| [{"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}, {"loss": 7.649, "learning_rate": 0.0002, "epoch": 1.08, "step": 125}, {"loss": 7.2697, "learning_rate": 0.0002, "epoch": 1.29, "step": 150}, {"loss": 7.2826, "learning_rate": 0.0002, "epoch": 1.51, "step": 175}, {"loss": 7.3271, "learning_rate": 0.0002, "epoch": 1.72, "step": 200}, {"loss": 7.044, "learning_rate": 0.0002, "epoch": 1.94, "step": 225}, {"loss": 6.8532, "learning_rate": 0.0002, "epoch": 2.16, "step": 250}, {"loss": 6.7007, "learning_rate": 0.0002, "epoch": 2.37, "step": 275}, {"loss": 6.9196, "learning_rate": 0.0002, "epoch": 2.59, "step": 300}, {"loss": 6.7398, "learning_rate": 0.0002, "epoch": 2.8, "step": 325}, {"train_runtime": 1038.0672, "train_samples_per_second": 1.332, "train_steps_per_second": 0.335, "total_flos": 7131025026514944.0, "train_loss": 7.810453656076015, "epoch": 3.0, "step": 348}] |