End of training

README.md

@@ -16,9 +16,9 @@ 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: 0.1485
-- Validation Loss: 0.2882
-- Train Accuracy: 0.9234
+- Train Loss: 0.1349
+- Validation Loss: 0.2197
+- Train Accuracy: 0.9571
 - Epoch: 4
 
 ## Model description
@@ -38,23 +38,23 @@ 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': 13040, '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': 13045, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.3120     | 0.8327          | 0.8683         | 0     |
-| 0.5857     | 0.4779          | 0.9112         | 1     |
-| 0.3149     | 0.3776          | 0.9035         | 2     |
-| 0.2088     | 0.3102          | 0.9265         | 3     |
-| 0.1485     | 0.2882          | 0.9234         | 4     |
+| 1.3075     | 0.7344          | 0.8988         | 0     |
+| 0.5513     | 0.4531          | 0.9141         | 1     |
+| 0.3134     | 0.3091          | 0.9448         | 2     |
+| 0.2058     | 0.2620          | 0.9356         | 3     |
+| 0.1349     | 0.2197          | 0.9571         | 4     |
 
 
 ### Framework versions
 
-- Transformers 4.46.2
+- Transformers 4.46.3
 - TensorFlow 2.17.1
 - Datasets 3.1.0
 - Tokenizers 0.20.3

config.json

@@ -36,5 +36,5 @@
   "num_hidden_layers": 12,
   "patch_size": 16,
   "qkv_bias": true,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.46.3"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e63cfa3aee8af38c1a9c15df2bba6774ef737aaf171cf1eab4f491e9b733656
+oid sha256:da865d1a4cf39eecf32c6c205bcf08c25fe4f562d4c81ae125f47853deb996c8
 size 343485112