Training in progress epoch 2

README.md

@@ -14,13 +14,13 @@ 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: 0.1008
-- Train Accuracy: 0.9876
-- Train Top-3-accuracy: 0.9997
-- Validation Loss: 0.0855
-- Validation Accuracy: 0.9856
+- Train Loss: 0.0495
+- Train Accuracy: 0.9948
+- Train Top-3-accuracy: 0.9999
+- Validation Loss: 0.0782
+- Validation Accuracy: 0.9839
 - Validation Top-3-accuracy: 1.0
-- Epoch: 1
+- Epoch: 2
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 |:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
 | 0.4593     | 0.9478         | 0.9912               | 0.1558          | 0.9809              | 0.9995                    | 0     |
 | 0.1008     | 0.9876         | 0.9997               | 0.0855          | 0.9856              | 1.0                       | 1     |
+| 0.0495     | 0.9948         | 0.9999               | 0.0782          | 0.9839              | 1.0                       | 2     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1651328868.localhost.localdomain.208434.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38daa041f2103b984773c51930c9605b69b03e8250d1731ec8122358f53549f1
-size 2250521
+oid sha256:afc7ba3761e09930b1fd7f33a8f007a9f100d66d9a68520bf22dffc9806b3548
+size 2250816

logs/validation/events.out.tfevents.1651334842.localhost.localdomain.208434.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c9020d3952843f1c17d9bd9bc1a8fa39ebc414b744ed56529f53ddf23adba8
-size 1026
+oid sha256:833da3b5afd136b1d783b170caec08f795a34ac652bb8a348a033639b58cb439
+size 1522

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf03c28f0b947f225c505e8dbde89b38e6850a28bcc1c87c9318da9f0f0c7366
+oid sha256:121e215420f57c4251b0b9da1b354a8e73a5dbfffe81c8babac359d4fefbde27
 size 343493888