Upload TFBertForTokenClassification

README.md

@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0683
-- Validation Loss: 0.1681
+- Train Loss: 0.3167
+- Validation Loss: 0.4221
 - Epoch: 2
 
 ## Model description
@@ -35,16 +35,16 @@ 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': 2e-05, 'decay_steps': 372, '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': 2e-06, 'decay_steps': 744, '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 | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.3356     | 0.2039          | 0     |
-| 0.0898     | 0.1704          | 1     |
-| 0.0683     | 0.1681          | 2     |
+| 0.7900     | 0.5758          | 0     |
+| 0.3790     | 0.4553          | 1     |
+| 0.3167     | 0.4221          | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f4f6693b741c09f93273c36da44025dd2d487986021ed4aec3b2d45731eb31
-size 538712044
+oid sha256:5504f3ba268865f4102e7ea06c6f114385f9cec625c9a12cc08cc7993527c66d
+size 538724332