|
--- |
|
base_model: ProsusAI/finbert |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: finbert_flang-bert |
|
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_flang-bert |
|
|
|
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: 0.5591 |
|
- Accuracy: 0.8612 |
|
- F1: 0.8609 |
|
- Precision: 0.8614 |
|
- Recall: 0.8612 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.8272 | 1.0 | 91 | 0.7513 | 0.6849 | 0.6737 | 0.6816 | 0.6849 | |
|
| 0.5021 | 2.0 | 182 | 0.4521 | 0.8346 | 0.8352 | 0.8385 | 0.8346 | |
|
| 0.3117 | 3.0 | 273 | 0.4304 | 0.8440 | 0.8443 | 0.8451 | 0.8440 | |
|
| 0.2461 | 4.0 | 364 | 0.5123 | 0.8346 | 0.8331 | 0.8373 | 0.8346 | |
|
| 0.1517 | 5.0 | 455 | 0.5046 | 0.8393 | 0.8377 | 0.8410 | 0.8393 | |
|
| 0.1005 | 6.0 | 546 | 0.5839 | 0.8502 | 0.8513 | 0.8562 | 0.8502 | |
|
| 0.0847 | 7.0 | 637 | 0.5591 | 0.8612 | 0.8609 | 0.8614 | 0.8612 | |
|
| 0.0984 | 8.0 | 728 | 0.7036 | 0.8268 | 0.8260 | 0.8343 | 0.8268 | |
|
| 0.1664 | 9.0 | 819 | 0.6091 | 0.8346 | 0.8320 | 0.8384 | 0.8346 | |
|
| 0.1215 | 10.0 | 910 | 0.6464 | 0.8393 | 0.8397 | 0.8475 | 0.8393 | |
|
| 0.0881 | 11.0 | 1001 | 0.5982 | 0.8580 | 0.8563 | 0.8591 | 0.8580 | |
|
| 0.0579 | 12.0 | 1092 | 0.6472 | 0.8596 | 0.8593 | 0.8592 | 0.8596 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.1 |
|
|
