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: 0.8641
-- Validation Loss: 0.7810
-- Train Accuracy: 0.975
+- Train Loss: 0.4750
+- Validation Loss: 1.2942
+- Train Accuracy: 0.753
 - 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': 4000, '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': 20000, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 3.2775     | 2.2709          | 0.905          | 0     |
-| 1.8962     | 1.6275          | 0.975          | 1     |
-| 1.4069     | 1.2565          | 0.97           | 2     |
-| 1.0910     | 0.9813          | 0.98           | 3     |
-| 0.8641     | 0.7810          | 0.975          | 4     |
+| 3.1686     | 2.7854          | 0.595          | 0     |
+| 1.6403     | 1.9912          | 0.666          | 1     |
+| 0.9538     | 1.6441          | 0.688          | 2     |
+| 0.6312     | 1.4643          | 0.685          | 3     |
+| 0.4750     | 1.2942          | 0.753          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6370f04842c05564d5d30c4ca57790566fa8083cca222d81ba6a2a750f7169b0
+oid sha256:7872ab5dba2c861d61e147653f9b014af2c8aa738ede72a24fb93a15067d9a0a
 size 343773880