|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: finbert-finetuned-FG-SINGLE_SENTENCE-NEWS |
|
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. --> |
|
|
|
# finbert-finetuned-FG-SINGLE_SENTENCE-NEWS |
|
|
|
This model is a fine-tuned version of [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.0147 |
|
- Accuracy: 0.5361 |
|
- F1: 0.5346 |
|
|
|
## 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: 6e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 1.0 | 198 | 1.0442 | 0.4616 | 0.4093 | |
|
| No log | 2.0 | 396 | 1.0938 | 0.4875 | 0.4455 | |
|
| 0.9778 | 3.0 | 594 | 1.1884 | 0.5247 | 0.5161 | |
|
| 0.9778 | 4.0 | 792 | 1.3903 | 0.5338 | 0.5290 | |
|
| 0.9778 | 5.0 | 990 | 1.5180 | 0.5452 | 0.5430 | |
|
| 0.3904 | 6.0 | 1188 | 1.8556 | 0.5270 | 0.5273 | |
|
| 0.3904 | 7.0 | 1386 | 2.1461 | 0.5376 | 0.5386 | |
|
| 0.142 | 8.0 | 1584 | 2.4582 | 0.5529 | 0.5489 | |
|
| 0.142 | 9.0 | 1782 | 2.6054 | 0.5255 | 0.5247 | |
|
| 0.142 | 10.0 | 1980 | 2.7953 | 0.5544 | 0.5483 | |
|
| 0.0797 | 11.0 | 2178 | 3.0892 | 0.5308 | 0.5315 | |
|
| 0.0797 | 12.0 | 2376 | 3.3025 | 0.5384 | 0.5315 | |
|
| 0.0415 | 13.0 | 2574 | 3.3124 | 0.5308 | 0.5249 | |
|
| 0.0415 | 14.0 | 2772 | 3.6247 | 0.5331 | 0.5322 | |
|
| 0.0415 | 15.0 | 2970 | 3.6592 | 0.5224 | 0.5252 | |
|
| 0.024 | 16.0 | 3168 | 3.8275 | 0.5308 | 0.5290 | |
|
| 0.024 | 17.0 | 3366 | 3.8818 | 0.5308 | 0.5295 | |
|
| 0.009 | 18.0 | 3564 | 3.9417 | 0.5407 | 0.5375 | |
|
| 0.009 | 19.0 | 3762 | 4.0033 | 0.5361 | 0.5339 | |
|
| 0.009 | 20.0 | 3960 | 4.0147 | 0.5361 | 0.5346 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.16.2 |
|
- Pytorch 1.9.1 |
|
- Datasets 1.18.4 |
|
- Tokenizers 0.11.6 |
|
|
