Model save

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5879
+- Loss: 0.5974
 - F1: 0.6869
 
 ## Model description
@@ -47,17 +47,19 @@ 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: 5
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | F1     |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.6179        | 0.9963 | 67   | 0.6125          | 0.6696 |
-| 0.5961        | 1.9926 | 134  | 0.5973          | 0.6771 |
-| 0.5971        | 2.9888 | 201  | 0.5913          | 0.6845 |
-| 0.6024        | 4.0    | 269  | 0.5907          | 0.6803 |
-| 0.5684        | 4.9814 | 335  | 0.5879          | 0.6869 |
+| 0.516         | 0.9963 | 67   | 0.5966          | 0.6873 |
+| 0.5235        | 1.9926 | 134  | 0.5976          | 0.6850 |
+| 0.5327        | 2.9888 | 201  | 0.5961          | 0.6873 |
+| 0.5494        | 4.0    | 269  | 0.5996          | 0.6850 |
+| 0.5238        | 4.9963 | 336  | 0.5970          | 0.6883 |
+| 0.522         | 5.9926 | 403  | 0.6024          | 0.6813 |
+| 0.5134        | 6.9740 | 469  | 0.5974          | 0.6869 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eefb7182272b53f4ebbaecae41f7f223f439c86a77184f9193aec90e95ee24f
+oid sha256:03de3949823ebb11b0d9cceeb4171e88e930f877914a999fbcaa799502c6f3dc
 size 347498816