{"train/loss": 0.6769, "train/grad_norm": 18.890430450439453, "train/learning_rate": 9.885931558935361e-07, "train/epoch": 3.0, "train/global_step": 6312, "_timestamp": 1720025048.2287927, "_runtime": 5856.53853559494, "_step": 15, "eval/loss": 1.2779136896133423, "eval/accuracy": 0.5880477146569033, "eval/runtime": 129.4954, "eval/samples_per_second": 65.385, "eval/steps_per_second": 4.093, "train_runtime": 5880.4469, "train_samples_per_second": 17.171, "train_steps_per_second": 1.073, "total_flos": 2981042653335552.0, "train_loss": 0.9554222430868596}