Upload TFBertForTokenClassification

README.md

@@ -14,9 +14,9 @@ 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: 0.0841
-- Validation Loss: 0.0625
-- Epoch: 2
+- Train Loss: 0.0305
+- Validation Loss: 0.0395
+- Epoch: 6
 
 ## Model description
 
@@ -35,16 +35,20 @@ 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': 75, '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-05, 'decay_steps': 175, '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 |
 |:----------:|:---------------:|:-----:|
-| 0.3036     | 0.1145          | 0     |
-| 0.1072     | 0.0710          | 1     |
-| 0.0841     | 0.0625          | 2     |
+| 0.2834     | 0.0949          | 0     |
+| 0.0963     | 0.0559          | 1     |
+| 0.0646     | 0.0423          | 2     |
+| 0.0468     | 0.0402          | 3     |
+| 0.0383     | 0.0391          | 4     |
+| 0.0341     | 0.0407          | 5     |
+| 0.0305     | 0.0395          | 6     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97dabe0f5425c02b578f36db3430e68bb835dbf1ae1c6aceb4a6afc7feba618f
+oid sha256:ef827f4302105fe4b1bbea1feab4a0cefc416f85c5342af815dc29ec32af1248
 size 538693588