metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: market_positivity
results: []
market_positivity
This model is a fine-tuned version of hfl/chinese-roberta-wwm-ext on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.1121
- Train Sparse Categorical Accuracy: 0.3337
- Validation Loss: 1.0984
- Validation Sparse Categorical Accuracy: 0.3417
- 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': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|---|---|---|---|---|
| 1.0908 | 0.3750 | 1.1132 | 0.3357 | 0 |
| 1.1104 | 0.3384 | 1.1178 | 0.3226 | 1 |
| 1.1121 | 0.3337 | 1.0984 | 0.3417 | 2 |
Framework versions
- Transformers 4.16.0
- TensorFlow 2.7.0
- Datasets 1.18.1
- Tokenizers 0.11.0