update model card README.md

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7586206896551724
+      value: 0.896551724137931
 ---
 
 <!-- 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: 0.6803
-- Accuracy: 0.7586
+- Loss: 0.4768
+- Accuracy: 0.8966
 
 ## Model description
 
@@ -53,11 +53,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 50
-- eval_batch_size: 50
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 200
+- total_train_batch_size: 512
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -67,20 +67,20 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.67  | 1    | 1.2027          | 0.3103   |
-| No log        | 2.0   | 3    | 1.1212          | 0.3448   |
-| No log        | 2.67  | 4    | 1.0648          | 0.4138   |
-| No log        | 4.0   | 6    | 0.9779          | 0.5172   |
-| No log        | 4.67  | 7    | 0.9494          | 0.5517   |
-| No log        | 6.0   | 9    | 0.9168          | 0.5862   |
-| 0.9535        | 6.67  | 10   | 0.8808          | 0.6552   |
-| 0.9535        | 8.0   | 12   | 0.8136          | 0.7241   |
-| 0.9535        | 8.67  | 13   | 0.8015          | 0.7241   |
-| 0.9535        | 10.0  | 15   | 0.7727          | 0.7586   |
-| 0.9535        | 10.67 | 16   | 0.7510          | 0.7586   |
-| 0.9535        | 12.0  | 18   | 0.6997          | 0.7586   |
-| 0.9535        | 12.67 | 19   | 0.6856          | 0.7586   |
-| 0.5181        | 13.33 | 20   | 0.6803          | 0.7586   |
+| No log        | 1.0   | 1    | 1.0387          | 0.3103   |
+| No log        | 2.0   | 3    | 1.0144          | 0.6552   |
+| No log        | 3.0   | 5    | 0.9570          | 0.7241   |
+| No log        | 4.0   | 6    | 0.9075          | 0.6552   |
+| No log        | 5.0   | 7    | 0.8455          | 0.7241   |
+| No log        | 6.0   | 9    | 0.7622          | 0.7931   |
+| 0.4555        | 7.0   | 11   | 0.7067          | 0.7931   |
+| 0.4555        | 8.0   | 12   | 0.6745          | 0.8276   |
+| 0.4555        | 9.0   | 13   | 0.6108          | 0.8621   |
+| 0.4555        | 10.0  | 15   | 0.5319          | 0.8966   |
+| 0.4555        | 11.0  | 17   | 0.4943          | 0.8966   |
+| 0.4555        | 12.0  | 18   | 0.4896          | 0.8966   |
+| 0.4555        | 13.0  | 19   | 0.4820          | 0.8966   |
+| 0.2224        | 13.33 | 20   | 0.4768          | 0.8966   |
 
 
 ### Framework versions