{ "ewc_loss": 0.023193359375, "ewc_loss_diag": 0.0001049041748046875, "ewc_loss_parallel": 1.2636184692382812e-05, "total_flos": 5.751448627479105e+19, "train_loss": 0.3408017477382914, "train_runtime": 50265.1743, "train_samples": 125770, "train_samples_per_second": 7.506, "train_steps_per_second": 0.469 }