{ "epoch": 1.0, "eval_logits/chosen": 98.25546264648438, "eval_logits/rejected": 98.2234878540039, "eval_logps/chosen": -32.8620491027832, "eval_logps/rejected": -36.65834426879883, "eval_loss": 0.6803030967712402, "eval_rewards/accuracies": 0.5186877250671387, "eval_rewards/chosen": -0.0837748572230339, "eval_rewards/margins": 0.05458855256438255, "eval_rewards/rejected": -0.13836342096328735, "eval_runtime": 103.6862, "eval_samples": 343, "eval_samples_per_second": 3.308, "eval_steps_per_second": 0.415, "train_loss": 0.6168378699909557, "train_runtime": 2560.1818, "train_samples": 3079, "train_samples_per_second": 1.203, "train_steps_per_second": 0.15 }