{ "epoch": 2.983957219251337, "eval_logits/chosen": -2.377612590789795, "eval_logits/rejected": -2.3392257690429688, "eval_logps/chosen": -251.21542358398438, "eval_logps/rejected": -216.66961669921875, "eval_loss": 0.5004006028175354, "eval_rewards/accuracies": 0.800595223903656, "eval_rewards/chosen": 0.6966643929481506, "eval_rewards/margins": 2.7116470336914062, "eval_rewards/rejected": -2.014982223510742, "eval_runtime": 176.0961, "eval_samples_per_second": 15.105, "eval_steps_per_second": 0.239, "total_flos": 3289753017384960.0, "train_loss": 0.3301437693684759, "train_runtime": 10405.088, "train_samples_per_second": 6.9, "train_steps_per_second": 0.027 }