|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: twiiter_try15_fold3 |
|
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. --> |
|
|
|
# twiiter_try15_fold3 |
|
|
|
This model is a fine-tuned version of [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1796 |
|
- F1: 0.9805 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.2022 | 1.0 | 500 | 0.1547 | 0.9636 | |
|
| 0.0612 | 2.0 | 1000 | 0.2014 | 0.9660 | |
|
| 0.0211 | 3.0 | 1500 | 0.1204 | 0.9776 | |
|
| 0.0107 | 4.0 | 2000 | 0.1797 | 0.9745 | |
|
| 0.0073 | 5.0 | 2500 | 0.1931 | 0.9752 | |
|
| 0.0128 | 6.0 | 3000 | 0.1808 | 0.9741 | |
|
| 0.0088 | 7.0 | 3500 | 0.1756 | 0.9750 | |
|
| 0.0088 | 8.0 | 4000 | 0.1726 | 0.9781 | |
|
| 0.0012 | 9.0 | 4500 | 0.1707 | 0.9785 | |
|
| 0.0004 | 10.0 | 5000 | 0.1794 | 0.9780 | |
|
| 0.0031 | 11.0 | 5500 | 0.2156 | 0.9743 | |
|
| 0.0012 | 12.0 | 6000 | 0.2106 | 0.9741 | |
|
| 0.0 | 13.0 | 6500 | 0.1925 | 0.9796 | |
|
| 0.0 | 14.0 | 7000 | 0.1903 | 0.9789 | |
|
| 0.0008 | 15.0 | 7500 | 0.1796 | 0.9805 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|