onizukal
/

Boya3_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold3

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

onizukal commited on 26 days ago

Commit

93d2846

•

1 Parent(s): d21e603

End of training

Files changed (1) hide show

README.md +9 -14

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8299723210755239
 ---
 <!-- 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: 1.6702
-- Accuracy: 0.8300
 ## Model description
@@ -59,22 +59,17 @@ 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: 10
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4648        | 1.0   | 632  | 0.4488          | 0.8043   |
-| 0.3305        | 2.0   | 1264 | 0.4801          | 0.8300   |
-| 0.2644        | 3.0   | 1896 | 0.4984          | 0.8173   |
-| 0.0426        | 4.0   | 2528 | 0.9639          | 0.8327   |
-| 0.0408        | 5.0   | 3160 | 1.2519          | 0.8383   |
-| 0.0134        | 6.0   | 3792 | 1.4345          | 0.8319   |
-| 0.0           | 7.0   | 4424 | 1.5640          | 0.8327   |
-| 0.0001        | 8.0   | 5056 | 1.6117          | 0.8343   |
-| 0.0           | 9.0   | 5688 | 1.6490          | 0.8319   |
-| 0.0           | 10.0  | 6320 | 1.6702          | 0.8300   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.8382759984183472
 ---
 <!-- 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: 1.1301
+- Accuracy: 0.8383
 ## 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: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.48          | 1.0   | 632  | 0.4558          | 0.8106   |
+| 0.3393        | 2.0   | 1264 | 0.4738          | 0.8312   |
+| 0.3238        | 3.0   | 1896 | 0.5381          | 0.8375   |
+| 0.0626        | 4.0   | 2528 | 0.9352          | 0.8359   |
+| 0.0011        | 5.0   | 3160 | 1.1301          | 0.8383   |
 ### Framework versions