1{"step": 0, "loss": 2.298006296157837, "lr": 0.0001, "grad_norm": 0.09031800925731659, "tokens": 68, "tok_per_s": 162.15141950096879, "t": 0.87}2{"step": 50, "loss": 2.058422088623047, "lr": 0.0007369367558508489, "grad_norm": 0.12141810357570648, "tokens": 4115, "tok_per_s": 302.02736493529886, "t": 14.07}3{"step": 100, "loss": 1.9985322952270508, "lr": 0.00017143591022596844, "grad_norm": 0.21364711225032806, "tokens": 8233, "tok_per_s": 334.57399121717356, "t": 25.06}4{"step": 119, "loss": 2.201204538345337, "lr": 0.00010018351322731485, "grad_norm": 0.20862196385860443, "tokens": 9847, "tok_per_s": 337.68230198090333, "t": 29.61}5{"step": 119, "val_loss_b0": 2.3909947187051004, "val_loss_b1": 2.177954662805316, "val_loss_b2": 2.145720558604975, "val_loss_b4": 2.0783485324903466, "val_loss_b8": 2.0136146983881105, "t": 30.08}6{"step": 119, "checkpoint_sha256": "cd59f80c64ff29b3a0baf145c64778a34c9f6080457eded4e4f6cdda3649aeb2", "t": 30.09}7