End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5
+      value: 0.5375
 ---
 
 <!-- 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: 1.4639
-- Accuracy: 0.5
+- Loss: 1.3293
+- Accuracy: 0.5375
 
 ## Model description
 
@@ -53,23 +53,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 10   | 1.4014          | 0.5188   |
-| No log        | 2.0   | 20   | 1.3733          | 0.55     |
-| No log        | 3.0   | 30   | 1.5627          | 0.4938   |
-| No log        | 4.0   | 40   | 1.5493          | 0.4938   |
-| No log        | 5.0   | 50   | 1.4639          | 0.5      |
+| No log        | 1.0   | 20   | 1.4818          | 0.4375   |
+| No log        | 2.0   | 40   | 1.4215          | 0.4562   |
+| No log        | 3.0   | 60   | 1.3947          | 0.5      |
+| No log        | 4.0   | 80   | 1.3840          | 0.5      |
+| No log        | 5.0   | 100  | 1.3293          | 0.5375   |
 
 
 ### Framework versions