{ "epoch": 1.0, "eval_kl": 0.0, "eval_logits/chosen": -141123088.0, "eval_logits/rejected": -139890512.0, "eval_logps/chosen": -287.08896875, "eval_logps/rejected": -293.79315625, "eval_loss": 0.3648396134376526, "eval_rewards/chosen": 0.0766905059814453, "eval_rewards/margins": 2.760806716918945, "eval_rewards/rejected": -2.6841162109375, "eval_runtime": 92.6279, "eval_samples": 4000, "eval_samples_per_second": 43.184, "eval_steps_per_second": 1.349, "total_flos": 0.0, "train_loss": 1.5426912418834826, "train_runtime": 5367.6535, "train_samples": 122270, "train_samples_per_second": 22.779, "train_steps_per_second": 0.178 }