|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: training-8 |
|
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. --> |
|
|
|
# training-8 |
|
|
|
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: 0.0308 |
|
- Accuracy: 0.995 |
|
- Precision: 0.9955 |
|
- Recall: 0.9844 |
|
- F1: 0.9899 |
|
|
|
## 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 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| No log | 0.5 | 262 | 0.0687 | 0.9872 | 0.9755 | 0.9733 | 0.9744 | |
|
| No log | 1.0 | 524 | 0.0501 | 0.9906 | 0.9977 | 0.9644 | 0.9808 | |
|
| 0.1015 | 1.5 | 786 | 0.0465 | 0.9928 | 0.9955 | 0.9756 | 0.9854 | |
|
| 0.1015 | 2.0 | 1048 | 0.0440 | 0.9906 | 0.9932 | 0.9689 | 0.9809 | |
|
| 0.0372 | 2.5 | 1310 | 0.0399 | 0.9922 | 0.9955 | 0.9733 | 0.9843 | |
|
| 0.0372 | 2.99 | 1572 | 0.0298 | 0.995 | 0.9955 | 0.9844 | 0.9899 | |
|
| 0.0131 | 3.49 | 1834 | 0.0312 | 0.995 | 0.9955 | 0.9844 | 0.9899 | |
|
| 0.0131 | 3.99 | 2096 | 0.0308 | 0.995 | 0.9955 | 0.9844 | 0.9899 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.2.0.dev20230913+cu121 |
|
- Tokenizers 0.13.3 |
|
|
