[ { "step": 0, "val_loss": 5.653509521484375, "tok_per_s": 0.0 }, { "step": 0, "train_loss": 5.5814666748046875, "lr": 1e-06, "grad_norm": 13.262894322262873 }, { "step": 400, "train_loss": 2.416318416595459, "lr": 0.00040100000000000004, "grad_norm": 0.6385184898864017 }, { "step": 500, "val_loss": 3.082964277267456, "tok_per_s": 7353.034710926345 }, { "step": 800, "train_loss": 1.6120072603225708, "lr": 0.0008010000000000001, "grad_norm": 0.7084504426978477 }, { "step": 1000, "val_loss": 3.0517220973968504, "tok_per_s": 7422.438347837392 }, { "step": 1200, "train_loss": 1.5758367776870728, "lr": 0.000988964669915361, "grad_norm": 0.606163267395569 }, { "step": 1500, "val_loss": 2.738486385345459, "tok_per_s": 7446.004210597483 }, { "step": 1600, "train_loss": 1.3207018375396729, "lr": 0.0009042005118087267, "grad_norm": 0.5098235841908811 }, { "step": 2000, "val_loss": 2.8913249254226683, "tok_per_s": 7457.7868950539005 }, { "step": 2000, "train_loss": 1.0848292112350464, "lr": 0.0007495464131639923, "grad_norm": 0.43657336874306774 }, { "step": 2400, "train_loss": 1.086487889289856, "lr": 0.0005517434726252113, "grad_norm": 0.41061234194201285 }, { "step": 2500, "val_loss": 2.8504832863807676, "tok_per_s": 7464.902119770951 }, { "step": 2800, "train_loss": 1.0458492040634155, "lr": 0.00034499361559483973, "grad_norm": 0.38063624390350104 }, { "step": 3000, "val_loss": 2.5975316882133486, "tok_per_s": 7469.624347383343 }, { "step": 3200, "train_loss": 1.2963083982467651, "lr": 0.00016504577061691466, "grad_norm": 0.554473536775391 }, { "step": 3500, "val_loss": 2.753005313873291, "tok_per_s": 7472.654569796267 }, { "step": 3600, "train_loss": 1.0354111194610596, "lr": 4.301455486296946e-05, "grad_norm": 0.4133181698759571 }, { "step": 4000, "val_loss": 2.771369421482086, "tok_per_s": 7475.274380762689 }, { "step": 4000, "train_loss": 1.1188071966171265, "lr": 2.741556527352529e-10, "grad_norm": 0.4136691179164048 } ]