Upload TFViTForImageClassification

README.md

@@ -16,10 +16,10 @@ 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: 2.0418
-- Validation Loss: 2.0389
-- Train Accuracy: 0.2121
-- Epoch: 0
+- Train Loss: 1.9897
+- Validation Loss: 1.9904
+- Train Accuracy: 0.3905
+- Epoch: 9
 
 ## Model description
 
@@ -38,19 +38,28 @@ 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': 1, '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': 10, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.0418     | 2.0389          | 0.2121         | 0     |
+| 1.9904     | 1.9904          | 0.3905         | 0     |
+| 1.9894     | 1.9904          | 0.3905         | 1     |
+| 1.9898     | 1.9904          | 0.3905         | 2     |
+| 1.9897     | 1.9904          | 0.3905         | 3     |
+| 1.9897     | 1.9904          | 0.3905         | 4     |
+| 1.9901     | 1.9904          | 0.3905         | 5     |
+| 1.9897     | 1.9904          | 0.3905         | 6     |
+| 1.9897     | 1.9904          | 0.3905         | 7     |
+| 1.9902     | 1.9904          | 0.3905         | 8     |
+| 1.9897     | 1.9904          | 0.3905         | 9     |
 
 
 ### Framework versions
 
-- Transformers 4.45.1
-- TensorFlow 2.16.1
-- Datasets 3.0.1
-- Tokenizers 0.20.0
+- Transformers 4.46.2
+- TensorFlow 2.17.1
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -38,5 +38,5 @@
   "num_hidden_layers": 12,
   "patch_size": 16,
   "qkv_bias": true,
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.46.2"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784b8ea0f4f1a3f56670fdcda0eba3678897a31db465c643aa3678f16cab1e12
+oid sha256:0be1776dca95ebe0fb6bf9f2be8cd755333093b9b7ad9a7b9b4395c14224a85f
 size 343488184