[ { "step": 0, "val_loss": 5.58193359375, "tok_per_s": 0.0 }, { "step": 0, "train_loss": 5.6109619140625, "lr": 1e-06, "grad_norm": 9.888680762594152 }, { "step": 400, "train_loss": 2.446561336517334, "lr": 0.00040100000000000004, "grad_norm": 0.8258977142160494 }, { "step": 500, "val_loss": 3.2868219375610352, "tok_per_s": 2054.886555523649 }, { "step": 800, "train_loss": 1.657127857208252, "lr": 0.0008010000000000001, "grad_norm": 0.7207793043890298 }, { "step": 1000, "val_loss": 3.0127882957458496, "tok_per_s": 2075.676320022549 }, { "step": 1200, "train_loss": 1.439911127090454, "lr": 0.000988964669915361, "grad_norm": 0.6918267287873078 }, { "step": 1500, "val_loss": 3.1109124064445495, "tok_per_s": 2082.604405546491 }, { "step": 1600, "train_loss": 1.3208760023117065, "lr": 0.0009042005118087267, "grad_norm": 0.46964749288958346 }, { "step": 2000, "val_loss": 2.9630029678344725, "tok_per_s": 2086.1097494803685 }, { "step": 2000, "train_loss": 1.2361996173858643, "lr": 0.0007495464131639923, "grad_norm": 0.4868616595311802 }, { "step": 2400, "train_loss": 1.375333547592163, "lr": 0.0005517434726252113, "grad_norm": 0.5504912286387305 }, { "step": 2500, "val_loss": 3.0222906470298767, "tok_per_s": 2088.2879672418094 }, { "step": 2800, "train_loss": 0.8583204746246338, "lr": 0.00034499361559483973, "grad_norm": 0.3340267158695349 }, { "step": 3000, "val_loss": 2.819178342819214, "tok_per_s": 2089.7442111843507 }, { "step": 3200, "train_loss": 1.0901888608932495, "lr": 0.00016504577061691466, "grad_norm": 0.41001456695044497 }, { "step": 3500, "val_loss": 2.7360673546791077, "tok_per_s": 2090.7246422699573 }, { "step": 3600, "train_loss": 1.182705044746399, "lr": 4.301455486296946e-05, "grad_norm": 0.533361263737973 }, { "step": 4000, "val_loss": 2.8145708560943605, "tok_per_s": 2091.511885105994 }, { "step": 4000, "train_loss": 0.9793441891670227, "lr": 2.741556527352529e-10, "grad_norm": 0.367307059953119 } ]