End of training

README.md

@@ -0,0 +1,98 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: image_classification
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.4625
+---
+
+<!-- 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. -->
+
+# image_classification
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4745
+- Accuracy: 0.4625
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.3
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.0497        | 1.0   | 10   | 1.9973          | 0.2938   |
+| 1.8686        | 2.0   | 20   | 1.9635          | 0.3      |
+| 1.825         | 3.0   | 30   | 1.9291          | 0.3125   |
+| 1.6801        | 4.0   | 40   | 1.7476          | 0.3688   |
+| 1.4192        | 5.0   | 50   | 1.6341          | 0.4125   |
+| 1.2182        | 6.0   | 60   | 1.6148          | 0.3937   |
+| 1.1688        | 7.0   | 70   | 1.5954          | 0.4      |
+| 1.0198        | 8.0   | 80   | 1.5394          | 0.4      |
+| 0.7465        | 9.0   | 90   | 1.4797          | 0.4313   |
+| 0.5733        | 10.0  | 100  | 1.4648          | 0.4      |
+| 0.5417        | 11.0  | 110  | 1.4613          | 0.3937   |
+| 0.4472        | 12.0  | 120  | 1.4418          | 0.4562   |
+| 0.3015        | 13.0  | 130  | 1.4745          | 0.4625   |
+| 0.2287        | 14.0  | 140  | 1.4175          | 0.45     |
+| 0.2154        | 15.0  | 150  | 1.4635          | 0.4562   |
+| 0.1787        | 16.0  | 160  | 1.4860          | 0.4437   |
+| 0.1312        | 17.0  | 170  | 1.5453          | 0.45     |
+| 0.1106        | 18.0  | 180  | 1.5976          | 0.4375   |
+| 0.1075        | 19.0  | 190  | 1.5866          | 0.4188   |
+| 0.0989        | 20.0  | 200  | 1.6112          | 0.4188   |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94595c66cba15951bf665ac20c4008d2d12bc572689eda14c117abd49ef740a
+oid sha256:1e69874220a0f31e149d17e82fb7495c63aed85cb69d207d33615d7116a043f3
 size 343242432

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4428d473f090be593eeb7759ce26fdf4b204177d168d69f6e1aa3b991f51f6e
-size 5304
+oid sha256:a51a404e31e499a5509e4732acb0fa1cc0997011ac7f844a0898ea7765e77627
+size 5240