|
--- |
|
base_model: vinai/bertweet-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- recall |
|
model-index: |
|
- name: bertweet-base |
|
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. --> |
|
|
|
# bertweet-base |
|
|
|
This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5822 |
|
- F1 Macro: 0.7750 |
|
- F1: 0.8571 |
|
- F1 Neg: 0.6929 |
|
- Acc: 0.805 |
|
- Prec: 0.8069 |
|
- Recall: 0.9141 |
|
- Mcc: 0.5646 |
|
|
|
## 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 |
|
- distributed_type: multi-GPU |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:| |
|
| 0.6482 | 1.0 | 600 | 0.5610 | 0.6822 | 0.8022 | 0.5622 | 0.7275 | 0.7492 | 0.8633 | 0.3812 | |
|
| 0.5567 | 2.0 | 1200 | 0.5125 | 0.7382 | 0.8364 | 0.64 | 0.775 | 0.7823 | 0.8984 | 0.4938 | |
|
| 0.4549 | 3.0 | 1800 | 0.6164 | 0.7195 | 0.7588 | 0.6802 | 0.725 | 0.865 | 0.6758 | 0.4688 | |
|
| 0.4021 | 4.0 | 2400 | 0.5785 | 0.7344 | 0.7875 | 0.6812 | 0.745 | 0.8438 | 0.7383 | 0.4789 | |
|
| 0.3159 | 5.0 | 3000 | 0.5822 | 0.7750 | 0.8571 | 0.6929 | 0.805 | 0.8069 | 0.9141 | 0.5646 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
