Model save

README.md

@@ -2,8 +2,6 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
-- image-classification
-- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans
 
-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 beans dataset.
+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: 0.3442
-- Accuracy: 0.9624
+- Loss: 0.5646
+- Accuracy: 0.9699
 
 ## Model description
 
@@ -45,17 +43,15 @@ The following hyperparameters were used during training:
 - seed: 1337
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5.0
+- num_epochs: 3.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9867        | 1.0   | 17   | 0.7571          | 0.9248   |
-| 0.6897        | 2.0   | 34   | 0.5547          | 0.9624   |
-| 0.4993        | 3.0   | 51   | 0.4208          | 0.9699   |
-| 0.455         | 4.0   | 68   | 0.3615          | 0.9624   |
-| 0.3931        | 5.0   | 85   | 0.3442          | 0.9624   |
+| 0.9886        | 1.0   | 17   | 0.7758          | 0.9248   |
+| 0.7226        | 2.0   | 34   | 0.6198          | 0.9549   |
+| 0.6041        | 3.0   | 51   | 0.5646          | 0.9699   |
 
 
 ### Framework versions