{ "epoch": 1.0, "eval_logits/chosen": -1.3924791812896729, "eval_logits/rejected": 1.0068244934082031, "eval_logps/chosen": -385.703857421875, "eval_logps/rejected": -374.45843505859375, "eval_loss": 0.5347221493721008, "eval_rewards/accuracies": 0.6527777910232544, "eval_rewards/chosen": -0.8760086297988892, "eval_rewards/margins": 0.9213289618492126, "eval_rewards/rejected": -1.7973376512527466, "eval_runtime": 61.4466, "eval_samples": 568, "eval_samples_per_second": 9.244, "eval_steps_per_second": 0.293, "train_loss": 0.004050073670405967, "train_runtime": 90.6565, "train_samples": 19572, "train_samples_per_second": 215.892, "train_steps_per_second": 3.375 }