update model card README.md

README.md

@@ -6,6 +6,9 @@ datasets:
 - imagefolder
 metrics:
 - accuracy
+- f1
+- precision
+- recall
 model-index:
 - name: swin-tiny-patch4-window7-224-finetuned-eurosat
   results:
@@ -21,7 +24,16 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9755555555555555
+      value: 0.9637037037037037
+    - name: F1
+      type: f1
+      value: 0.9638654060560553
+    - name: Precision
+      type: precision
+      value: 0.9647087049809714
+    - name: Recall
+      type: recall
+      value: 0.9637037037037037
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +43,11 @@ 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: 0.0675
-- Accuracy: 0.9756
+- Loss: 0.1086
+- Accuracy: 0.9637
+- F1: 0.9639
+- Precision: 0.9647
+- Recall: 0.9637
 
 ## Model description
 
@@ -51,12 +66,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 2.5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -64,11 +79,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.2658        | 1.0   | 190  | 0.1311          | 0.9596   |
-| 0.1908        | 2.0   | 380  | 0.0730          | 0.9748   |
-| 0.1388        | 3.0   | 570  | 0.0675          | 0.9756   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.3304        | 1.0   | 95   | 0.2118          | 0.9326   | 0.9331 | 0.9379    | 0.9326 |
+| 0.233         | 2.0   | 190  | 0.1295          | 0.9596   | 0.9597 | 0.9611    | 0.9596 |
+| 0.1906        | 3.0   | 285  | 0.1086          | 0.9637   | 0.9639 | 0.9647    | 0.9637 |
 
 
 ### Framework versions