[ { "step": 0, "val_loss": 5.619070100784302, "tok_per_s": 0.0 }, { "step": 0, "train_loss": 5.616189956665039, "lr": 1e-06, "grad_norm": 29.273247877751935 }, { "step": 400, "train_loss": 2.6516408920288086, "lr": 0.00040100000000000004, "grad_norm": 1.352886640052276 }, { "step": 500, "val_loss": 3.729518210887909, "tok_per_s": 9780.942111616952 }, { "step": 800, "train_loss": 2.1480326652526855, "lr": 0.0008010000000000001, "grad_norm": 1.4094370777928795 }, { "step": 1000, "val_loss": 3.7294750928878786, "tok_per_s": 12756.35488794051 }, { "step": 1200, "train_loss": 2.240513563156128, "lr": 0.000988964669915361, "grad_norm": 0.8976523252261448 }, { "step": 1500, "val_loss": 3.4839155077934265, "tok_per_s": 14198.011686047617 }, { "step": 1600, "train_loss": 1.931168556213379, "lr": 0.0009042005118087267, "grad_norm": 0.7024651656325952 }, { "step": 2000, "val_loss": 3.584827196598053, "tok_per_s": 15103.588029890892 }, { "step": 2000, "train_loss": 1.7497514486312866, "lr": 0.0007495464131639923, "grad_norm": 0.7033821207986488 }, { "step": 2400, "train_loss": 1.6890695095062256, "lr": 0.0005517434726252113, "grad_norm": 0.5302752272105545 }, { "step": 2500, "val_loss": 3.5327754378318788, "tok_per_s": 15689.552746711572 }, { "step": 2800, "train_loss": 1.6101696491241455, "lr": 0.00034499361559483973, "grad_norm": 0.5084148331381609 }, { "step": 3000, "val_loss": 3.376665234565735, "tok_per_s": 16068.29102371795 }, { "step": 3200, "train_loss": 1.9343514442443848, "lr": 0.00016504577061691466, "grad_norm": 0.6363576595902085 }, { "step": 3500, "val_loss": 3.4783490896224976, "tok_per_s": 16377.076453772866 }, { "step": 3600, "train_loss": 1.604689121246338, "lr": 4.301455486296946e-05, "grad_norm": 0.5709548462524181 }, { "step": 4000, "val_loss": 3.490683543682098, "tok_per_s": 16631.861465038073 }, { "step": 4000, "train_loss": 1.6441144943237305, "lr": 2.741556527352529e-10, "grad_norm": 0.5403057249666863 } ]