End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.16875
+      value: 0.4125
 ---
 
 <!-- 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: 2.0822
-- Accuracy: 0.1688
+- Loss: 1.7875
+- Accuracy: 0.4125
 
 ## Model description
 
@@ -52,48 +52,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.02
-- train_batch_size: 16
+- learning_rate: 5e-05
+- train_batch_size: 32
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 30
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 2.1729          | 0.1187   |
-| No log        | 2.0   | 80   | 2.1526          | 0.0813   |
-| No log        | 3.0   | 120  | 2.1301          | 0.0813   |
-| No log        | 4.0   | 160  | 2.1663          | 0.1313   |
-| No log        | 5.0   | 200  | 2.1524          | 0.0813   |
-| No log        | 6.0   | 240  | 2.0822          | 0.1688   |
-| No log        | 7.0   | 280  | 2.1661          | 0.1187   |
-| No log        | 8.0   | 320  | 2.1294          | 0.1375   |
-| No log        | 9.0   | 360  | 2.0832          | 0.1562   |
-| No log        | 10.0  | 400  | 2.1144          | 0.1187   |
-| No log        | 11.0  | 440  | 2.1037          | 0.1187   |
-| No log        | 12.0  | 480  | 2.1001          | 0.1562   |
-| 2.1281        | 13.0  | 520  | 2.1115          | 0.0813   |
-| 2.1281        | 14.0  | 560  | 2.0788          | 0.1187   |
-| 2.1281        | 15.0  | 600  | 2.1156          | 0.0813   |
-| 2.1281        | 16.0  | 640  | 2.1254          | 0.0813   |
-| 2.1281        | 17.0  | 680  | 2.0847          | 0.1688   |
-| 2.1281        | 18.0  | 720  | 2.0966          | 0.0813   |
-| 2.1281        | 19.0  | 760  | 2.1371          | 0.0813   |
-| 2.1281        | 20.0  | 800  | 2.0953          | 0.0813   |
-| 2.1281        | 21.0  | 840  | 2.0928          | 0.0875   |
-| 2.1281        | 22.0  | 880  | 2.1005          | 0.0813   |
-| 2.1281        | 23.0  | 920  | 2.0875          | 0.0875   |
-| 2.1281        | 24.0  | 960  | 2.0953          | 0.0813   |
-| 2.0868        | 25.0  | 1000 | 2.0931          | 0.0875   |
-| 2.0868        | 26.0  | 1040 | 2.0941          | 0.0875   |
-| 2.0868        | 27.0  | 1080 | 2.0949          | 0.0813   |
-| 2.0868        | 28.0  | 1120 | 2.0938          | 0.0875   |
-| 2.0868        | 29.0  | 1160 | 2.0940          | 0.0813   |
-| 2.0868        | 30.0  | 1200 | 2.0938          | 0.0875   |
+| No log        | 1.0   | 20   | 1.9763          | 0.325    |
+| No log        | 2.0   | 40   | 1.8310          | 0.4062   |
+| No log        | 3.0   | 60   | 1.7842          | 0.425    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b984bfb41b464109ba59bab46ae5f3c7bcb825174ef3dba072463fda18c912d6
-size 343287149
+oid sha256:602d1da71ea85b5a2511e9343c7386156574285f5d4d1664113fae13f3961d29
+size 343284397

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327de8134c460e481b1b119c436145e07d48e878832aac2c2bf06fe2480f0a43
-size 4091
+oid sha256:986c4f1d3352eee02f0ba613fc1c4f2ebeb5528f72cb2c4580ceceecf34eaec4
+size 4027