{ "epoch": 1.0, "eval_logits/chosen": 98.74346160888672, "eval_logits/rejected": 98.71293640136719, "eval_logps/chosen": -32.52199172973633, "eval_logps/rejected": -36.13157272338867, "eval_loss": 0.9996863603591919, "eval_rewards/accuracies": 0.5394518375396729, "eval_rewards/chosen": -0.04729102551937103, "eval_rewards/margins": 0.05173712968826294, "eval_rewards/rejected": -0.09902816265821457, "eval_runtime": 103.8083, "eval_samples": 343, "eval_samples_per_second": 3.304, "eval_steps_per_second": 0.414, "train_loss": 0.746250953302755, "train_runtime": 2556.1232, "train_samples": 3079, "train_samples_per_second": 1.205, "train_steps_per_second": 0.151 }