End of training

README.md

@@ -14,9 +14,9 @@ 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: 0.3923
-- Validation Loss: 0.3608
-- Train Accuracy: 0.904
+- Train Loss: 0.3741
+- Validation Loss: 0.3406
+- Train Accuracy: 0.917
 - Epoch: 4
 
 ## Model description
@@ -43,11 +43,11 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.8080     | 1.6465          | 0.817          | 0     |
-| 1.2437     | 0.8525          | 0.878          | 1     |
-| 0.7138     | 0.5172          | 0.908          | 2     |
-| 0.5087     | 0.3884          | 0.91           | 3     |
-| 0.3923     | 0.3608          | 0.904          | 4     |
+| 2.7884     | 1.6524          | 0.802          | 0     |
+| 1.1929     | 0.8100          | 0.891          | 1     |
+| 0.6910     | 0.5326          | 0.905          | 2     |
+| 0.4867     | 0.4020          | 0.916          | 3     |
+| 0.3741     | 0.3406          | 0.917          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c6f2b17e88c9069035b106702a8a688c556773d97c2956f0a2823cc71489df3
+oid sha256:34e4fc259148bc7706a9e826b881b612b26e11c50197a88dace398482d3b1b23
 size 343773880