| { |
| "seed": 42, |
| "debug": false, |
| "wandb": true, |
| "pretrained_model_path": "pretrained/new/mae_base_mask0.9_dec512d2b_seq.ckpt", |
| "datamodule": { |
| "batch_size": 64, |
| "pin_memory": true, |
| "num_workers": 12, |
| "train_transform": { |
| "_target_": "tedbench.data.transform.Compose", |
| "transforms": [ |
| { |
| "_target_": "tedbench.data.transform.RandomCrop", |
| "size": 512 |
| }, |
| { |
| "_target_": "tedbench.data.transform.RandomNoise", |
| "std": 0.2, |
| "mean": 0.0 |
| } |
| ] |
| }, |
| "_target_": "tedbench.data.TEDLightningDataset", |
| "root": "./datasets/ted", |
| "dataset_name": "ted" |
| }, |
| "trainer": { |
| "_target_": "pytorch_lightning.Trainer", |
| "accelerator": "auto", |
| "max_steps": 18300, |
| "strategy": "auto", |
| "devices": "auto", |
| "default_root_dir": "${logs.path}", |
| "num_sanity_val_steps": 0, |
| "accumulate_grad_batches": 2 |
| }, |
| "train": { |
| "optimizer": { |
| "_target_": "torch.optim.AdamW", |
| "lr": 0.0016, |
| "weight_decay": 0.1, |
| "betas": [ |
| 0.9, |
| 0.95 |
| ] |
| }, |
| "lr_scheduler": { |
| "_target_": "tedbench.lr_schedulers.get_cosine_schedule_with_warmup", |
| "warmup_steps": 1830, |
| "max_steps": "${trainer.max_steps}" |
| }, |
| "loss": { |
| "_target_": "torch.nn.CrossEntropyLoss", |
| "label_smoothing": 0.0 |
| }, |
| "llrd": 0.8, |
| "ckpt_path": null |
| }, |
| "model": { |
| "_target_": "tedbench.model.miae_encoder_model", |
| "name": "miae_b", |
| "num_classes": 965, |
| "avg_pool": false, |
| "use_seq_input": true |
| }, |
| "logs": { |
| "prefix": "logs/finetune/${datamodule.dataset_name}/${seed}", |
| "path": "${logs.prefix}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}" |
| }, |
| "mode": {}, |
| "_model_class": "miae_classifier" |
| } |
