Final model push

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.33
+      value: 0.5294117647058824
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,10 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 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 arrow dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2416
-- Accuracy: 0.33
-- F1 Macro: 0.0388
-- F1 Micro: 0.33
+- Loss: 2.1426
+- Accuracy: 0.5294
+- F1 Macro: 0.2642
+- F1 Micro: 0.5294
 
 ## Model description
 
@@ -68,11 +68,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
-| 3.6873        | 1.0   | 250  | 3.6610          | 0.262    | 0.0331   | 0.262    |
-| 3.4794        | 2.0   | 500  | 3.4666          | 0.31     | 0.0356   | 0.31     |
-| 3.3469        | 3.0   | 750  | 3.3379          | 0.328    | 0.0380   | 0.328    |
-| 3.2643        | 4.0   | 1000 | 3.2652          | 0.332    | 0.0393   | 0.332    |
-| 3.2281        | 5.0   | 1250 | 3.2416          | 0.33     | 0.0388   | 0.33     |
+| 2.2743        | 1.0   | 88   | 2.2088          | 0.3235   | 0.0906   | 0.3235   |
+| 2.225         | 2.0   | 176  | 2.1776          | 0.4706   | 0.1411   | 0.4706   |
+| 2.1906        | 3.0   | 264  | 2.1581          | 0.4706   | 0.1590   | 0.4706   |
+| 2.1659        | 4.0   | 352  | 2.1473          | 0.5294   | 0.2642   | 0.5294   |
+| 2.1618        | 5.0   | 440  | 2.1426          | 0.5294   | 0.2642   | 0.5294   |
 
 
 ### Framework versions