End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.43125
+      value: 0.5875
 ---
 
 <!-- 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: 1.6219
-- Accuracy: 0.4313
+- Loss: 1.3177
+- Accuracy: 0.5875
 
 ## Model description
 
@@ -52,21 +52,38 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3
+- lr_scheduler_type: cosine_with_restarts
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 1.9262          | 0.3063   |
-| No log        | 2.0   | 80   | 1.6858          | 0.3937   |
-| No log        | 3.0   | 120  | 1.6364          | 0.425    |
+| No log        | 1.0   | 20   | 2.0411          | 0.2188   |
+| No log        | 2.0   | 40   | 1.9683          | 0.3063   |
+| No log        | 3.0   | 60   | 1.8584          | 0.3563   |
+| No log        | 4.0   | 80   | 1.7136          | 0.4437   |
+| No log        | 5.0   | 100  | 1.6210          | 0.4437   |
+| No log        | 6.0   | 120  | 1.5458          | 0.4813   |
+| No log        | 7.0   | 140  | 1.5078          | 0.4938   |
+| No log        | 8.0   | 160  | 1.4580          | 0.5125   |
+| No log        | 9.0   | 180  | 1.4189          | 0.55     |
+| No log        | 10.0  | 200  | 1.3971          | 0.525    |
+| No log        | 11.0  | 220  | 1.3858          | 0.5312   |
+| No log        | 12.0  | 240  | 1.3413          | 0.5437   |
+| No log        | 13.0  | 260  | 1.3453          | 0.5375   |
+| No log        | 14.0  | 280  | 1.3515          | 0.5625   |
+| No log        | 15.0  | 300  | 1.3277          | 0.575    |
+| No log        | 16.0  | 320  | 1.3666          | 0.5062   |
+| No log        | 17.0  | 340  | 1.3552          | 0.5625   |
+| No log        | 18.0  | 360  | 1.3313          | 0.5938   |
+| No log        | 19.0  | 380  | 1.3268          | 0.5875   |
+| No log        | 20.0  | 400  | 1.3177          | 0.55     |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:089f5ff83c4b35f17ca8d435b68afc90682f32cd0b31e77932b77e1bb2afb1a4
+oid sha256:eb69ebea46ce65e41921c8aa22389a9d7d2bb271395822ba3c5985d436b78b5e
 size 343242432

runs/Feb06_12-01-57_bbe9a805e152/events.out.tfevents.1707222242.bbe9a805e152.840.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75dcc0e73c040fc24fdd8edb8fc4d9799bfb49e07276e1eb78cfb4ec1ad04915
+size 411