End of training

README.md

@@ -18,8 +18,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6335
-- Accuracy: 0.885
+- Loss: 1.6255
+- Accuracy: 0.9
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.7017        | 0.992 | 62   | 2.5137          | 0.83     |
-| 1.865         | 2.0   | 125  | 1.7847          | 0.874    |
-| 1.6145        | 2.976 | 186  | 1.6335          | 0.885    |
+| 2.6779        | 0.992 | 62   | 2.5162          | 0.822    |
+| 1.8259        | 2.0   | 125  | 1.8007          | 0.87     |
+| 1.604         | 2.976 | 186  | 1.6255          | 0.9      |
 
 
 ### Framework versions

runs/Sep07_10-02-32_meng-wei-Ubuntu-Server/events.out.tfevents.1725674554.meng-wei-Ubuntu-Server.2456.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03264ba1e9247b59316c4afe19c7e7fb1acdc2448d18e8580ad994969b91dd5
-size 14211
+oid sha256:286b3a77f07660b415487886d3d36ab55705ad95b9666c22352785e3ca8266c3
+size 14888