End of training

README.md

@@ -1,12 +1,13 @@
 ---
-license: apache-2.0
-base_model: microsoft/swinv2-tiny-patch4-window8-256
 tags:
 - generated_from_trainer
 datasets:
 - imagefolder
 metrics:
 - accuracy
+- f1
+- precision
+- recall
 model-index:
 - name: msi-swinv2-tiny
   results:
@@ -22,7 +23,16 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6273762929829466
+      value: 0.9253901789113057
+    - name: F1
+      type: f1
+      value: 0.9052377115229654
+    - name: Precision
+      type: precision
+      value: 0.9233171693926194
+    - name: Recall
+      type: recall
+      value: 0.8878526831581444
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +40,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # msi-swinv2-tiny
 
-This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
+This model was trained from scratch on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5764
-- Accuracy: 0.6274
+- Loss: 0.1768
+- Accuracy: 0.9254
+- F1: 0.9052
+- Precision: 0.9233
+- Recall: 0.8879
 
 ## Model description
 
@@ -61,22 +74,17 @@ The following hyperparameters were used during training:
 - 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 |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.4392        | 1.0   | 2015  | 0.7935          | 0.6100   |
-| 0.3266        | 2.0   | 4031  | 0.9694          | 0.6132   |
-| 0.2673        | 3.0   | 6047  | 1.2037          | 0.6114   |
-| 0.2222        | 4.0   | 8063  | 1.3734          | 0.6097   |
-| 0.1922        | 5.0   | 10078 | 1.3308          | 0.6235   |
-| 0.1716        | 6.0   | 12094 | 1.4758          | 0.6136   |
-| 0.1742        | 7.0   | 14110 | 1.4332          | 0.6274   |
-| 0.1653        | 8.0   | 16126 | 1.4940          | 0.6247   |
-| 0.1429        | 9.0   | 18141 | 1.6058          | 0.6236   |
-| 0.1546        | 10.0  | 20150 | 1.5764          | 0.6274   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.3786        | 1.0   | 1970 | 0.3166          | 0.8590   | 0.8184 | 0.8469    | 0.7917 |
+| 0.2976        | 2.0   | 3941 | 0.2426          | 0.8952   | 0.8621 | 0.9138    | 0.8159 |
+| 0.2525        | 3.0   | 5911 | 0.2015          | 0.9144   | 0.8908 | 0.9132    | 0.8694 |
+| 0.2319        | 4.0   | 7882 | 0.1859          | 0.9216   | 0.9026 | 0.8996    | 0.9056 |
+| 0.206         | 5.0   | 9850 | 0.1768          | 0.9254   | 0.9052 | 0.9233    | 0.8879 |
 
 
 ### Framework versions