metadata
license: mit
base_model: tangminhanh/ts_tg
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: ts_cate
results: []
ts_cate
This model is a fine-tuned version of tangminhanh/ts_tg on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0263
- Accuracy: 0.8555
- F1: 0.8736
- Precision: 0.8824
- Recall: 0.8649
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 404 | 0.0458 | 0.6802 | 0.7650 | 0.8750 | 0.6796 |
| 0.1001 | 2.0 | 808 | 0.0318 | 0.7717 | 0.8259 | 0.8817 | 0.7767 |
| 0.0321 | 3.0 | 1212 | 0.0278 | 0.8251 | 0.8564 | 0.8862 | 0.8286 |
| 0.0215 | 4.0 | 1616 | 0.0256 | 0.8322 | 0.8627 | 0.8909 | 0.8363 |
| 0.0161 | 5.0 | 2020 | 0.0256 | 0.8455 | 0.8679 | 0.8812 | 0.8551 |
| 0.0161 | 6.0 | 2424 | 0.0259 | 0.8499 | 0.8711 | 0.8831 | 0.8594 |
| 0.0124 | 7.0 | 2828 | 0.0255 | 0.8536 | 0.8713 | 0.8836 | 0.8594 |
| 0.0105 | 8.0 | 3232 | 0.0262 | 0.8533 | 0.8723 | 0.8836 | 0.8612 |
| 0.0087 | 9.0 | 3636 | 0.0261 | 0.8567 | 0.8746 | 0.8838 | 0.8656 |
| 0.0078 | 10.0 | 4040 | 0.0263 | 0.8555 | 0.8736 | 0.8824 | 0.8649 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1