| [ |
| { |
| "stage": "pretrain", |
| "step": 100, |
| "tokens": 52428800, |
| "wall_s": 1420.0, |
| "loss": 7.3191, |
| "grad_norm": 1.059, |
| "lr": 5.9399999999999994e-05, |
| "tok_per_s": 36921 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 200, |
| "tokens": 104857600, |
| "wall_s": 2843.1, |
| "loss": 6.1484, |
| "grad_norm": 1.084, |
| "lr": 0.00011939999999999999, |
| "tok_per_s": 36881 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 300, |
| "tokens": 157286400, |
| "wall_s": 4285.5, |
| "loss": 5.7304, |
| "grad_norm": 1.385, |
| "lr": 0.00017939999999999997, |
| "tok_per_s": 36702 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 400, |
| "tokens": 209715200, |
| "wall_s": 5708.5, |
| "loss": 5.5112, |
| "grad_norm": 1.089, |
| "lr": 0.00023939999999999996, |
| "tok_per_s": 36738 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 500, |
| "tokens": 262144000, |
| "wall_s": 7148.0, |
| "loss": 4.8949, |
| "grad_norm": 0.888, |
| "lr": 0.0002994, |
| "tok_per_s": 36674 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 600, |
| "tokens": 314572800, |
| "wall_s": 8570.8, |
| "loss": 4.904, |
| "grad_norm": 0.96, |
| "lr": 0.00029995826888796654, |
| "tok_per_s": 36703 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 700, |
| "tokens": 367001600, |
| "wall_s": 10010.9, |
| "loss": 4.6172, |
| "grad_norm": 0.857, |
| "lr": 0.0002998314102112406, |
| "tok_per_s": 36660 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 800, |
| "tokens": 419430400, |
| "wall_s": 11433.9, |
| "loss": 4.4615, |
| "grad_norm": 0.706, |
| "lr": 0.0002996194955214142, |
| "tok_per_s": 36683 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 900, |
| "tokens": 471859200, |
| "wall_s": 12875.0, |
| "loss": 4.2078, |
| "grad_norm": 0.571, |
| "lr": 0.0002993226514568634, |
| "tok_per_s": 36649 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1000, |
| "tokens": 524288000, |
| "wall_s": 14298.0, |
| "loss": 4.0421, |
| "grad_norm": 0.435, |
| "lr": 0.0002989410554090198, |
| "tok_per_s": 36669 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1100, |
| "tokens": 576716800, |
| "wall_s": 15737.7, |
| "loss": 3.9573, |
| "grad_norm": 0.607, |
| "lr": 0.0002984749354163635, |
| "tok_per_s": 36645 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1200, |
| "tokens": 629145600, |
| "wall_s": 17160.5, |
| "loss": 3.957, |
| "grad_norm": 0.538, |
| "lr": 0.000297924570028149, |
| "tok_per_s": 36662 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1300, |
| "tokens": 681574400, |
| "wall_s": 18600.7, |
| "loss": 3.6969, |
| "grad_norm": 0.43, |
| "lr": 0.0002972902881379466, |
| "tok_per_s": 36642 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1400, |
| "tokens": 734003200, |
| "wall_s": 20023.5, |
| "loss": 3.9048, |
| "grad_norm": 0.373, |
| "lr": 0.0002965724687870983, |
| "tok_per_s": 36657 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1500, |
| "tokens": 786432000, |
| "wall_s": 21463.8, |
| "loss": 3.2995, |
| "grad_norm": 0.403, |
| "lr": 0.0002957715409382067, |
| "tok_per_s": 36640 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1600, |
| "tokens": 838860800, |
| "wall_s": 22886.7, |
| "loss": 3.9037, |
| "grad_norm": 0.377, |
| "lr": 0.00029488798321878956, |
| "tok_per_s": 36653 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1700, |
| "tokens": 891289600, |
| "wall_s": 24328.5, |
| "loss": 3.267, |
| "grad_norm": 0.398, |
| "lr": 0.00029392232363525717, |
| "tok_per_s": 36636 |
| }, |
| { |
| "stage": "pretrain", |
| "step": 1800, |
| "tokens": 943718400, |
| "wall_s": 25751.5, |
| "loss": 3.4073, |
| "grad_norm": 0.355, |
| "lr": 0.0002928751392573797, |
| "tok_per_s": 36647 |
| } |
| ] |