Model save

README.md

@@ -5,8 +5,6 @@ license: apache-2.0
 metrics:
 - accuracy
 tags:
-- image-classification
-- vision
 - generated_from_trainer
 model-index:
 - name: vit-base-beans
@@ -18,10 +16,10 @@ 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: 1.0667
-- Accuracy: 0.5188
+- Loss: 0.8530
+- Accuracy: 0.8045
 
 ## Model description
 
@@ -41,8 +39,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 128
-- eval_batch_size: 128
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 1337
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -52,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 9    | 1.0751          | 0.4737   |
-| 1.0798        | 2.0   | 18   | 1.0715          | 0.4812   |
-| 1.0728        | 3.0   | 27   | 1.0689          | 0.4962   |
-| 1.0719        | 4.0   | 36   | 1.0673          | 0.5188   |
-| 1.062         | 5.0   | 45   | 1.0667          | 0.5188   |
+| 1.0326        | 1.0   | 130  | 1.0319          | 0.6090   |
+| 0.9721        | 2.0   | 260  | 0.9699          | 0.7293   |
+| 0.8948        | 3.0   | 390  | 0.9060          | 0.7820   |
+| 0.8524        | 4.0   | 520  | 0.8661          | 0.8045   |
+| 0.866         | 5.0   | 650  | 0.8530          | 0.8045   |
 
 
 ### Framework versions