{ "epoch": 2.0, "eval_logits/chosen": -2.557917594909668, "eval_logits/rejected": -2.551140069961548, "eval_logps/chosen": -108.47079467773438, "eval_logps/rejected": -123.29180908203125, "eval_loss": 0.6549217700958252, "eval_rewards/accuracies": 0.6194238066673279, "eval_rewards/chosen": -0.4975888729095459, "eval_rewards/margins": 0.1035279631614685, "eval_rewards/rejected": -0.6011168956756592, "eval_runtime": 383.2884, "eval_samples": 4304, "eval_samples_per_second": 11.229, "eval_steps_per_second": 1.404, "total_flos": 0.0, "train_loss": 0.6539956355489261, "train_runtime": 95357.4081, "train_samples": 92858, "train_samples_per_second": 1.948, "train_steps_per_second": 0.122 }