End of training

README.md

@@ -15,7 +15,8 @@ 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: 0.1769
+- Train Loss: 0.4037
+- Train Accuracy: 0.8039
 - Epoch: 9
 
 ## Model description
@@ -35,28 +36,28 @@ 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': 2550, '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': 4080, '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 | Epoch |
-|:----------:|:-----:|
-| 0.4562     | 0     |
-| 0.3993     | 1     |
-| 0.3517     | 2     |
-| 0.3186     | 3     |
-| 0.2959     | 4     |
-| 0.2589     | 5     |
-| 0.2289     | 6     |
-| 0.2065     | 7     |
-| 0.1904     | 8     |
-| 0.1769     | 9     |
+| Train Loss | Train Accuracy | Epoch |
+|:----------:|:--------------:|:-----:|
+| 2.0951     | 0.3039         | 0     |
+| 1.8395     | 0.4902         | 1     |
+| 1.6157     | 0.4902         | 2     |
+| 1.3806     | 0.5686         | 3     |
+| 1.1369     | 0.6569         | 4     |
+| 0.9272     | 0.6667         | 5     |
+| 0.7538     | 0.7157         | 6     |
+| 0.6106     | 0.7451         | 7     |
+| 0.4929     | 0.7843         | 8     |
+| 0.4037     | 0.8039         | 9     |
 
 
 ### Framework versions
 
-- Transformers 4.36.1
+- Transformers 4.36.2
 - TensorFlow 2.15.0
 - Datasets 2.15.0
 - Tokenizers 0.15.0

config.json

@@ -42,5 +42,5 @@
   "num_hidden_layers": 12,
   "patch_size": 16,
   "qkv_bias": true,
-  "transformers_version": "4.36.1"
+  "transformers_version": "4.36.2"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0d91fa681683c8b33d18350c8c5e7c47691f7c872a418d28faf894fdd05d3d
+oid sha256:6524ab6ea2643de88b44d357d184c61c0daf59d75770f1eeb0299068fffef79f
 size 343494328