{ "epoch": 1.971563981042654, "eval_logits/chosen": 97.58919525146484, "eval_logits/rejected": 91.993408203125, "eval_logps/chosen": -450.8316955566406, "eval_logps/rejected": -483.3000183105469, "eval_loss": 0.47516268491744995, "eval_rewards/accuracies": 0.75, "eval_rewards/chosen": -4.358173370361328, "eval_rewards/margins": 1.7032774686813354, "eval_rewards/rejected": -6.061450958251953, "eval_runtime": 119.5637, "eval_samples": 750, "eval_samples_per_second": 6.273, "eval_steps_per_second": 0.201, "total_flos": 0.0, "train_loss": 0.4319001900462004, "train_runtime": 2177.8844, "train_samples": 6750, "train_samples_per_second": 6.199, "train_steps_per_second": 0.048 }