[ { "step": 0, "val_loss": 5.724483394622803, "tok_per_s": 0.0 }, { "step": 0, "train_loss": 5.738528728485107, "lr": 1e-06, "grad_norm": 18.557702700432156 }, { "step": 400, "train_loss": 2.5503506660461426, "lr": 0.00040100000000000004, "grad_norm": 1.5563106453646307 }, { "step": 500, "val_loss": 4.181924271583557, "tok_per_s": 2184.0695229395146 }, { "step": 800, "train_loss": 2.169980049133301, "lr": 0.0008010000000000001, "grad_norm": 1.385430282630754 }, { "step": 1000, "val_loss": 3.9483901262283325, "tok_per_s": 3970.938096122552 }, { "step": 1200, "train_loss": 2.0457634925842285, "lr": 0.000988964669915361, "grad_norm": 1.0112889612874592 }, { "step": 1500, "val_loss": 3.940820741653442, "tok_per_s": 5463.298530973348 }, { "step": 1600, "train_loss": 1.9771353006362915, "lr": 0.0009042005118087267, "grad_norm": 0.8698389811850052 }, { "step": 2000, "val_loss": 3.6034568548202515, "tok_per_s": 6733.318830432771 }, { "step": 2000, "train_loss": 1.9552191495895386, "lr": 0.0007495464131639923, "grad_norm": 0.8105395679074034 }, { "step": 2400, "train_loss": 2.0290591716766357, "lr": 0.0005517434726252113, "grad_norm": 0.7772307357811391 }, { "step": 2500, "val_loss": 3.8027327179908754, "tok_per_s": 7825.7691054805655 }, { "step": 2800, "train_loss": 1.4810876846313477, "lr": 0.00034499361559483973, "grad_norm": 0.5642906609112506 }, { "step": 3000, "val_loss": 3.4605381011962892, "tok_per_s": 8775.98397199023 }, { "step": 3200, "train_loss": 1.6780955791473389, "lr": 0.00016504577061691466, "grad_norm": 0.6131905937913334 }, { "step": 3500, "val_loss": 3.523012411594391, "tok_per_s": 9610.316128988608 }, { "step": 3600, "train_loss": 1.8657923936843872, "lr": 4.301455486296946e-05, "grad_norm": 0.8052576967507755 }, { "step": 4000, "val_loss": 3.5965240597724915, "tok_per_s": 10347.765560997088 }, { "step": 4000, "train_loss": 1.5910844802856445, "lr": 2.741556527352529e-10, "grad_norm": 0.5769667369420309 } ]