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: 1.8946
-- Validation Loss: 1.9332
-- Train Accuracy: 0.375
+- Train Loss: 0.8371
+- Validation Loss: 0.7054
+- Train Accuracy: 0.786
 - Epoch: 4
 
 ## Model description
@@ -37,23 +37,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 480, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 20000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.0880     | 2.0676          | 0.2083         | 0     |
-| 2.0370     | 2.0331          | 0.25           | 1     |
-| 1.9903     | 1.9986          | 0.2917         | 2     |
-| 1.9406     | 1.9644          | 0.2917         | 3     |
-| 1.8946     | 1.9332          | 0.375          | 4     |
+| 1.5386     | 1.0983          | 0.74           | 0     |
+| 1.1263     | 0.8877          | 0.754          | 1     |
+| 0.9805     | 0.7840          | 0.77           | 2     |
+| 0.9209     | 0.7624          | 0.769          | 3     |
+| 0.8371     | 0.7054          | 0.786          | 4     |
 
 
 ### Framework versions
 
 - Transformers 4.32.0.dev0
 - TensorFlow 2.9.1
-- Datasets 2.14.2
+- Datasets 2.14.3
 - Tokenizers 0.12.1

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:505757c321219b10fe874c22559c560afaa16de3f09aee42b7654621f777294e
+oid sha256:e3c670a485e9dd1ebc866972b345c5ba0e30175c99414836457f32c1ff45c95b
 size 343488288