Model save

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: 1.8957
-- Accuracy: 0.3
+- Loss: 1.9405
+- Accuracy: 0.2938
 
 ## Model description
 
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 2.0172          | 0.2125   |
-| No log        | 2.0   | 80   | 1.9290          | 0.2375   |
-| No log        | 3.0   | 120  | 1.8957          | 0.3      |
+| No log        | 1.0   | 40   | 2.0322          | 0.2      |
+| No log        | 2.0   | 80   | 1.9634          | 0.2562   |
+| No log        | 3.0   | 120  | 1.9405          | 0.2938   |
 
 
 ### Framework versions

runs/Nov19_03-35-51_2d32a965d509/events.out.tfevents.1731987382.2d32a965d509.1732.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5a166da191e319f0b6bcd2ec5da94e483d113999edeb336bc7582f7655b1e5
-size 6237
+oid sha256:883fb100d4bb0c5f1ec12dd9e59484b7d251e84cbb7857f844e703de2aa149d8
+size 6585