End of training

README.md

@@ -3,11 +3,26 @@ 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: []
+  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: 0.58125
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ 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 an unknown dataset.
+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: 1.6479
-- Accuracy: 0.885
+- Loss: 1.1334
+- Accuracy: 0.5813
 
 ## Model description
 
@@ -37,29 +52,36 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.7451        | 0.992 | 62   | 2.5612          | 0.826    |
-| 1.8505        | 2.0   | 125  | 1.8206          | 0.863    |
-| 1.6186        | 2.976 | 186  | 1.6613          | 0.882    |
+| 2.0287        | 1.0   | 40   | 1.9886          | 0.3312   |
+| 1.6572        | 2.0   | 80   | 1.6017          | 0.4      |
+| 1.4274        | 3.0   | 120  | 1.3753          | 0.5      |
+| 1.2165        | 4.0   | 160  | 1.2923          | 0.5125   |
+| 1.0676        | 5.0   | 200  | 1.2017          | 0.5437   |
+| 0.9438        | 6.0   | 240  | 1.1987          | 0.525    |
+| 0.7568        | 7.0   | 280  | 1.1113          | 0.5625   |
+| 0.6683        | 8.0   | 320  | 1.1406          | 0.5625   |
+| 0.5162        | 9.0   | 360  | 1.1863          | 0.5625   |
+| 0.4258        | 10.0  | 400  | 1.0780          | 0.65     |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
-- Pytorch 2.4.0+cu121
+- Transformers 4.44.0
+- Pytorch 2.4.0
 - Datasets 2.21.0
 - Tokenizers 0.19.1