Model save

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](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2258
-- Accuracy: 0.5
+- Loss: 0.4312
+- Accuracy: 0.9
 
 ## Model description
 
@@ -46,14 +46,20 @@ 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: 12
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.67  | 1    | 1.6466          | 0.15     |
-| No log        | 2.0   | 3    | 1.2258          | 0.5      |
+| No log        | 0.67  | 1    | 1.2258          | 0.5      |
+| No log        | 2.0   | 3    | 1.0536          | 0.7      |
+| No log        | 2.67  | 4    | 0.9143          | 0.75     |
+| No log        | 4.0   | 6    | 0.6899          | 0.9      |
+| No log        | 4.67  | 7    | 0.6300          | 0.95     |
+| No log        | 6.0   | 9    | 0.5069          | 0.9      |
+| 0.8554        | 6.67  | 10   | 0.4671          | 0.9      |
+| 0.8554        | 8.0   | 12   | 0.4312          | 0.9      |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a475fe8256ad101281324a370067c9db2023b674e4dfc1eaeffcfb650c8ceec
+oid sha256:0ad4583a87838655ff9fd19c960563b7098e167a219a4b45e8b4d0fc9d83fb2d
 size 343274861