|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: banking77-text-classification |
|
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. --> |
|
|
|
# banking77-text-classification |
|
|
|
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: 0.4686 |
|
- F1: 0.8989 |
|
- Accuracy: 0.9054 |
|
|
|
## 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: 32 |
|
- 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 | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:| |
|
| 3.9638 | 0.46 | 100 | 3.1616 | 0.3449 | 0.4205 | |
|
| 2.5608 | 0.91 | 200 | 1.9064 | 0.6739 | 0.7231 | |
|
| 1.5807 | 1.37 | 300 | 1.2332 | 0.7769 | 0.8111 | |
|
| 1.0547 | 1.83 | 400 | 0.8750 | 0.8433 | 0.8594 | |
|
| 0.7201 | 2.28 | 500 | 0.6806 | 0.8620 | 0.8777 | |
|
| 0.5474 | 2.74 | 600 | 0.5627 | 0.8856 | 0.8970 | |
|
| 0.4168 | 3.2 | 700 | 0.5010 | 0.8884 | 0.8984 | |
|
| 0.3382 | 3.65 | 800 | 0.4686 | 0.8989 | 0.9054 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|