Training in progress epoch 2

README.md

@@ -15,13 +15,13 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1770
-- Train Accuracy: 0.9413
+- Train Loss: 0.0943
+- Train Accuracy: 0.9760
 - Train Top-3-accuracy: 1.0
-- Validation Loss: 0.1919
-- Validation Accuracy: 0.9332
+- Validation Loss: 0.1654
+- Validation Accuracy: 0.9436
 - Validation Top-3-accuracy: 1.0
-- Epoch: 1
+- Epoch: 2
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 |:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
 | 0.4326     | 0.8143         | 1.0                  | 0.2613          | 0.9102              | 1.0                       | 0     |
 | 0.1770     | 0.9413         | 1.0                  | 0.1919          | 0.9332              | 1.0                       | 1     |
+| 0.0943     | 0.9760         | 1.0                  | 0.1654          | 0.9436              | 1.0                       | 2     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1708755158.ed9548208ee2.34.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca46baec183a68cdd72205b11b8159a9e5fb3ca410bf87b30f2e942f6052674
-size 3273480
+oid sha256:4e675f84b00e8f33773889c9b2ab61728d913758f3af4a5cc60621d72b1a4bff
+size 3273775

logs/validation/events.out.tfevents.1708755353.ed9548208ee2.34.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85170c8d0d4652d17ec0b5f1840296b45921933103208b9a55edc0456cd0387
-size 1061
+oid sha256:57eba783bdb04924ec6aeb3438dcee3eb42e4eaa49c7a37164deeada2a027402
+size 1557

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f00b72b2c05cffdd06a11435f561215cf14d0e19486cc833811cb8ec3769131
+oid sha256:1ec0088caa26917210ac92bb8c68e4fd16d724d185ac3ebd02aef3bb87584ee4
 size 343469752