End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.43125
+      value: 0.38125
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ 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 imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7576
-- Accuracy: 0.4313
+- Loss: 1.6448
+- Accuracy: 0.3812
 
 ## Model description
 
@@ -65,11 +65,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 20   | 1.9557          | 0.3438   |
-| No log        | 2.0   | 40   | 1.8729          | 0.3812   |
-| No log        | 3.0   | 60   | 1.8088          | 0.4125   |
-| No log        | 4.0   | 80   | 1.7655          | 0.4188   |
-| No log        | 5.0   | 100  | 1.7576          | 0.4313   |
+| No log        | 1.0   | 20   | 1.7814          | 0.3375   |
+| No log        | 2.0   | 40   | 1.7125          | 0.3563   |
+| No log        | 3.0   | 60   | 1.6787          | 0.3688   |
+| No log        | 4.0   | 80   | 1.6547          | 0.3625   |
+| No log        | 5.0   | 100  | 1.6448          | 0.3812   |
 
 
 ### Framework versions

runs/Feb24_15-07-43_d89d03a1f4d1/events.out.tfevents.1740410575.d89d03a1f4d1.300.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4165913eb0fefa296913aae670bca42b75d14964717223d91787106c81b8e0
-size 6606
+oid sha256:a6c65360ee67b5e3163d9c90f65410e69729e7603931b01f5d23a466453d57a4
+size 7271

runs/Feb24_15-07-43_d89d03a1f4d1/events.out.tfevents.1740411327.d89d03a1f4d1.300.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8607a8946d8de4bafd2f9887417c034b37ab1e56566b80abe42480046832e8
+size 722