|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: twiiter_try15_fold4 |
|
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_fold4 |
|
|
|
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: 0.1791 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.2113 | 1.0 | 500 | 0.1149 | 0.9642 | |
|
| 0.0638 | 2.0 | 1000 | 0.1456 | 0.9646 | |
|
| 0.0179 | 3.0 | 1500 | 0.1507 | 0.9737 | |
|
| 0.0171 | 4.0 | 2000 | 0.1835 | 0.9737 | |
|
| 0.0096 | 5.0 | 2500 | 0.2713 | 0.9613 | |
|
| 0.0072 | 6.0 | 3000 | 0.2221 | 0.9695 | |
|
| 0.0073 | 7.0 | 3500 | 0.1639 | 0.9775 | |
|
| 0.0049 | 8.0 | 4000 | 0.2184 | 0.9737 | |
|
| 0.0018 | 9.0 | 4500 | 0.2568 | 0.9723 | |
|
| 0.0062 | 10.0 | 5000 | 0.2106 | 0.9753 | |
|
| 0.0001 | 11.0 | 5500 | 0.2204 | 0.9763 | |
|
| 0.0 | 12.0 | 6000 | 0.2195 | 0.9761 | |
|
| 0.0015 | 13.0 | 6500 | 0.1732 | 0.9795 | |
|
| 0.0 | 14.0 | 7000 | 0.1739 | 0.9810 | |
|
| 0.0011 | 15.0 | 7500 | 0.1791 | 0.9805 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
