[ { "step": 0, "val_loss": 5.574858093261719, "tok_per_s": 0.0 }, { "step": 0, "train_loss": 5.5917205810546875, "lr": 1e-06, "grad_norm": 12.717687525126948 }, { "step": 400, "train_loss": 2.40862774848938, "lr": 0.00040100000000000004, "grad_norm": 0.6444747412529727 }, { "step": 500, "val_loss": 2.9989272117614747, "tok_per_s": 3718.2248728935924 }, { "step": 800, "train_loss": 1.5925631523132324, "lr": 0.0008010000000000001, "grad_norm": 0.55659908126474 }, { "step": 1000, "val_loss": 2.9269163846969604, "tok_per_s": 3750.517035850887 }, { "step": 1200, "train_loss": 1.52901291847229, "lr": 0.000988964669915361, "grad_norm": 0.495081136965696 }, { "step": 1500, "val_loss": 2.7253864288330076, "tok_per_s": 3761.4818781802555 }, { "step": 1600, "train_loss": 1.3101574182510376, "lr": 0.0009042005118087267, "grad_norm": 0.5471434485914135 }, { "step": 2000, "val_loss": 2.8566264510154724, "tok_per_s": 3766.8687186069046 }, { "step": 2000, "train_loss": 1.0662428140640259, "lr": 0.0007495464131639923, "grad_norm": 0.40414115602629586 }, { "step": 2400, "train_loss": 1.0698206424713135, "lr": 0.0005517434726252113, "grad_norm": 0.3638077828799298 }, { "step": 2500, "val_loss": 2.8301284432411196, "tok_per_s": 3770.1451769209293 }, { "step": 2800, "train_loss": 1.0058163404464722, "lr": 0.00034499361559483973, "grad_norm": 0.35350228406513934 }, { "step": 3000, "val_loss": 2.6090492963790894, "tok_per_s": 3772.2713155786982 }, { "step": 3200, "train_loss": 1.2697056531906128, "lr": 0.00016504577061691466, "grad_norm": 0.4867203515384807 }, { "step": 3500, "val_loss": 2.7727127075195312, "tok_per_s": 3773.412703899254 }, { "step": 3600, "train_loss": 1.0147331953048706, "lr": 4.301455486296946e-05, "grad_norm": 0.3598032306041595 }, { "step": 4000, "val_loss": 2.7373061776161194, "tok_per_s": 3774.2970880066314 }, { "step": 4000, "train_loss": 1.102695345878601, "lr": 2.741556527352529e-10, "grad_norm": 0.36774689673228605 } ]