| # pytorch_lightning==2.0.2 | |
| seed_everything: true | |
| trainer: | |
| accelerator: gpu | |
| strategy: auto | |
| devices: 1 | |
| num_nodes: 1 | |
| precision: 16-mixed | |
| logger: | |
| class_path: pytorch_lightning.loggers.CSVLogger | |
| init_args: | |
| save_dir: output | |
| name: nuts | |
| version: null | |
| prefix: '' | |
| flush_logs_every_n_steps: 100 | |
| callbacks: null | |
| fast_dev_run: false | |
| max_epochs: null | |
| min_epochs: null | |
| max_steps: 5000 | |
| min_steps: null | |
| max_time: null | |
| limit_train_batches: null | |
| limit_val_batches: null | |
| limit_test_batches: null | |
| limit_predict_batches: null | |
| overfit_batches: 0.0 | |
| val_check_interval: 500 | |
| check_val_every_n_epoch: null | |
| num_sanity_val_steps: null | |
| log_every_n_steps: null | |
| enable_checkpointing: null | |
| enable_progress_bar: null | |
| enable_model_summary: null | |
| accumulate_grad_batches: 1 | |
| gradient_clip_val: null | |
| gradient_clip_algorithm: null | |
| deterministic: null | |
| benchmark: null | |
| inference_mode: true | |
| use_distributed_sampler: true | |
| profiler: null | |
| detect_anomaly: false | |
| barebones: false | |
| plugins: null | |
| sync_batchnorm: false | |
| reload_dataloaders_every_n_epochs: 0 | |
| default_root_dir: null | |
| model: | |
| model_name: vit-b16-224-in21k | |
| optimizer: sgd | |
| lr: 0.01 | |
| betas: | |
| - 0.9 | |
| - 0.999 | |
| momentum: 0.9 | |
| weight_decay: 0.0 | |
| scheduler: cosine | |
| warmup_steps: 500 | |
| mixup_alpha: 0.0 | |
| cutmix_alpha: 0.0 | |
| mix_prob: 1.0 | |
| label_smoothing: 0.0 | |
| weights: null | |
| training_mode: full | |
| lora_r: 16 | |
| lora_alpha: 16 | |
| lora_target_modules: | |
| - query | |
| - value | |
| lora_dropout: 0.0 | |
| lora_bias: none | |
| from_scratch: false | |
| data: | |
| dataset: custom | |
| root: data/ | |
| num_classes: 10 | |
| size: 224 | |
| min_scale: 0.08 | |
| max_scale: 1.0 | |
| flip_prob: 0.5 | |
| rand_aug_n: 0 | |
| rand_aug_m: 9 | |
| erase_prob: 0.0 | |
| use_trivial_aug: false | |
| mean: | |
| - 0.5 | |
| - 0.5 | |
| - 0.5 | |
| std: | |
| - 0.5 | |
| - 0.5 | |
| - 0.5 | |
| batch_size: 128 | |
| workers: 8 | |
| model_checkpoint: | |
| dirpath: null | |
| filename: best-step-{step}-{val_acc:.4f} | |
| monitor: val_acc | |
| verbose: false | |
| save_last: true | |
| save_top_k: 1 | |
| save_weights_only: false | |
| mode: max | |
| auto_insert_metric_name: true | |
| every_n_train_steps: null | |
| train_time_interval: null | |
| every_n_epochs: null | |
| save_on_train_epoch_end: null | |
| ckpt_path: null | |