{ "epoch": 1.0, "eval_logits/chosen": -1.4358036518096924, "eval_logits/rejected": -1.3431825637817383, "eval_logps/chosen": -517.1965942382812, "eval_logps/rejected": -595.2865600585938, "eval_loss": 0.4974534213542938, "eval_rewards/accuracies": 0.7490000128746033, "eval_rewards/chosen": -2.4549365043640137, "eval_rewards/margins": 1.0207281112670898, "eval_rewards/rejected": -3.4756648540496826, "eval_runtime": 206.3812, "eval_samples": 2000, "eval_samples_per_second": 9.691, "eval_steps_per_second": 0.606, "train_loss": 0.5312882837824796, "train_runtime": 19005.9968, "train_samples": 61134, "train_samples_per_second": 3.217, "train_steps_per_second": 0.1 }