{ "epoch": 2.0, "eval_logits/chosen": -2.3789620399475098, "eval_logits/rejected": -2.3597521781921387, "eval_logps/chosen": -80.83098602294922, "eval_logps/rejected": -96.45763397216797, "eval_loss": 0.6398673057556152, "eval_rewards/accuracies": 0.3333333432674408, "eval_rewards/chosen": -0.23755605518817902, "eval_rewards/margins": 0.33684492111206055, "eval_rewards/rejected": -0.5744009017944336, "eval_runtime": 113.9474, "eval_samples": 2000, "eval_samples_per_second": 17.552, "eval_steps_per_second": 0.553, "total_flos": 0.0, "train_loss": 0.5773687552039822, "train_runtime": 2519.8607, "train_samples": 6113, "train_samples_per_second": 4.852, "train_steps_per_second": 0.076 }