[ { "step": 0, "val_loss": 5.640983986854553, "tok_per_s": 0.0 }, { "step": 0, "train_loss": 5.634721755981445, "lr": 1e-06, "grad_norm": 12.607086436558875 }, { "step": 400, "train_loss": 2.629965305328369, "lr": 0.00040100000000000004, "grad_norm": 1.66587478767584 }, { "step": 500, "val_loss": 3.769664227962494, "tok_per_s": 3042.8231135326296 }, { "step": 800, "train_loss": 2.148674964904785, "lr": 0.0008010000000000001, "grad_norm": 1.1605165896392973 }, { "step": 1000, "val_loss": 3.7590306758880616, "tok_per_s": 5612.427240002938 }, { "step": 1200, "train_loss": 2.2364728450775146, "lr": 0.000988964669915361, "grad_norm": 0.9972622909600706 }, { "step": 1500, "val_loss": 3.4896115183830263, "tok_per_s": 7818.960460836108 }, { "step": 1600, "train_loss": 1.9360148906707764, "lr": 0.0009042005118087267, "grad_norm": 0.7311790450787055 }, { "step": 2000, "val_loss": 3.6740593791007994, "tok_per_s": 9761.97235873411 }, { "step": 2000, "train_loss": 1.753335952758789, "lr": 0.0007495464131639923, "grad_norm": 0.7384131696379053 }, { "step": 2400, "train_loss": 1.6950229406356812, "lr": 0.0005517434726252113, "grad_norm": 0.5669060392883613 }, { "step": 2500, "val_loss": 3.5427012920379637, "tok_per_s": 11471.654518421445 }, { "step": 2800, "train_loss": 1.6302014589309692, "lr": 0.00034499361559483973, "grad_norm": 0.5795686377318386 }, { "step": 3000, "val_loss": 3.404037892818451, "tok_per_s": 12984.195805231486 }, { "step": 3200, "train_loss": 1.938350796699524, "lr": 0.00016504577061691466, "grad_norm": 0.6872694114985712 }, { "step": 3500, "val_loss": 3.5261181354522706, "tok_per_s": 14324.63255784625 }, { "step": 3600, "train_loss": 1.614745855331421, "lr": 4.301455486296946e-05, "grad_norm": 0.6007246302215206 }, { "step": 4000, "val_loss": 3.5474262833595276, "tok_per_s": 15547.294000883148 }, { "step": 4000, "train_loss": 1.6616897583007812, "lr": 2.741556527352529e-10, "grad_norm": 0.6082381440308673 } ]