Model save

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.3155737704918033
+      value: 0.3483606557377049
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,17 +31,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/dit-base](https://huggingface.co/microsoft/dit-base) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0995
-- Accuracy: 0.3156
-- Weighted f1: 0.2119
-- Micro f1: 0.3156
-- Macro f1: 0.2258
-- Weighted recall: 0.3156
-- Micro recall: 0.3156
-- Macro recall: 0.3347
-- Weighted precision: 0.2311
-- Micro precision: 0.3156
-- Macro precision: 0.2480
+- Loss: 1.0820
+- Accuracy: 0.3484
+- Weighted f1: 0.2183
+- Micro f1: 0.3484
+- Macro f1: 0.2173
+- Weighted recall: 0.3484
+- Micro recall: 0.3484
+- Macro recall: 0.3545
+- Weighted precision: 0.4016
+- Micro precision: 0.3484
+- Macro precision: 0.3764
 
 ## Model description
 
@@ -75,7 +75,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy | Weighted f1 | Micro f1 | Macro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
 |:-------------:|:------:|:----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:|
-| 1.2333        | 0.9855 | 17   | 1.0995          | 0.3156   | 0.2119      | 0.3156   | 0.2258   | 0.3156          | 0.3156       | 0.3347       | 0.2311             | 0.3156          | 0.2480          |
+| 1.7064        | 0.9855 | 17   | 1.0820          | 0.3484   | 0.2183      | 0.3484   | 0.2173   | 0.3484          | 0.3484       | 0.3545       | 0.4016             | 0.3484          | 0.3764          |
 
 
 ### Framework versions