End of training

README.md

@@ -17,8 +17,8 @@ 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: 1.6326
-- Accuracy: 0.891
+- Loss: 0.8426
+- Accuracy: 0.922
 
 ## Model description
 
@@ -46,15 +46,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.7093        | 0.992 | 62   | 2.5579          | 0.788    |
-| 1.8325        | 2.0   | 125  | 1.8277          | 0.836    |
-| 1.5672        | 2.976 | 186  | 1.6515          | 0.869    |
+| 2.8526        | 0.992 | 62   | 2.6167          | 0.836    |
+| 1.7104        | 2.0   | 125  | 1.5818          | 0.884    |
+| 1.2318        | 2.992 | 187  | 1.1876          | 0.915    |
+| 0.9759        | 4.0   | 250  | 0.9661          | 0.92     |
+| 0.8262        | 4.992 | 312  | 0.8780          | 0.92     |
+| 0.7681        | 5.952 | 372  | 0.8362          | 0.93     |
 
 
 ### Framework versions

runs/Jun18_15-27-42_8351af5fa5cf/events.out.tfevents.1718724995.8351af5fa5cf.1355.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0841859d77eb2a23430815262008d6a6f7c2e6b4d457d2ff180b6893f548b1
+size 411