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: 0.3406
-- Validation Loss: 0.5757
-- Train Accuracy: 0.7333
+- Train Loss: 0.4492
+- Validation Loss: 0.5853
+- Train Accuracy: 0.6548
 - Epoch: 14
 
 ## Model description
@@ -37,33 +37,33 @@ 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': 3555, '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': 5025, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.6974     | 0.6887          | 0.5167         | 0     |
-| 0.6729     | 0.6653          | 0.6167         | 1     |
-| 0.6525     | 0.6491          | 0.6333         | 2     |
-| 0.6286     | 0.6279          | 0.6833         | 3     |
-| 0.6004     | 0.6080          | 0.7167         | 4     |
-| 0.5721     | 0.5709          | 0.7            | 5     |
-| 0.5128     | 0.5500          | 0.7333         | 6     |
-| 0.5062     | 0.5888          | 0.6833         | 7     |
-| 0.5024     | 0.5971          | 0.6667         | 8     |
-| 0.4748     | 0.6142          | 0.6667         | 9     |
-| 0.4499     | 0.5167          | 0.7833         | 10    |
-| 0.4543     | 0.6911          | 0.65           | 11    |
-| 0.3976     | 0.6175          | 0.6833         | 12    |
-| 0.4040     | 0.5987          | 0.7            | 13    |
-| 0.3406     | 0.5757          | 0.7333         | 14    |
+| 0.6757     | 0.6910          | 0.5119         | 0     |
+| 0.6569     | 0.6739          | 0.5357         | 1     |
+| 0.6395     | 0.6663          | 0.5357         | 2     |
+| 0.6161     | 0.6465          | 0.6071         | 3     |
+| 0.5919     | 0.6299          | 0.6548         | 4     |
+| 0.5801     | 0.6173          | 0.6429         | 5     |
+| 0.5518     | 0.6039          | 0.6310         | 6     |
+| 0.5414     | 0.6205          | 0.6905         | 7     |
+| 0.5181     | 0.6138          | 0.6548         | 8     |
+| 0.4902     | 0.6300          | 0.6667         | 9     |
+| 0.4824     | 0.6672          | 0.6667         | 10    |
+| 0.4493     | 0.6038          | 0.6071         | 11    |
+| 0.4287     | 0.6329          | 0.6667         | 12    |
+| 0.4668     | 0.6371          | 0.6548         | 13    |
+| 0.4492     | 0.5853          | 0.6548         | 14    |
 
 
 ### Framework versions
 
-- Transformers 4.31.0
+- Transformers 4.32.0
 - TensorFlow 2.12.0
 - Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -26,5 +26,5 @@
   "num_hidden_layers": 12,
   "patch_size": 16,
   "qkv_bias": true,
-  "transformers_version": "4.31.0"
+  "transformers_version": "4.32.0"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7322ce06804b808addca8e4627f4917603c1388c441ce0a912e6ed595f1b18c7
+oid sha256:3436130d81d25adac7e1f69f09a8a8c4fd11efa0c6c368b7e084ab704cfa022e
 size 343469752