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: 0.8840
-- Accuracy: 0.8647
+- Loss: 0.2273
+- Accuracy: 0.9699
 
 ## Model description
 
@@ -45,13 +43,19 @@ 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: 1.0
+- num_epochs: 7.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9983        | 1.0   | 17   | 0.8840          | 0.8647   |
+| 0.9859        | 1.0   | 17   | 0.7494          | 0.9323   |
+| 0.6764        | 2.0   | 34   | 0.5287          | 0.9624   |
+| 0.4614        | 3.0   | 51   | 0.3725          | 0.9624   |
+| 0.4053        | 4.0   | 68   | 0.2980          | 0.9699   |
+| 0.3172        | 5.0   | 85   | 0.2541          | 0.9699   |
+| 0.2542        | 6.0   | 102  | 0.2286          | 0.9774   |
+| 0.2629        | 7.0   | 119  | 0.2273          | 0.9699   |
 
 
 ### Framework versions