Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mbert-base-finetuned-pt_br-rte – AI Model by pmfsl | AlphaNeural AI
You can deploy this model and start earning money today!
pmfsl
/
mbert-base-finetuned-pt_br-rte
like
0
transformers
tf
bert
text-classification
generated_from_keras_callback
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
pmfsl/mbert-base-finetuned-pt_br-rte
This model is a fine-tuned version of
bert-base-multilingual-cased
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.0664
Validation Loss: 0.2401
Train Accuracy: 0.9286
Train F1: 0.9279
Epoch: 4
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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 505, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32
Training results
Train Loss
Validation Loss
Train Accuracy
Train F1
Epoch
0.4070
0.2690
0.8884
0.8922
0
0.2460
0.2288
0.9286
0.9304
1
0.1722
0.1869
0.9263
0.9287
2
0.1098
0.2032
0.9308
0.9310
3
0.0664
0.2401
0.9286
0.9279
4
Framework versions
Transformers 4.27.4
TensorFlow 2.12.0
Datasets 2.11.0
Tokenizers 0.13.2
