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: 0.1141
-- Validation Loss: 0.1065
+- Train Loss: 0.0361
+- Validation Loss: 0.0352
 - Train Accuracy: 1.0
-- Epoch: 4
+- Epoch: 19
 
 ## Model description
 
@@ -37,18 +37,33 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'clipnorm': 1.0, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1800, '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', 'clipnorm': 1.0, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 7200, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.9407     | 0.5637          | 1.0            | 0     |
-| 0.3930     | 0.2584          | 1.0            | 1     |
-| 0.2076     | 0.1642          | 1.0            | 2     |
-| 0.1430     | 0.1257          | 1.0            | 3     |
-| 0.1141     | 0.1065          | 1.0            | 4     |
+| 0.9729     | 0.5902          | 1.0            | 0     |
+| 0.4190     | 0.2874          | 1.0            | 1     |
+| 0.2212     | 0.1722          | 1.0            | 2     |
+| 0.1512     | 0.1305          | 1.0            | 3     |
+| 0.1192     | 0.1058          | 1.0            | 4     |
+| 0.1007     | 0.0926          | 1.0            | 5     |
+| 0.0885     | 0.0827          | 1.0            | 6     |
+| 0.0796     | 0.0753          | 1.0            | 7     |
+| 0.0726     | 0.0689          | 1.0            | 8     |
+| 0.0668     | 0.0636          | 1.0            | 9     |
+| 0.0620     | 0.0594          | 1.0            | 10    |
+| 0.0578     | 0.0554          | 1.0            | 11    |
+| 0.0541     | 0.0524          | 1.0            | 12    |
+| 0.0507     | 0.0494          | 1.0            | 13    |
+| 0.0477     | 0.0459          | 1.0            | 14    |
+| 0.0450     | 0.0436          | 1.0            | 15    |
+| 0.0425     | 0.0413          | 1.0            | 16    |
+| 0.0402     | 0.0392          | 1.0            | 17    |
+| 0.0380     | 0.0371          | 1.0            | 18    |
+| 0.0361     | 0.0352          | 1.0            | 19    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c3683f41c135d177907184d257f16138792e6dac13eb2f22916104167ecf36
+oid sha256:0240e3c042bad9221d60e331024e5f5b533da72c192d1911fa1bd91c927a78d1
 size 343492280