End of training

README.md

@@ -15,9 +15,9 @@ 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: 0.7467
-- Validation Loss: 0.8080
-- Train Accuracy: 0.8333
+- Train Loss: 0.1936
+- Validation Loss: 0.1743
+- Train Accuracy: 0.9889
 - Epoch: 4
 
 ## Model description
@@ -37,18 +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': 3e-05, 'decay_steps': 330, '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': 3e-05, 'decay_steps': 1755, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.0953     | 1.0191          | 0.7222         | 0     |
-| 0.9838     | 0.9614          | 0.7778         | 1     |
-| 0.8988     | 0.9069          | 0.7778         | 2     |
-| 0.8179     | 0.8586          | 0.8333         | 3     |
-| 0.7467     | 0.8080          | 0.8333         | 4     |
+| 1.0088     | 0.8898          | 0.8667         | 0     |
+| 0.7325     | 0.6165          | 0.9333         | 1     |
+| 0.4620     | 0.3794          | 0.9444         | 2     |
+| 0.3100     | 0.2546          | 0.9667         | 3     |
+| 0.1936     | 0.1743          | 0.9889         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d534a8ba47e59c3c62aa03a9787b1e162b2eeab90769b3804b6efca95dbc466
+oid sha256:e908d3c46c6c8c8566603fb9b5b75775df4bac1f7930baa89187f932ea3e36e2
 size 343472824