Model save

README.md

@@ -6,9 +6,24 @@ tags:
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- accuracy
 model-index:
 - name: finetuned-websites
-  results: []
+  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: 0.39705882352941174
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
 # finetuned-websites
 
 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: 1.5660
+- Accuracy: 0.3971
 
 ## Model description
 
@@ -35,17 +53,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 16
+- learning_rate: 5e-05
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Use 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: 4
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 1.8678        | 2.0833 | 50   | 1.8966          | 0.3088   |
+| 1.6483        | 4.1667 | 100  | 1.7938          | 0.3382   |
+| 1.3419        | 6.25   | 150  | 1.6614          | 0.3824   |
+| 1.1189        | 8.3333 | 200  | 1.5660          | 0.3971   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9933abc9e69a9af1be5a27d975f4f17af110876b08c1e56b66638ea4b8a8d8c
+oid sha256:086b8fe62b0d5fed3e346f2a9d99dc00d9f5731dde320e3d0146aecb147105ea
 size 343239356

preprocessor_config.json

@@ -7,7 +7,7 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "ViTFeatureExtractor",
+  "image_processor_type": "ViTImageProcessor",
   "image_std": [
     0.5,
     0.5,

runs/Dec05_11-51-50_edab03f22c59/events.out.tfevents.1733399523.edab03f22c59.4058.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b667a81a89bd23391a7d6289a5e1ec13ab1ea430d1dcf10363ccdc54f625bd3e
+size 11892

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:506da4b0a84eacfb75e0f69de927254c79eee1db1f8a3fb0649150c5c0f94687
+oid sha256:10a6bd5335dcbeb330a5b30b2ffd7d502c27ce6f6343e794c3eb34529d57ad1d
 size 5240