Training in progress epoch 16

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: 0.0637
-- Train Accuracy: 1.0
+- Train Loss: 0.0573
+- Train Accuracy: 0.9996
 - Train Top-3-accuracy: 1.0
-- Validation Loss: 0.1426
-- Validation Accuracy: 0.9762
+- Validation Loss: 0.1361
+- Validation Accuracy: 0.9784
 - Validation Top-3-accuracy: 0.9978
-- Epoch: 15
+- Epoch: 16
 
 ## Model description
 
@@ -63,6 +63,7 @@ The following hyperparameters were used during training:
 | 0.0809     | 0.9992         | 1.0                  | 0.1595          | 0.9719              | 0.9978                    | 13    |
 | 0.0715     | 0.9992         | 1.0                  | 0.1503          | 0.9719              | 0.9978                    | 14    |
 | 0.0637     | 1.0            | 1.0                  | 0.1426          | 0.9762              | 0.9978                    | 15    |
+| 0.0573     | 0.9996         | 1.0                  | 0.1361          | 0.9784              | 0.9978                    | 16    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1699744453.48cd21698220.35352.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec41373b218a98d15bcdef300970b697ce3e30b65da6b0375c38cf89eff8a9b1
-size 3392769
+oid sha256:ecb2618d8b14f4b6b8c60d830a00c14202fd384083f10b068acc31fbc9c38e11
+size 3393064

logs/validation/events.out.tfevents.1699744990.48cd21698220.35352.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d34d02164d93c364d9c47631255f9ea0491f134d933c3e0ec34294597037ac16
-size 8005
+oid sha256:fca56cd55fbc4a6bfe79829bedf3ee3638bf14aa3ae3753e39a7e5223b79cca8
+size 8501

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9aa24c19f0d663565f806d3d6f3950bdca277f3e8a325980e742c12477cfd8a
+oid sha256:fcbdb830c18a17ed5f229201d51a6d6081d195f6fd95bacad263df550106e556
 size 343526072