metadata
license: mit
base_model: tangminhanh/results
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: results
results: []
results
This model is a fine-tuned version of tangminhanh/results on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0214
- Accuracy: 0.8673
- F1: 0.8828
- Precision: 0.8907
- Recall: 0.8750
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0959 | 1.0 | 816 | 0.0287 | 0.7330 | 0.7966 | 0.8666 | 0.7371 |
| 0.0223 | 2.0 | 1632 | 0.0203 | 0.8256 | 0.8587 | 0.8922 | 0.8277 |
| 0.0171 | 3.0 | 2448 | 0.0197 | 0.8348 | 0.8639 | 0.8824 | 0.8463 |
| 0.0116 | 4.0 | 3264 | 0.0194 | 0.8486 | 0.8708 | 0.8873 | 0.8548 |
| 0.0101 | 5.0 | 4080 | 0.0198 | 0.8532 | 0.8704 | 0.8798 | 0.8612 |
| 0.008 | 6.0 | 4896 | 0.0200 | 0.8550 | 0.8742 | 0.8872 | 0.8615 |
| 0.0065 | 7.0 | 5712 | 0.0204 | 0.8614 | 0.8775 | 0.8867 | 0.8686 |
| 0.0056 | 8.0 | 6528 | 0.0208 | 0.8587 | 0.8768 | 0.8858 | 0.8679 |
| 0.0048 | 9.0 | 7344 | 0.0214 | 0.8624 | 0.8781 | 0.8875 | 0.8689 |
| 0.0044 | 10.0 | 8160 | 0.0214 | 0.8673 | 0.8828 | 0.8907 | 0.8750 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1