Model save

README.md

@@ -1,10 +1,14 @@
 ---
+library_name: transformers
 license: apache-2.0
 base_model: microsoft/swin-tiny-patch4-window7-224
 tags:
 - generated_from_trainer
 metrics:
 - accuracy
+- precision
+- recall
+- f1
 model-index:
 - name: swin-tiny-patch4-window7-224-finetuned
   results: []
@@ -17,9 +21,11 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7278
-- Logloss: 0.7278
-- Accuracy: {'accuracy': 0.699}
+- Loss: 0.8847
+- Accuracy: 0.6612
+- Precision: 0.6590
+- Recall: 0.6612
+- F1: 0.6504
 
 ## Model description
 
@@ -47,22 +53,27 @@ 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: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy            |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------------------:|
-| 1.0137        | 0.992 | 31   | 0.9122          | 0.9122  | {'accuracy': 0.61}  |
-| 0.8297        | 1.984 | 62   | 0.7678          | 0.7678  | {'accuracy': 0.682} |
-| 0.8024        | 2.976 | 93   | 0.7520          | 0.7520  | {'accuracy': 0.687} |
-| 0.7441        | 4.0   | 125  | 0.7390          | 0.7390  | {'accuracy': 0.694} |
-| 0.7515        | 4.96  | 155  | 0.7278          | 0.7278  | {'accuracy': 0.699} |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.089         | 0.9846 | 32   | 1.0433          | 0.5919   | 0.5706    | 0.5919 | 0.5663 |
+| 1.0165        | 2.0    | 65   | 1.0114          | 0.5929   | 0.6008    | 0.5929 | 0.5521 |
+| 0.935         | 2.9846 | 97   | 0.9437          | 0.6372   | 0.6627    | 0.6372 | 0.6069 |
+| 0.9051        | 4.0    | 130  | 0.9239          | 0.6400   | 0.6381    | 0.6400 | 0.6328 |
+| 0.856         | 4.9846 | 162  | 0.9269          | 0.6381   | 0.6476    | 0.6381 | 0.6319 |
+| 0.8317        | 6.0    | 195  | 0.9115          | 0.6487   | 0.6536    | 0.6487 | 0.6367 |
+| 0.7914        | 6.9846 | 227  | 0.8913          | 0.6660   | 0.6622    | 0.6660 | 0.6558 |
+| 0.763         | 8.0    | 260  | 0.8967          | 0.6631   | 0.6610    | 0.6631 | 0.6568 |
+| 0.7079        | 8.9846 | 292  | 0.9005          | 0.6612   | 0.6638    | 0.6612 | 0.6519 |
+| 0.6984        | 9.8462 | 320  | 0.8847          | 0.6612   | 0.6590    | 0.6612 | 0.6504 |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
-- Pytorch 2.3.1+cu121
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
 - Datasets 2.21.0
 - Tokenizers 0.19.1