distilbert-finance / README.md
IngeniousArtist's picture
update model card README.md
7158dee
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- financial_phrasebank
metrics:
- accuracy
model-index:
- name: distilbert-finance
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: financial_phrasebank
type: financial_phrasebank
config: sentences_50agree
split: train
args: sentences_50agree
metrics:
- name: Accuracy
type: accuracy
value: 0.7386363636363636
---
<!-- 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. -->
# distilbert-finance
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the financial_phrasebank dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9962
- Accuracy: 0.7386
## 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: 2e-05
- 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: cosine
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.904 | 0.33 | 20 | 1.5959 | 0.4205 |
| 0.6562 | 0.66 | 40 | 1.6665 | 0.4143 |
| 0.539 | 0.98 | 60 | 1.6067 | 0.3936 |
| 0.4759 | 1.31 | 80 | 1.5079 | 0.4236 |
| 0.3882 | 1.64 | 100 | 1.4719 | 0.4298 |
| 0.3782 | 1.97 | 120 | 1.2392 | 0.4267 |
| 0.2729 | 2.3 | 140 | 1.0114 | 0.4928 |
| 0.2607 | 2.62 | 160 | 0.9514 | 0.5930 |
| 0.2889 | 2.95 | 180 | 0.8661 | 0.6477 |
| 0.181 | 3.28 | 200 | 0.7093 | 0.7417 |
| 0.1742 | 3.61 | 220 | 1.1042 | 0.5764 |
| 0.1904 | 3.93 | 240 | 0.7439 | 0.7510 |
| 0.1186 | 4.26 | 260 | 0.8587 | 0.7469 |
| 0.137 | 4.59 | 280 | 0.7408 | 0.7603 |
| 0.1166 | 4.92 | 300 | 1.0107 | 0.6705 |
| 0.0938 | 5.25 | 320 | 0.7883 | 0.7624 |
| 0.0881 | 5.57 | 340 | 1.0339 | 0.7056 |
| 0.0812 | 5.9 | 360 | 0.8409 | 0.7490 |
| 0.0586 | 6.23 | 380 | 0.9146 | 0.7345 |
| 0.0572 | 6.56 | 400 | 0.9000 | 0.7366 |
| 0.0527 | 6.89 | 420 | 0.9782 | 0.7335 |
| 0.045 | 7.21 | 440 | 1.0102 | 0.7262 |
| 0.0471 | 7.54 | 460 | 1.0322 | 0.7324 |
| 0.0508 | 7.87 | 480 | 0.9381 | 0.7448 |
| 0.039 | 8.2 | 500 | 0.9489 | 0.7459 |
| 0.0419 | 8.52 | 520 | 0.9779 | 0.7469 |
| 0.0256 | 8.85 | 540 | 0.9834 | 0.7407 |
| 0.0264 | 9.18 | 560 | 0.9963 | 0.7376 |
| 0.0378 | 9.51 | 580 | 0.9981 | 0.7376 |
| 0.0421 | 9.84 | 600 | 0.9962 | 0.7386 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3