{ "epoch": 1.0, "eval_logits/chosen": -2.8232436180114746, "eval_logits/rejected": -2.8211076259613037, "eval_logps/chosen": -31.491378784179688, "eval_logps/rejected": -35.14382553100586, "eval_loss": 0.9104546904563904, "eval_rewards/accuracies": 0.5514950156211853, "eval_rewards/chosen": -0.08357102423906326, "eval_rewards/margins": 0.09469697624444962, "eval_rewards/rejected": -0.17826800048351288, "eval_runtime": 112.9595, "eval_samples": 343, "eval_samples_per_second": 3.036, "eval_steps_per_second": 0.381, "train_loss": 0.7203964704042906, "train_runtime": 2720.5927, "train_samples": 3079, "train_samples_per_second": 1.132, "train_steps_per_second": 0.142 }