End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.525
+      value: 0.55
 ---
 
 <!-- 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: 1.3481
-- Accuracy: 0.525
+- Loss: 1.2412
+- Accuracy: 0.55
 
 ## Model description
 
@@ -58,22 +58,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 20   | 1.9902          | 0.3187   |
-| No log        | 2.0   | 40   | 1.7760          | 0.3937   |
-| No log        | 3.0   | 60   | 1.5876          | 0.4188   |
-| No log        | 4.0   | 80   | 1.5014          | 0.4875   |
-| No log        | 5.0   | 100  | 1.4304          | 0.5188   |
-| No log        | 6.0   | 120  | 1.4211          | 0.4813   |
-| No log        | 7.0   | 140  | 1.3558          | 0.5062   |
-| No log        | 8.0   | 160  | 1.3184          | 0.55     |
-| No log        | 9.0   | 180  | 1.3240          | 0.5125   |
-| No log        | 10.0  | 200  | 1.3435          | 0.4938   |
+| No log        | 1.0   | 20   | 1.2182          | 0.5625   |
+| No log        | 2.0   | 40   | 1.2392          | 0.5312   |
+| No log        | 3.0   | 60   | 1.1474          | 0.6      |
 
 
 ### Framework versions

runs/Feb14_01-39-38_62bacf9b1492/events.out.tfevents.1707874900.62bacf9b1492.4959.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab6f1ad5d88a955e7e917bd9c1f338f85f38fba5d50a002b08054398cc510ef
+size 405