Model save

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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7897
-- Accuracy: 0.8236
+- Loss: 0.0212
+- Accuracy: 0.9917
 
 ## Model description
 
@@ -37,22 +37,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0002
 - train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.1735        | 1.0   | 203  | 1.1257          | 0.7361   |
-| 0.8295        | 2.0   | 406  | 0.8613          | 0.8042   |
-| 0.7085        | 3.0   | 609  | 0.7897          | 0.8236   |
+| 0.222         | 1.0   | 203  | 0.2224          | 0.9097   |
+| 0.0911        | 2.0   | 406  | 0.0806          | 0.9653   |
+| 0.0163        | 3.0   | 609  | 0.0560          | 0.9681   |
+| 0.0126        | 4.0   | 812  | 0.0554          | 0.9792   |
+| 0.0233        | 5.0   | 1015 | 0.0347          | 0.9806   |
+| 0.0096        | 6.0   | 1218 | 0.0949          | 0.9792   |
+| 0.0013        | 7.0   | 1421 | 0.0440          | 0.9917   |
+| 0.0011        | 8.0   | 1624 | 0.0222          | 0.9917   |
+| 0.0009        | 9.0   | 1827 | 0.0213          | 0.9917   |
+| 0.0009        | 10.0  | 2030 | 0.0212          | 0.9917   |
 
 
 ### Framework versions