| { | |
| "base_model": "Qwen/Qwen3-8B", | |
| "base_revision": "b968826d9c46dd6066d109eabc6255188de91218", | |
| "data_format": "qwen3_8b/v1", | |
| "optimizer": "AdamW", | |
| "seed": 42, | |
| "epochs": 1, | |
| "lr": 1e-05, | |
| "weight_decay": 0.01, | |
| "max_grad_norm": 1.0, | |
| "pretrain_train_samples": 72000, | |
| "pretrain_validation_samples": 8000, | |
| "pretrain_grad_accum_steps": 8, | |
| "finetune_train_samples": 11491, | |
| "finetune_validation_samples": 1642, | |
| "finetune_grad_accum_steps": 1 | |
| } | |