End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.425
+      value: 0.34375
 ---
 
 <!-- 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: 1.6840
-- Accuracy: 0.425
+- Loss: 1.7721
+- Accuracy: 0.3438
 
 ## Model description
 
@@ -52,22 +52,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 32
-- eval_batch_size: 8
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 2
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.8028        | 10.0  | 100  | 1.6759          | 0.4375   |
+| 2.078         | 1.0   | 10   | 2.0567          | 0.1875   |
+| 1.9889        | 2.0   | 20   | 1.9714          | 0.2812   |
+| 1.874         | 3.0   | 30   | 1.8689          | 0.3312   |
+| 1.7814        | 4.0   | 40   | 1.8008          | 0.3812   |
+| 1.7228        | 5.0   | 50   | 1.7661          | 0.4      |
 
 
 ### Framework versions