{ "epoch": 0.9997382884061764, "eval_logits/chosen": -14.105589866638184, "eval_logits/rejected": -14.292818069458008, "eval_logps/chosen": -375.1571960449219, "eval_logps/rejected": -407.44989013671875, "eval_loss": 0.5276930332183838, "eval_rewards/accuracies": 0.6880000233650208, "eval_rewards/chosen": -0.6083627939224243, "eval_rewards/margins": 0.6220458149909973, "eval_rewards/rejected": -1.2304086685180664, "eval_runtime": 148.4787, "eval_samples": 2000, "eval_samples_per_second": 13.47, "eval_steps_per_second": 0.842, "total_flos": 0.0, "train_loss": 0.560625178402007, "train_runtime": 12630.0326, "train_samples": 61134, "train_samples_per_second": 4.84, "train_steps_per_second": 0.076 }