{"train/loss": 3.5286, "train/grad_norm": 29.236722946166992, "train/learning_rate": 2.7883845626740046e-05, "train/epoch": 0.31, "train/global_step": 3920, "_timestamp": 1712912441.055419, "_runtime": 4796.547700881958, "_step": 195} |
{"train/loss": 3.5286, "train/grad_norm": 29.236722946166992, "train/learning_rate": 2.7883845626740046e-05, "train/epoch": 0.31, "train/global_step": 3920, "_timestamp": 1712912441.055419, "_runtime": 4796.547700881958, "_step": 195} |