| [{"loss": 13.1588, "learning_rate": 0.0002, "epoch": 0.22, "step": 25}, {"loss": 9.279, "learning_rate": 0.0002, "epoch": 0.43, "step": 50}, {"loss": 8.3847, "learning_rate": 0.0002, "epoch": 0.65, "step": 75}, {"loss": 8.0383, "learning_rate": 0.0002, "epoch": 0.86, "step": 100}, {"train_runtime": 305.8967, "train_samples_per_second": 1.507, "train_steps_per_second": 0.379, "total_flos": 2373225471000576.0, "train_loss": 9.44900262766871, "epoch": 1.0, "step": 116}] |