{ "epoch": 0.99, "eval_logits/chosen": 85.92010498046875, "eval_logits/rejected": 78.73693084716797, "eval_logps/chosen": -710.1602172851562, "eval_logps/rejected": -827.8626098632812, "eval_loss": 0.4769742786884308, "eval_rewards/accuracies": 0.7083333134651184, "eval_rewards/chosen": 0.8210906982421875, "eval_rewards/margins": 1.0284124612808228, "eval_rewards/rejected": -0.20732170343399048, "eval_runtime": 54.5772, "eval_samples": 750, "eval_samples_per_second": 13.742, "eval_steps_per_second": 0.44 }