Model save

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6363636363636364
+      value: 0.7727272727272727
 ---
 
 <!-- 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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6086
-- Accuracy: 0.6364
+- Loss: 0.5770
+- Accuracy: 0.7727
 
 ## Model description
 
@@ -53,27 +53,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- 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: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.67  | 1    | 0.6086          | 0.6364   |
-| No log        | 2.0   | 3    | 0.6712          | 0.6364   |
-| No log        | 2.67  | 4    | 0.7224          | 0.5455   |
-| No log        | 4.0   | 6    | 0.6421          | 0.5909   |
-| No log        | 4.67  | 7    | 0.6588          | 0.5455   |
-| No log        | 6.0   | 9    | 0.7261          | 0.5455   |
-| 0.542         | 6.67  | 10   | 0.7230          | 0.5455   |
+| No log        | 1.0   | 3    | 2.8754          | 0.2727   |
+| No log        | 2.0   | 6    | 0.5872          | 0.7273   |
+| No log        | 3.0   | 9    | 0.5770          | 0.7727   |
 
 
 ### Framework versions