End of training

README.md

@@ -14,10 +14,10 @@ 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: 0.7832
-- Validation Loss: 0.6840
-- Train Accuracy: 0.8043
-- Epoch: 4
+- Train Loss: 0.6782
+- Validation Loss: 0.7004
+- Train Accuracy: 0.7391
+- Epoch: 6
 
 ## Model description
 
@@ -36,18 +36,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 920, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1288, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.0825     | 1.0898          | 0.3478         | 0     |
-| 1.0065     | 0.9575          | 0.6522         | 1     |
-| 0.8874     | 0.8564          | 0.6739         | 2     |
-| 0.8020     | 0.8281          | 0.6522         | 3     |
-| 0.7832     | 0.6840          | 0.8043         | 4     |
+| 1.0935     | 1.0228          | 0.6304         | 0     |
+| 1.0469     | 0.9620          | 0.7174         | 1     |
+| 0.9548     | 0.8669          | 0.8043         | 2     |
+| 0.8802     | 0.7712          | 0.7391         | 3     |
+| 0.8107     | 0.6756          | 0.8261         | 4     |
+| 0.7338     | 0.5727          | 0.8478         | 5     |
+| 0.6782     | 0.7004          | 0.7391         | 6     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a722e9313fda7c73dd604367e969c5219e60f96172225ddeab51d1a5e8789297
+oid sha256:50360fa6935fe9264a20fea00732028bed006766bf2cd8e20d73fc95e3edc056
 size 343472824