Training in progress epoch 0

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: 0.5080
-- Train Accuracy: 0.958
-- Validation Loss: 0.4289
-- Validation Accuracy: 0.9580
-- Epoch: 4
+- Train Loss: 2.0110
+- Train Accuracy: 0.8531
+- Validation Loss: 1.5291
+- Validation Accuracy: 0.8531
+- Epoch: 0
 
 ## Model description
 
@@ -50,10 +50,6 @@ The following hyperparameters were used during training:
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
 | 2.0110     | 0.8531         | 1.5291          | 0.8531              | 0     |
-| 1.3596     | 0.9151         | 0.9948          | 0.9151              | 1     |
-| 0.9608     | 0.9302         | 0.7593          | 0.9302              | 2     |
-| 0.6974     | 0.9448         | 0.5795          | 0.9448              | 3     |
-| 0.5080     | 0.958          | 0.4289          | 0.9580              | 4     |
 
 
 ### Framework versions

all_results.json

@@ -0,0 +1 @@
+{"accuracy": 0.958}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b0f2bc51cbae186d1027eee3f8a7e67076cfbae58ce44e650d27a57534007e
+oid sha256:df1fe69a301f0ab215175a1dd47a5382ddce873b72553090a630764d587c4562
 size 343494328