{ "epoch": 3.0, "eval_logits/chosen": -2.731050491333008, "eval_logits/rejected": -2.7048842906951904, "eval_logps/chosen": -183.7933349609375, "eval_logps/rejected": -201.51939392089844, "eval_loss": 0.5440468788146973, "eval_rewards/accuracies": 0.71875, "eval_rewards/chosen": -2.391056537628174, "eval_rewards/margins": 1.7549664974212646, "eval_rewards/rejected": -4.146022796630859, "eval_runtime": 125.4394, "eval_samples_per_second": 16.287, "eval_steps_per_second": 0.255, "total_flos": 2546799910846464.0, "train_loss": 0.30356262255184074, "train_runtime": 7672.2284, "train_samples_per_second": 7.189, "train_steps_per_second": 0.028 }