---
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: 0.7427685950413223
---

<!-- 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: 0.9820
- Accuracy: 0.7428

## 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: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.905         | 0.33  | 20   | 1.5902          | 0.4205   |
| 0.66          | 0.66  | 40   | 1.6678          | 0.4184   |
| 0.5429        | 0.98  | 60   | 1.6024          | 0.3915   |
| 0.4804        | 1.31  | 80   | 1.5001          | 0.4236   |
| 0.3914        | 1.64  | 100  | 1.4990          | 0.4246   |
| 0.3817        | 1.97  | 120  | 1.3082          | 0.4225   |
| 0.2829        | 2.3   | 140  | 1.0931          | 0.4566   |
| 0.2737        | 2.62  | 160  | 0.9830          | 0.5579   |
| 0.2958        | 2.95  | 180  | 0.8748          | 0.6281   |
| 0.1963        | 3.28  | 200  | 0.7356          | 0.7335   |
| 0.1861        | 3.61  | 220  | 1.0993          | 0.5599   |
| 0.2025        | 3.93  | 240  | 0.7504          | 0.75     |
| 0.1326        | 4.26  | 260  | 0.8450          | 0.7438   |
| 0.1491        | 4.59  | 280  | 0.7221          | 0.7593   |
| 0.1303        | 4.92  | 300  | 0.9738          | 0.6756   |
| 0.109         | 5.25  | 320  | 0.7593          | 0.7634   |
| 0.0994        | 5.57  | 340  | 1.1073          | 0.6632   |
| 0.0969        | 5.9   | 360  | 0.8082          | 0.7479   |
| 0.0697        | 6.23  | 380  | 0.9121          | 0.7242   |
| 0.0635        | 6.56  | 400  | 0.8706          | 0.7490   |
| 0.0637        | 6.89  | 420  | 1.0041          | 0.7221   |
| 0.0561        | 7.21  | 440  | 1.0379          | 0.7035   |
| 0.0577        | 7.54  | 460  | 1.0113          | 0.7180   |
| 0.0612        | 7.87  | 480  | 0.9029          | 0.75     |
| 0.0505        | 8.2   | 500  | 0.9523          | 0.7428   |
| 0.0493        | 8.52  | 520  | 0.9854          | 0.7304   |
| 0.0271        | 8.85  | 540  | 1.0400          | 0.7252   |
| 0.0271        | 9.18  | 560  | 1.0337          | 0.7314   |
| 0.0397        | 9.51  | 580  | 1.0058          | 0.7366   |
| 0.0441        | 9.84  | 600  | 0.9820          | 0.7428   |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3