per_second": 0.143 }