End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.41875
+      value: 0.575
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 1.6437
-- Accuracy: 0.4188
+- Loss: 1.1641
+- Accuracy: 0.575
 
 ## Model description
 
@@ -52,21 +52,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 1.8854          | 0.3125   |
-| No log        | 2.0   | 80   | 1.7062          | 0.4      |
-| No log        | 3.0   | 120  | 1.6417          | 0.4313   |
+| No log        | 1.0   | 40   | 1.6582          | 0.475    |
+| No log        | 2.0   | 80   | 1.4117          | 0.4375   |
+| No log        | 3.0   | 120  | 1.3116          | 0.55     |
+| No log        | 4.0   | 160  | 1.2137          | 0.5437   |
+| No log        | 5.0   | 200  | 1.1592          | 0.5813   |
+| No log        | 6.0   | 240  | 1.1247          | 0.5875   |
+| No log        | 7.0   | 280  | 1.1440          | 0.6188   |
 
 
 ### Framework versions