{ "epoch": 0.9990600241708071, "eval_logits/chosen": -20.56425666809082, "eval_logits/rejected": -20.5841007232666, "eval_logps/chosen": -448.48443603515625, "eval_logps/rejected": -537.9843139648438, "eval_loss": 0.44997087121009827, "eval_rewards/accuracies": 0.7581967115402222, "eval_rewards/chosen": -2.6815857887268066, "eval_rewards/margins": 0.9758842587471008, "eval_rewards/rejected": -3.657470226287842, "eval_runtime": 93.5582, "eval_samples": 1941, "eval_samples_per_second": 20.746, "eval_steps_per_second": 1.304, "total_flos": 0.0, "train_loss": 0.5369526706716066, "train_runtime": 9531.2046, "train_samples": 59569, "train_samples_per_second": 6.25, "train_steps_per_second": 0.049 }