End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.21568627450980393
+      value: 0.07339449541284404
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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: 3.0804
-- Accuracy: 0.2157
+- Loss: 3.4096
+- Accuracy: 0.0734
 
 ## Model description
 
@@ -61,15 +61,17 @@ 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: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.92  | 3    | 3.1607          | 0.1765   |
-| No log        | 1.85  | 6    | 3.1068          | 0.2157   |
-| No log        | 2.77  | 9    | 3.0804          | 0.2157   |
+| No log        | 1.0   | 7    | 3.5144          | 0.0917   |
+| 3.4861        | 2.0   | 14   | 3.4666          | 0.0734   |
+| 3.3767        | 3.0   | 21   | 3.4310          | 0.0459   |
+| 3.3767        | 4.0   | 28   | 3.4107          | 0.0459   |
+| 3.3363        | 5.0   | 35   | 3.4096          | 0.0734   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6409e924450da5e09b4416d8d729e3fcd0e2018485252a7c83aa7af58c08a563
+oid sha256:62df42f53df6b4a32d9ec992b875686609dac70ed84dc931568e984dd96f2fbf
 size 343334720