|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: BERT_Text_classification_clean |
|
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. --> |
|
|
|
# BERT_Text_classification_clean |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5208 |
|
- Accuracy: 0.9028 |
|
- F1: 0.8924 |
|
- Precision: 0.8990 |
|
- Recall: 0.8925 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.6803 | 0.24 | 50 | 1.2419 | 0.7613 | 0.7374 | 0.7493 | 0.7460 | |
|
| 0.6367 | 0.48 | 100 | 0.4523 | 0.8437 | 0.8358 | 0.8377 | 0.8357 | |
|
| 0.2756 | 0.71 | 150 | 0.4543 | 0.8625 | 0.8550 | 0.8576 | 0.8544 | |
|
| 0.2569 | 0.95 | 200 | 0.4377 | 0.8845 | 0.8715 | 0.8791 | 0.8727 | |
|
| 0.1044 | 1.19 | 250 | 0.5032 | 0.8903 | 0.8793 | 0.8828 | 0.8795 | |
|
| 0.0745 | 1.43 | 300 | 0.5342 | 0.8912 | 0.8791 | 0.8881 | 0.8798 | |
|
| 0.0906 | 1.67 | 350 | 0.5484 | 0.8992 | 0.8880 | 0.8956 | 0.8886 | |
|
| 0.0839 | 1.9 | 400 | 0.5337 | 0.8939 | 0.8827 | 0.8858 | 0.8830 | |
|
| 0.0474 | 2.14 | 450 | 0.5237 | 0.8983 | 0.8876 | 0.8938 | 0.8879 | |
|
| 0.0346 | 2.38 | 500 | 0.4822 | 0.9037 | 0.8939 | 0.9005 | 0.8939 | |
|
| 0.0243 | 2.62 | 550 | 0.5014 | 0.9019 | 0.8916 | 0.8964 | 0.8917 | |
|
| 0.0181 | 2.86 | 600 | 0.5208 | 0.9028 | 0.8924 | 0.8990 | 0.8925 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.2 |
|
|
