1{"step": 0, "loss": 4.882978916168213, "lr": 0.0001, "grad_norm": 2.631913661956787, "tokens": 1708, "tok_per_s": 12605.103772273553, "t": 0.71}2{"step": 50, "loss": 2.508582353591919, "lr": 0.0008305704108364302, "grad_norm": 0.9815729856491089, "tokens": 94447, "tok_per_s": 88797.80277866195, "t": 1.64}3{"step": 100, "loss": 1.909483790397644, "lr": 0.0003547523173970989, "grad_norm": 1.143792748451233, "tokens": 187214, "tok_per_s": 95544.55275035149, "t": 2.54}4{"step": 149, "loss": 1.5540279150009155, "lr": 0.00010011329427587207, "grad_norm": 1.4631657600402832, "tokens": 279708, "tok_per_s": 96143.08211684186, "t": 3.49}5{"step": 149, "val_loss_b0": 1.6609648618492778, "t": 3.5}6{"step": 149, "checkpoint_sha256": "fff6ca1bd1170d08423861d53f6e4c270ed2c20a4359ccfe7b8eb78e091d694b", "t": 3.51}7