{ "ewc_loss": -85.5, "ewc_loss_diag": 0.000370025634765625, "ewc_loss_parallel": -0.08544921875, "total_flos": 5.62815163329864e+19, "train_loss": 0.0, "train_runtime": 1304.047, "train_samples": 125770, "train_samples_per_second": 289.338, "train_steps_per_second": 18.084 }