Training in progress epoch 1

README.md

@@ -19,11 +19,11 @@ 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 mnist dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.0107
-- Train Accuracy: 0.8548
-- Validation Loss: 1.5288
-- Validation Accuracy: 0.8548
-- Epoch: 0
+- Train Loss: 1.3538
+- Train Accuracy: 0.9149
+- Validation Loss: 0.9913
+- Validation Accuracy: 0.9149
+- Epoch: 1
 
 ## Model description
 
@@ -50,6 +50,7 @@ The following hyperparameters were used during training:
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
 | 2.0107     | 0.8548         | 1.5288          | 0.8548              | 0     |
+| 1.3538     | 0.9149         | 0.9913          | 0.9149              | 1     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbee15c200534b213b9d09cefd97704b0fd1ce640a8f773b309abb54ee71771b
+oid sha256:a63b3533fb0a3d972c91818c5bd85ee2e9c89d4d6f42a3e8fef22e4e42f26e18
 size 343494328