Model save

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+model-index:
+- name: vit-base-oxford-iiit-pets
+  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-base-oxford-iiit-pets
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 3.6956
+- eval_accuracy: 0.0244
+- eval_runtime: 7.9874
+- eval_samples_per_second: 92.52
+- eval_steps_per_second: 5.884
+- step: 0
+
+## 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: 0.0003
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,102 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Siamese",
+    "1": "Birman",
+    "2": "shiba inu",
+    "3": "staffordshire bull terrier",
+    "4": "basset hound",
+    "5": "Bombay",
+    "6": "japanese chin",
+    "7": "chihuahua",
+    "8": "german shorthaired",
+    "9": "pomeranian",
+    "10": "beagle",
+    "11": "english cocker spaniel",
+    "12": "american pit bull terrier",
+    "13": "Ragdoll",
+    "14": "Persian",
+    "15": "Egyptian Mau",
+    "16": "miniature pinscher",
+    "17": "Sphynx",
+    "18": "Maine Coon",
+    "19": "keeshond",
+    "20": "yorkshire terrier",
+    "21": "havanese",
+    "22": "leonberger",
+    "23": "wheaten terrier",
+    "24": "american bulldog",
+    "25": "english setter",
+    "26": "boxer",
+    "27": "newfoundland",
+    "28": "Bengal",
+    "29": "samoyed",
+    "30": "British Shorthair",
+    "31": "great pyrenees",
+    "32": "Abyssinian",
+    "33": "pug",
+    "34": "saint bernard",
+    "35": "Russian Blue",
+    "36": "scottish terrier"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Abyssinian": 32,
+    "Bengal": 28,
+    "Birman": 1,
+    "Bombay": 5,
+    "British Shorthair": 30,
+    "Egyptian Mau": 15,
+    "Maine Coon": 18,
+    "Persian": 14,
+    "Ragdoll": 13,
+    "Russian Blue": 35,
+    "Siamese": 0,
+    "Sphynx": 17,
+    "american bulldog": 24,
+    "american pit bull terrier": 12,
+    "basset hound": 4,
+    "beagle": 10,
+    "boxer": 26,
+    "chihuahua": 7,
+    "english cocker spaniel": 11,
+    "english setter": 25,
+    "german shorthaired": 8,
+    "great pyrenees": 31,
+    "havanese": 21,
+    "japanese chin": 6,
+    "keeshond": 19,
+    "leonberger": 22,
+    "miniature pinscher": 16,
+    "newfoundland": 27,
+    "pomeranian": 9,
+    "pug": 33,
+    "saint bernard": 34,
+    "samoyed": 29,
+    "scottish terrier": 36,
+    "shiba inu": 2,
+    "staffordshire bull terrier": 3,
+    "wheaten terrier": 23,
+    "yorkshire terrier": 20
+  },
+  "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": "4.48.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a87964c87db5b72393bfeffccab366155189a39b8c42cf1c7c50f228a853a8bc
+size 343331644

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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
+  }
+}

runs/Dec30_11-49-04_gpu-cv/events.out.tfevents.1735555753.gpu-cv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363fec083cb80f5d7049a7293d6dc595e8210b3c5ef552b474db418c678a6d9a
+size 40

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4ba67b83c131405513fb37aba08df1b41cfe84db1d64096c73a3f9f2c40474
+size 5368