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: 3.9756
-- Accuracy: 0.3004
+- Loss: 2.7318
+- Accuracy: 0.4200
 
 ## Model description
 
@@ -37,7 +37,7 @@ 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: 8
 - seed: 42
@@ -46,15 +46,18 @@ 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: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 4.5745        | 0.9996 | 662  | 4.5617          | 0.2469   |
-| 4.0811        | 1.9992 | 1324 | 4.1151          | 0.2900   |
-| 3.9045        | 2.9989 | 1986 | 3.9756          | 0.3004   |
+| 4.2032        | 0.9996 | 662  | 4.1884          | 0.2552   |
+| 3.3354        | 1.9992 | 1324 | 3.4367          | 0.3206   |
+| 2.8501        | 2.9989 | 1986 | 3.0902          | 0.3626   |
+| 2.643         | 4.0    | 2649 | 2.9247          | 0.3870   |
+| 2.4272        | 4.9996 | 3311 | 2.8228          | 0.4070   |
+| 2.1558        | 5.9977 | 3972 | 2.7318          | 0.4200   |
 
 
 ### Framework versions