my-awesome-bert-model-sentiment-analysis
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0733
- Train Accuracy: 0.9697
- Validation Loss: 0.1888
- Validation Accuracy: 0.9443
- 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': 1e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
---|---|---|---|---|
0.6042 | 0.7451 | 0.3504 | 0.8689 | 0 |
0.2387 | 0.9104 | 0.2092 | 0.9253 | 1 |
0.1230 | 0.9524 | 0.2296 | 0.9288 | 2 |
0.0892 | 0.9633 | 0.2171 | 0.9347 | 3 |
0.0733 | 0.9697 | 0.1888 | 0.9443 | 4 |
Framework versions
- Transformers 4.35.0
- TensorFlow 2.14.0
- Tokenizers 0.14.1
- Downloads last month
- 6
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Guspfc/my-awesome-bert-model-sentiment-analysis
Base model
google-bert/bert-base-uncased