{ "epoch": 1.0, "eval_logits/chosen": 98.63704681396484, "eval_logits/rejected": 98.61363220214844, "eval_logps/chosen": -32.56790542602539, "eval_logps/rejected": -36.25141525268555, "eval_loss": 0.7417604923248291, "eval_rewards/accuracies": 0.5510797500610352, "eval_rewards/chosen": -0.08731049299240112, "eval_rewards/margins": 0.11211014539003372, "eval_rewards/rejected": -0.19942064583301544, "eval_runtime": 103.7829, "eval_samples": 343, "eval_samples_per_second": 3.305, "eval_steps_per_second": 0.414, "train_loss": 0.5948986065852178, "train_runtime": 2557.7017, "train_samples": 3079, "train_samples_per_second": 1.204, "train_steps_per_second": 0.151 }