|
--- |
|
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: 0.7965 |
|
- F1 Macro: 0.8142 |
|
- F1: 0.8639 |
|
- F1 Neg: 0.7645 |
|
- Acc: 0.8275 |
|
- Prec: 0.8725 |
|
- Recall: 0.8555 |
|
- Mcc: 0.6287 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:| |
|
| 0.6396 | 1.0 | 614 | 0.6126 | 0.7238 | 0.7652 | 0.6824 | 0.73 | 0.8627 | 0.6875 | 0.4734 | |
|
| 0.4753 | 2.0 | 1228 | 0.5095 | 0.8057 | 0.8669 | 0.7445 | 0.825 | 0.8444 | 0.8906 | 0.6138 | |
|
| 0.3965 | 3.0 | 1842 | 0.7932 | 0.7358 | 0.8527 | 0.6188 | 0.7875 | 0.7664 | 0.9609 | 0.5306 | |
|
| 0.3534 | 4.0 | 2456 | 0.8950 | 0.7831 | 0.8140 | 0.7522 | 0.7875 | 0.9254 | 0.7266 | 0.5975 | |
|
| 0.2284 | 5.0 | 3070 | 0.7965 | 0.8142 | 0.8639 | 0.7645 | 0.8275 | 0.8725 | 0.8555 | 0.6287 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
