config.json

{
  "architecture": "vit_base_patch16_224",
  "num_classes": 2,
  "num_features": 768,
  "global_pool": "token",
  "crop_pct": 0.875,
  "interpolation": "bicubic",
  "mean": [
    0.485,
    0.456,
    0.406
  ],
  "std": [
    0.229,
    0.224,
    0.225
  ],
  "first_conv": "patch_embed.proj",
  "classifier": "head",
  "input_size": [
    3,
    224,
    224
  ],
  "pool_size": [
    7,
    7
  ],
  "pretrained_cfg": {
    "tag": "gravit_a3",
    "custom_load": false,
    "input_size": [
      3,
      224,
      224
    ],
    "fixed_input_size": true,
    "interpolation": "bicubic",
    "crop_pct": 0.875,
    "crop_mode": "center",
    "mean": [
      0.485,
      0.456,
      0.406
    ],
    "std": [
      0.229,
      0.224,
      0.225
    ],
    "num_classes": 2,
    "pool_size": [
      7,
      7
    ],
    "first_conv": "patch_embed.proj",
    "classifier": "head"
  },
  "model_name": "vit_gravit_a3",
  "experiment": "a3",
  "training_strategy": "all-blocks",
  "dataset": "C21",
  "hyperparameters": {
    "batch_size": "192",
    "learning_rate": "AdamW with ReduceLROnPlateau",
    "epochs": "100",
    "patience": "10",
    "optimizer": "AdamW",
    "scheduler": "ReduceLROnPlateau",
    "image_size": "224x224",
    "fine_tune_mode": "all_blocks",
    "stochastic_depth_probability": "0.1"
  },
  "hf_hub_id": "parlange/vit-gravit-a3",
  "license": "apache-2.0"
}