Model save

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8709677419354839
+      value: 0.8257839721254355
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3968
-- Accuracy: 0.8710
+- Loss: 0.4614
+- Accuracy: 0.8258
 
 ## Model description
 
@@ -53,7 +53,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 1e-05
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
@@ -62,39 +62,22 @@ 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: 30
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
-|:-------------:|:-------:|:----:|:---------------:|:--------:|
-| No log        | 0.8889  | 2    | 1.7756          | 0.2258   |
-| No log        | 1.7778  | 4    | 1.6784          | 0.2581   |
-| No log        | 2.6667  | 6    | 1.5861          | 0.3226   |
-| No log        | 4.0     | 9    | 1.3571          | 0.4194   |
-| No log        | 4.8889  | 11   | 1.0993          | 0.5484   |
-| No log        | 5.7778  | 13   | 0.9242          | 0.6452   |
-| 1.4667        | 6.6667  | 15   | 0.7538          | 0.7097   |
-| 1.4667        | 8.0     | 18   | 0.6294          | 0.7742   |
-| 1.4667        | 8.8889  | 20   | 0.5326          | 0.7097   |
-| 1.4667        | 9.7778  | 22   | 0.4848          | 0.7419   |
-| 1.4667        | 10.6667 | 24   | 0.4832          | 0.7742   |
-| 1.4667        | 12.0    | 27   | 0.4483          | 0.7742   |
-| 1.4667        | 12.8889 | 29   | 0.4296          | 0.7742   |
-| 0.5925        | 13.7778 | 31   | 0.4023          | 0.7742   |
-| 0.5925        | 14.6667 | 33   | 0.4111          | 0.8387   |
-| 0.5925        | 16.0    | 36   | 0.3873          | 0.8065   |
-| 0.5925        | 16.8889 | 38   | 0.4029          | 0.8065   |
-| 0.5925        | 17.7778 | 40   | 0.4065          | 0.8065   |
-| 0.5925        | 18.6667 | 42   | 0.3864          | 0.8065   |
-| 0.3285        | 20.0    | 45   | 0.3968          | 0.8710   |
-| 0.3285        | 20.8889 | 47   | 0.3930          | 0.8710   |
-| 0.3285        | 21.7778 | 49   | 0.3871          | 0.8710   |
-| 0.3285        | 22.6667 | 51   | 0.3779          | 0.8065   |
-| 0.3285        | 24.0    | 54   | 0.3698          | 0.8065   |
-| 0.3285        | 24.8889 | 56   | 0.3726          | 0.8387   |
-| 0.3285        | 25.7778 | 58   | 0.3732          | 0.8387   |
-| 0.2621        | 26.6667 | 60   | 0.3732          | 0.8387   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.8826        | 1.0   | 64   | 1.5673          | 0.4669   |
+| 1.1123        | 2.0   | 128  | 0.9031          | 0.7154   |
+| 0.8883        | 3.0   | 192  | 0.7255          | 0.7573   |
+| 0.7778        | 4.0   | 256  | 0.6219          | 0.7793   |
+| 0.708         | 5.0   | 320  | 0.5521          | 0.8002   |
+| 0.6308        | 6.0   | 384  | 0.5193          | 0.8130   |
+| 0.6142        | 7.0   | 448  | 0.4854          | 0.8235   |
+| 0.5817        | 8.0   | 512  | 0.4726          | 0.8200   |
+| 0.5952        | 9.0   | 576  | 0.4648          | 0.8211   |
+| 0.5915        | 10.0  | 640  | 0.4614          | 0.8258   |
 
 
 ### Framework versions