{ "epoch": 0.9999813887699838, "eval_logits/chosen": -3.90625, "eval_logits/rejected": -3.71875, "eval_logps/chosen": -912.0, "eval_logps/rejected": -1024.0, "eval_loss": 0.4587233364582062, "eval_rewards/accuracies": 0.755190908908844, "eval_rewards/chosen": -7.125, "eval_rewards/margins": 1.40625, "eval_rewards/rejected": -8.5, "eval_runtime": 6073.2681, "eval_samples": 191184, "eval_samples_per_second": 31.459, "eval_steps_per_second": 0.492, "total_flos": 0.0, "train_loss": 0.0, "train_runtime": 20.8147, "train_samples": 3438778, "train_samples_per_second": 165208.979, "train_steps_per_second": 1290.673 }