{ "epoch": 1.0, "eval_logits/chosen": -1.404586672782898, "eval_logits/rejected": -1.3435096740722656, "eval_logps/chosen": -788.7391357421875, "eval_logps/rejected": -854.9130859375, "eval_loss": 0.9015858173370361, "eval_rewards/accuracies": 0.656000018119812, "eval_rewards/chosen": -5.041457653045654, "eval_rewards/margins": 0.9218845367431641, "eval_rewards/margins_max": 4.525033473968506, "eval_rewards/margins_min": -2.841050386428833, "eval_rewards/margins_std": 2.5078797340393066, "eval_rewards/rejected": -5.96334171295166, "eval_runtime": 428.0105, "eval_samples": 2000, "eval_samples_per_second": 4.673, "eval_steps_per_second": 0.292, "train_loss": 0.3073710792501208, "train_runtime": 4217.5244, "train_samples": 5678, "train_samples_per_second": 1.346, "train_steps_per_second": 0.084 }