Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bert-berta-base – AI Model by badokorach | AlphaNeural AI
You can deploy this model and start earning money today!
badokorach
/
bert-berta-base
like
0
transformers
tf
bert
question-answering
generated_from_keras_callback
Davlan/bert-base-multilingual-cased-finetuned-luganda
finetune
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
badokorach/bert-berta-base
This model is a fine-tuned version of
Davlan/bert-base-multilingual-cased-finetuned-luganda
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.6578
Validation Loss: 0.0
Epoch: 5
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 4e-05, 'decay_steps': 1120, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.03}
training_precision: mixed_float16
Training results
Train Loss
Validation Loss
Epoch
2.4199
0.0
0
1.8885
0.0
1
1.7700
0.0
2
1.5049
0.0
3
1.0805
0.0
4
0.6578
0.0
5
Framework versions
Transformers 4.33.0
TensorFlow 2.12.0
Datasets 2.14.4
Tokenizers 0.13.3
