{ "epoch": 2.0, "eval_logits/chosen": -2.444159746170044, "eval_logits/rejected": -2.178493022918701, "eval_logps/chosen": -174.84832763671875, "eval_logps/rejected": -98.5013198852539, "eval_loss": 0.6931471228599548, "eval_rewards/accuracies": 0.0, "eval_rewards/chosen": 0.0, "eval_rewards/margins": 0.0, "eval_rewards/rejected": 0.0, "eval_runtime": 0.4442, "eval_samples": 50, "eval_samples_per_second": 112.556, "eval_steps_per_second": 2.251 }