Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
POS_Arabic – AI Model by AlaaHussien | AlphaNeural AI
You can deploy this model and start earning money today!
AlaaHussien
/
POS_Arabic
like
0
transformers
tf
bert
token-classification
generated_from_keras_callback
asafaya/bert-base-arabic
finetune
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
AlaaHussien/POS_Arabic
This model is a fine-tuned version of
asafaya/bert-base-arabic
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.0886
Validation Loss: 0.1103
Train Precision: 0.9604
Train Recall: 0.9555
Train F1: 0.9579
Train Accuracy: 0.9703
Epoch: 2
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
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': 795, '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 Precision
Train Recall
Train F1
Train Accuracy
Epoch
0.1303
0.1180
0.9571
0.9508
0.9539
0.9677
0
0.0995
0.1103
0.9597
0.9555
0.9576
0.9701
1
0.0886
0.1103
0.9604
0.9555
0.9579
0.9703
2
Framework versions
Transformers 4.51.1
TensorFlow 2.18.0
Datasets 3.5.0
Tokenizers 0.21.0
