Model save

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
 tags:
 - generated_from_trainer
 datasets:
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6990805238227918
+      value: 0.7099470604625244
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Emotion_DF_Image_VIT_V1
 
-This model was trained from scratch on the imagefolder dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2870
-- Accuracy: 0.6991
+- Loss: 0.8621
+- Accuracy: 0.7099
 
 ## Model description
 
@@ -57,19 +59,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Accuracy | Validation Loss |
-|:-------------:|:-----:|:-----:|:--------:|:---------------:|
-| 0.9576        | 1.0   | 1795  | 0.6565   | 0.9175          |
-| 0.5058        | 2.0   | 3590  | 0.7063   | 0.8228          |
-| 0.5078        | 3.0   | 5385  | 0.7083   | 0.8647          |
-| 0.3086        | 4.0   | 7180  | 0.9248   | 0.7060          |
-| 0.1919        | 5.0   | 8975  | 1.1380   | 0.7069          |
-| 0.1284        | 6.0   | 10770 | 1.2783   | 0.7016          |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.9584        | 1.0   | 1795 | 0.9150          | 0.6581   |
+| 0.5361        | 2.0   | 3590 | 0.8223          | 0.7049   |
+| 0.483         | 3.0   | 5385 | 0.8621          | 0.7099   |
 
 
 ### Framework versions