{"train/loss": 3.4684, "train/grad_norm": 41.386260986328125, "train/learning_rate": 1.761003841513674e-05, "train/epoch": 0.74, "train/global_step": 9220, "_timestamp": 1712918933.531621, "_runtime": 11289.023902893066, "_step": 460} |
{"train/loss": 3.4684, "train/grad_norm": 41.386260986328125, "train/learning_rate": 1.761003841513674e-05, "train/epoch": 0.74, "train/global_step": 9220, "_timestamp": 1712918933.531621, "_runtime": 11289.023902893066, "_step": 460} |