End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.07339449541284404
+      value: 0.1743119266055046
 ---
 
 <!-- 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: 3.4096
-- Accuracy: 0.0734
+- Loss: 3.1740
+- Accuracy: 0.1743
 
 ## Model description
 
@@ -52,7 +52,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -61,17 +61,22 @@ 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: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 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   |
+| No log        | 1.0   | 7    | 3.5703          | 0.0826   |
+| 3.5953        | 2.0   | 14   | 3.4340          | 0.0826   |
+| 3.3696        | 3.0   | 21   | 3.3687          | 0.0550   |
+| 3.3696        | 4.0   | 28   | 3.3127          | 0.1101   |
+| 3.2267        | 5.0   | 35   | 3.2651          | 0.1193   |
+| 3.156         | 6.0   | 42   | 3.2224          | 0.1284   |
+| 3.156         | 7.0   | 49   | 3.2147          | 0.1651   |
+| 3.0285        | 8.0   | 56   | 3.1623          | 0.2018   |
+| 2.9667        | 9.0   | 63   | 3.1621          | 0.2018   |
+| 2.914         | 10.0  | 70   | 3.1740          | 0.1743   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f924cef9e90139306afa7aa4a013513a20a7579f80ec5c977795be8f5400cb5b
+oid sha256:83eb21395fafb251396a195403377c1f74bb28bd4be8f37850dd8d0b3506d42c
 size 343334720