{ "ewc_loss": 0.224609375, "ewc_loss_diag": 2.4199485778808594e-05, "ewc_loss_parallel": 0.0002002716064453125, "total_flos": 5.62815163329864e+19, "train_loss": 0.5611200594813073, "train_runtime": 47572.7611, "train_samples": 125770, "train_samples_per_second": 7.931, "train_steps_per_second": 0.496 }