update model card README.md

README.md

@@ -19,11 +19,11 @@ 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: 0.4513
-- Accuracy: 0.8601
-- F1: 0.8617
-- Precision: 0.8650
-- Recall: 0.8601
+- Loss: 0.4871
+- Accuracy: 0.8705
+- F1: 0.8762
+- Precision: 0.8862
+- Recall: 0.8705
 
 ## Model description
 
@@ -48,17 +48,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 6
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.1702        | 1.0   | 626  | 0.3922          | 0.8394   | 0.8381 | 0.8578    | 0.8394 |
-| 0.0647        | 2.0   | 1252 | 0.5615          | 0.8238   | 0.8248 | 0.8404    | 0.8238 |
-| 0.0111        | 3.0   | 1878 | 0.4316          | 0.8705   | 0.8684 | 0.8670    | 0.8705 |
-| 0.0034        | 4.0   | 2504 | 0.4513          | 0.8601   | 0.8617 | 0.8650    | 0.8601 |
+| 0.1966        | 1.0   | 626  | 0.3647          | 0.8290   | 0.8307 | 0.8431    | 0.8290 |
+| 0.1434        | 2.0   | 1252 | 0.3884          | 0.8238   | 0.8259 | 0.8418    | 0.8238 |
+| 0.058         | 3.0   | 1878 | 0.5064          | 0.8187   | 0.8137 | 0.8183    | 0.8187 |
+| 0.02          | 4.0   | 2504 | 0.5477          | 0.8394   | 0.8431 | 0.8538    | 0.8394 |
+| 0.0018        | 5.0   | 3130 | 0.4876          | 0.8705   | 0.8749 | 0.8864    | 0.8705 |
+| 0.0003        | 6.0   | 3756 | 0.4871          | 0.8705   | 0.8762 | 0.8862    | 0.8705 |
 
 
 ### Framework versions