| [{"loss": 1.9488, "learning_rate": 0.0002, "epoch": 0.13, "step": 20}, {"loss": 2.3923, "learning_rate": 0.0002, "epoch": 0.26, "step": 40}, {"loss": 1.8454, "learning_rate": 0.0002, "epoch": 0.39, "step": 60}, {"loss": 2.2645, "learning_rate": 0.0002, "epoch": 0.52, "step": 80}, {"loss": 1.8485, "learning_rate": 0.0002, "epoch": 0.65, "step": 100}, {"loss": 2.1069, "learning_rate": 0.0002, "epoch": 0.78, "step": 120}, {"loss": 1.9237, "learning_rate": 0.0002, "epoch": 0.91, "step": 140}, {"train_runtime": 50.2668, "train_samples_per_second": 9.171, "train_steps_per_second": 3.064, "total_flos": 2338059743748096.0, "train_loss": 2.065241442098246, "epoch": 1.0, "step": 154}] |