{ "epoch": 1.0, "eval_logits/chosen": 98.90196990966797, "eval_logits/rejected": 98.875, "eval_logps/chosen": -32.520835876464844, "eval_logps/rejected": -36.21490478515625, "eval_loss": 0.9721795320510864, "eval_rewards/accuracies": 0.545265793800354, "eval_rewards/chosen": -0.06213000789284706, "eval_rewards/margins": 0.13657446205615997, "eval_rewards/rejected": -0.19870448112487793, "eval_runtime": 103.7342, "eval_samples": 343, "eval_samples_per_second": 3.307, "eval_steps_per_second": 0.415, "train_loss": 0.7616742146479619, "train_runtime": 2551.1965, "train_samples": 3079, "train_samples_per_second": 1.207, "train_steps_per_second": 0.151 }