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: 0.6182
-- Validation Loss: 0.6003
-- Train Accuracy: 0.87
-- Epoch: 2
+- Train Loss: 0.3937
+- Validation Loss: 0.4591
+- Train Accuracy: 0.8688
+- Epoch: 3
 
 ## Model description
 
@@ -37,16 +37,17 @@ 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': 6000, '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': 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}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.6260     | 1.0603          | 0.788          | 0     |
-| 0.8648     | 0.7270          | 0.844          | 1     |
-| 0.6182     | 0.6003          | 0.87           | 2     |
+| 1.3921     | 0.8426          | 0.8237         | 0     |
+| 0.6841     | 0.6112          | 0.8538         | 1     |
+| 0.4972     | 0.5191          | 0.8438         | 2     |
+| 0.3937     | 0.4591          | 0.8688         | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3f53672e20f4d6818142a61f3fd9e41e79f3d729ee5f440382a80f4b0227bc
+oid sha256:0d841adf00cdf9aa665e14c448a935a1b43669520ccf074bbf9d265b91adc410
 size 343494328