|
--- |
|
license: mit |
|
base_model: tangminhanh/ts_subcate |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: cs_subcate |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# cs_subcate |
|
|
|
This model is a fine-tuned version of [tangminhanh/ts_subcate](https://huggingface.co/tangminhanh/ts_subcate) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0517 |
|
- Accuracy: 0.6283 |
|
- F1: 0.6777 |
|
- Precision: 0.7292 |
|
- Recall: 0.6330 |
|
|
|
## 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 | 195 | 0.0649 | 0.2715 | 0.4110 | 0.8554 | 0.2704 | |
|
| No log | 2.0 | 390 | 0.0532 | 0.5113 | 0.6149 | 0.7639 | 0.5145 | |
|
| 0.0785 | 3.0 | 585 | 0.0515 | 0.5688 | 0.6404 | 0.7225 | 0.5750 | |
|
| 0.0785 | 4.0 | 780 | 0.0496 | 0.5979 | 0.6606 | 0.7225 | 0.6085 | |
|
| 0.0785 | 5.0 | 975 | 0.0492 | 0.6147 | 0.6753 | 0.7367 | 0.6233 | |
|
| 0.0386 | 6.0 | 1170 | 0.0499 | 0.6141 | 0.6701 | 0.7151 | 0.6304 | |
|
| 0.0386 | 7.0 | 1365 | 0.0503 | 0.6206 | 0.6754 | 0.7265 | 0.6310 | |
|
| 0.0283 | 8.0 | 1560 | 0.0512 | 0.6199 | 0.6717 | 0.7129 | 0.6349 | |
|
| 0.0283 | 9.0 | 1755 | 0.0515 | 0.6193 | 0.6720 | 0.7228 | 0.6278 | |
|
| 0.0283 | 10.0 | 1950 | 0.0517 | 0.6283 | 0.6777 | 0.7292 | 0.6330 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
