End of training

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vit-food101
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vit-food101
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4925
+- Accuracy: 0.899
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 64
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.682         | 0.6369 | 100  | 2.5501          | 0.802    |
+| 1.312         | 1.2739 | 200  | 1.3870          | 0.855    |
+| 0.7605        | 1.9108 | 300  | 0.9167          | 0.862    |
+| 0.3844        | 2.5478 | 400  | 0.6248          | 0.88     |
+| 0.1957        | 3.1847 | 500  | 0.5220          | 0.896    |
+| 0.1756        | 3.8217 | 600  | 0.4925          | 0.899    |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,228 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "apple",
+    "1": "aquarium_fish",
+    "10": "bowl",
+    "11": "boy",
+    "12": "bridge",
+    "13": "bus",
+    "14": "butterfly",
+    "15": "camel",
+    "16": "can",
+    "17": "castle",
+    "18": "caterpillar",
+    "19": "cattle",
+    "2": "baby",
+    "20": "chair",
+    "21": "chimpanzee",
+    "22": "clock",
+    "23": "cloud",
+    "24": "cockroach",
+    "25": "couch",
+    "26": "cra",
+    "27": "crocodile",
+    "28": "cup",
+    "29": "dinosaur",
+    "3": "bear",
+    "30": "dolphin",
+    "31": "elephant",
+    "32": "flatfish",
+    "33": "forest",
+    "34": "fox",
+    "35": "girl",
+    "36": "hamster",
+    "37": "house",
+    "38": "kangaroo",
+    "39": "keyboard",
+    "4": "beaver",
+    "40": "lamp",
+    "41": "lawn_mower",
+    "42": "leopard",
+    "43": "lion",
+    "44": "lizard",
+    "45": "lobster",
+    "46": "man",
+    "47": "maple_tree",
+    "48": "motorcycle",
+    "49": "mountain",
+    "5": "bed",
+    "50": "mouse",
+    "51": "mushroom",
+    "52": "oak_tree",
+    "53": "orange",
+    "54": "orchid",
+    "55": "otter",
+    "56": "palm_tree",
+    "57": "pear",
+    "58": "pickup_truck",
+    "59": "pine_tree",
+    "6": "bee",
+    "60": "plain",
+    "61": "plate",
+    "62": "poppy",
+    "63": "porcupine",
+    "64": "possum",
+    "65": "rabbit",
+    "66": "raccoon",
+    "67": "ray",
+    "68": "road",
+    "69": "rocket",
+    "7": "beetle",
+    "70": "rose",
+    "71": "sea",
+    "72": "seal",
+    "73": "shark",
+    "74": "shrew",
+    "75": "skunk",
+    "76": "skyscraper",
+    "77": "snail",
+    "78": "snake",
+    "79": "spider",
+    "8": "bicycle",
+    "80": "squirrel",
+    "81": "streetcar",
+    "82": "sunflower",
+    "83": "sweet_pepper",
+    "84": "table",
+    "85": "tank",
+    "86": "telephone",
+    "87": "television",
+    "88": "tiger",
+    "89": "tractor",
+    "9": "bottle",
+    "90": "train",
+    "91": "trout",
+    "92": "tulip",
+    "93": "turtle",
+    "94": "wardrobe",
+    "95": "whale",
+    "96": "willow_tree",
+    "97": "wolf",
+    "98": "woman",
+    "99": "worm"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "apple": "0",
+    "aquarium_fish": "1",
+    "baby": "2",
+    "bear": "3",
+    "beaver": "4",
+    "bed": "5",
+    "bee": "6",
+    "beetle": "7",
+    "bicycle": "8",
+    "bottle": "9",
+    "bowl": "10",
+    "boy": "11",
+    "bridge": "12",
+    "bus": "13",
+    "butterfly": "14",
+    "camel": "15",
+    "can": "16",
+    "castle": "17",
+    "caterpillar": "18",
+    "cattle": "19",
+    "chair": "20",
+    "chimpanzee": "21",
+    "clock": "22",
+    "cloud": "23",
+    "cockroach": "24",
+    "couch": "25",
+    "cra": "26",
+    "crocodile": "27",
+    "cup": "28",
+    "dinosaur": "29",
+    "dolphin": "30",
+    "elephant": "31",
+    "flatfish": "32",
+    "forest": "33",
+    "fox": "34",
+    "girl": "35",
+    "hamster": "36",
+    "house": "37",
+    "kangaroo": "38",
+    "keyboard": "39",
+    "lamp": "40",
+    "lawn_mower": "41",
+    "leopard": "42",
+    "lion": "43",
+    "lizard": "44",
+    "lobster": "45",
+    "man": "46",
+    "maple_tree": "47",
+    "motorcycle": "48",
+    "mountain": "49",
+    "mouse": "50",
+    "mushroom": "51",
+    "oak_tree": "52",
+    "orange": "53",
+    "orchid": "54",
+    "otter": "55",
+    "palm_tree": "56",
+    "pear": "57",
+    "pickup_truck": "58",
+    "pine_tree": "59",
+    "plain": "60",
+    "plate": "61",
+    "poppy": "62",
+    "porcupine": "63",
+    "possum": "64",
+    "rabbit": "65",
+    "raccoon": "66",
+    "ray": "67",
+    "road": "68",
+    "rocket": "69",
+    "rose": "70",
+    "sea": "71",
+    "seal": "72",
+    "shark": "73",
+    "shrew": "74",
+    "skunk": "75",
+    "skyscraper": "76",
+    "snail": "77",
+    "snake": "78",
+    "spider": "79",
+    "squirrel": "80",
+    "streetcar": "81",
+    "sunflower": "82",
+    "sweet_pepper": "83",
+    "table": "84",
+    "tank": "85",
+    "telephone": "86",
+    "television": "87",
+    "tiger": "88",
+    "tractor": "89",
+    "train": "90",
+    "trout": "91",
+    "tulip": "92",
+    "turtle": "93",
+    "wardrobe": "94",
+    "whale": "95",
+    "willow_tree": "96",
+    "wolf": "97",
+    "woman": "98",
+    "worm": "99"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8247fc1bfd4993c348f650827718bcec383346671b151bfdd0b7dcbfdd53428
+size 343525432

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9983f71b713b6c70d45d748db25b269da87a2fa566e1b9dc904ab42bd97d2a9
+size 5112