onizukal
/

Boya1_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold1

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

onizukal commited on Jun 11

Commit

9643bf0

•

1 Parent(s): b00ee08

End of training

Files changed (1) hide show

README.md +14 -9

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8305729025251154
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2448
-- Accuracy: 0.8306
 ## Model description
@@ -59,17 +59,22 @@ 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: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.318         | 1.0   | 924  | 0.4416          | 0.8213   |
-| 0.3078        | 2.0   | 1848 | 0.4271          | 0.8330   |
-| 0.2139        | 3.0   | 2772 | 0.6246          | 0.8295   |
-| 0.0872        | 4.0   | 3696 | 0.9651          | 0.8287   |
-| 0.0039        | 5.0   | 4620 | 1.2448          | 0.8306   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.8392614716263915
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 This model is a fine-tuned version of [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.7950
+- Accuracy: 0.8393
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3585        | 1.0   | 924  | 0.4347          | 0.8249   |
+| 0.3184        | 2.0   | 1848 | 0.4237          | 0.8317   |
+| 0.2047        | 3.0   | 2772 | 0.5136          | 0.8355   |
+| 0.1174        | 4.0   | 3696 | 0.8121          | 0.8292   |
+| 0.0516        | 5.0   | 4620 | 1.1429          | 0.8390   |
+| 0.0132        | 6.0   | 5544 | 1.4356          | 0.8308   |
+| 0.0382        | 7.0   | 6468 | 1.5435          | 0.8360   |
+| 0.0           | 8.0   | 7392 | 1.7607          | 0.8355   |
+| 0.0016        | 9.0   | 8316 | 1.7775          | 0.8376   |
+| 0.0           | 10.0  | 9240 | 1.7950          | 0.8393   |
 ### Framework versions