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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1927
-- Accuracy: 0.7377
+- Loss: 0.7087
+- Accuracy: 0.8012
 
 ## Model description
 
@@ -46,14 +46,22 @@ 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: 2
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3621        | 1.0   | 157  | 1.3617          | 0.7274   |
-| 1.1294        | 1.99  | 314  | 1.1701          | 0.75     |
+| 1.7167        | 1.0   | 157  | 1.6188          | 0.6964   |
+| 1.0511        | 2.0   | 315  | 1.0981          | 0.7381   |
+| 0.9184        | 3.0   | 472  | 0.9225          | 0.7710   |
+| 0.7396        | 4.0   | 630  | 0.8333          | 0.7802   |
+| 0.6873        | 5.0   | 787  | 0.7917          | 0.7849   |
+| 0.6579        | 6.0   | 945  | 0.7510          | 0.7845   |
+| 0.5857        | 7.0   | 1102 | 0.7672          | 0.7845   |
+| 0.4968        | 8.0   | 1260 | 0.7467          | 0.7857   |
+| 0.513         | 9.0   | 1417 | 0.7156          | 0.7940   |
+| 0.4957        | 9.97  | 1570 | 0.7073          | 0.8024   |
 
 
 ### Framework versions