metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-chinese
metrics:
- accuracy
- f1
model-index:
- name: emotion-classification
results: []
language:
- zh
pipeline_tag: text-classification
emotion-classification
This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4979
- Model Preparation Time: 0.0019
- Accuracy: 0.8718
- F1: 0.8701
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:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy | F1 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 364 | 0.4835 | 0.0019 | 0.8510 | 0.8457 |
| 0.734 | 2.0 | 728 | 0.4865 | 0.0019 | 0.8638 | 0.8604 |
| 0.2323 | 3.0 | 1092 | 0.4782 | 0.0019 | 0.8830 | 0.8814 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.11.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2