End of training

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: 0.2879
-- Accuracy: 0.9152
+- Loss: 0.4637
+- Accuracy: 0.8753
 
 ## Model description
 
@@ -46,23 +46,21 @@ 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: 6
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3233        | 1.0   | 25   | 0.8780          | 0.7781   |
-| 0.6368        | 2.0   | 50   | 0.5324          | 0.8529   |
-| 0.4085        | 3.0   | 75   | 0.4805          | 0.8628   |
-| 0.2893        | 4.0   | 100  | 0.3767          | 0.9002   |
-| 0.2257        | 5.0   | 125  | 0.3576          | 0.8978   |
-| 0.1179        | 6.0   | 150  | 0.2879          | 0.9152   |
+| 1.2343        | 1.0   | 25   | 0.9184          | 0.7157   |
+| 0.5527        | 2.0   | 50   | 0.6300          | 0.8130   |
+| 0.377         | 3.0   | 75   | 0.5489          | 0.8404   |
+| 0.2202        | 4.0   | 100  | 0.4637          | 0.8753   |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
-- Pytorch 2.2.0+cu121
-- Datasets 2.17.0
+- Transformers 4.38.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.1
 - Tokenizers 0.15.2