jolieee
/

image_classification

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

jolieee commited on Sep 17, 2023

Commit

8f9f700

•

1 Parent(s): 4e997d4

End of training

Files changed (2) hide show

README.md +13 -13
pytorch_model.bin +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.53125
 ---
 <!-- 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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2576
-- Accuracy: 0.5312
 ## Model description
@@ -64,16 +64,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 1.4319          | 0.45     |
-| No log        | 2.0   | 80   | 1.3869          | 0.4562   |
-| No log        | 3.0   | 120  | 1.3152          | 0.4813   |
-| No log        | 4.0   | 160  | 1.3110          | 0.4875   |
-| No log        | 5.0   | 200  | 1.3177          | 0.4938   |
-| No log        | 6.0   | 240  | 1.3252          | 0.4688   |
-| No log        | 7.0   | 280  | 1.2458          | 0.5437   |
-| No log        | 8.0   | 320  | 1.2710          | 0.525    |
-| No log        | 9.0   | 360  | 1.3238          | 0.5062   |
-| No log        | 10.0  | 400  | 1.3074          | 0.5125   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.51875
 ---
 <!-- 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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.2805
+- Accuracy: 0.5188
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 40   | 1.7942          | 0.4062   |
+| No log        | 2.0   | 80   | 1.5663          | 0.3563   |
+| No log        | 3.0   | 120  | 1.4601          | 0.4813   |
+| No log        | 4.0   | 160  | 1.3494          | 0.4813   |
+| No log        | 5.0   | 200  | 1.3107          | 0.5062   |
+| No log        | 6.0   | 240  | 1.3054          | 0.475    |
+| No log        | 7.0   | 280  | 1.2423          | 0.575    |
+| No log        | 8.0   | 320  | 1.3189          | 0.5188   |
+| No log        | 9.0   | 360  | 1.2515          | 0.5062   |
+| No log        | 10.0  | 400  | 1.2279          | 0.5437   |
 ### Framework versions

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8969a816b87a7b68710b637ebf38cc5d25da5e65dcb2cabdb354883b73b2530e
 size 343287149

 version https://git-lfs.github.com/spec/v1
+oid sha256:3735ac97ea54494824d2fddcf71a0bb5052788e4d28755e455dd14c877ec12ab
 size 343287149