End of training

README.md

@@ -15,10 +15,10 @@ 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: 0.8852
-- Validation Loss: 1.7692
-- Train Accuracy: 0.425
-- Epoch: 19
+- Train Loss: 1.7648
+- Validation Loss: 1.8114
+- Train Accuracy: 0.1625
+- Epoch: 4
 
 ## Model description
 
@@ -37,33 +37,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 12800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 3200, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.9557     | 1.7012          | 0.2687         | 0     |
-| 1.8429     | 1.7698          | 0.2125         | 1     |
-| 1.8175     | 1.6158          | 0.2875         | 2     |
-| 1.6821     | 1.5730          | 0.3312         | 3     |
-| 1.5837     | 1.4980          | 0.3125         | 4     |
-| 1.5647     | 1.4806          | 0.375          | 5     |
-| 1.4481     | 1.4933          | 0.3438         | 6     |
-| 1.4185     | 1.4641          | 0.3688         | 7     |
-| 1.3848     | 1.4206          | 0.4188         | 8     |
-| 1.3315     | 1.4745          | 0.3625         | 9     |
-| 1.3214     | 1.3629          | 0.3875         | 10    |
-| 1.2092     | 1.3953          | 0.4375         | 11    |
-| 1.2342     | 1.3674          | 0.4313         | 12    |
-| 1.1648     | 1.3140          | 0.4375         | 13    |
-| 1.1258     | 1.4024          | 0.3812         | 14    |
-| 1.0459     | 1.5097          | 0.45           | 15    |
-| 1.0098     | 1.4080          | 0.4188         | 16    |
-| 0.9245     | 1.4329          | 0.4313         | 17    |
-| 0.8194     | 1.3921          | 0.4625         | 18    |
-| 0.8852     | 1.7692          | 0.425          | 19    |
+| 2.0762     | 1.9409          | 0.225          | 0     |
+| 2.0248     | 2.0010          | 0.1562         | 1     |
+| 1.9520     | 2.0716          | 0.1437         | 2     |
+| 1.8909     | 1.7114          | 0.2313         | 3     |
+| 1.7648     | 1.8114          | 0.1625         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205e1cbff44905e647339d389f4ff966c8c92b14e9de7f805e67177dec25e605
-size 343488184
+oid sha256:987fff8f6b152bc7af6fd9b48a857f7664d396b8aa7551db8ad16dfae877f8da
+size 343504568