---
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: 0.7045454545454546
---

<!-- 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: 1.7474
- Accuracy: 0.7045

## 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: 0.0002
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6755        | 0.33  | 20   | 1.4948          | 0.3709   |
| 0.4585        | 0.66  | 40   | 0.9705          | 0.6147   |
| 0.4267        | 0.98  | 60   | 1.2383          | 0.6012   |
| 0.3298        | 1.31  | 80   | 1.0040          | 0.5764   |
| 0.2955        | 1.64  | 100  | 1.4078          | 0.4845   |
| 0.2521        | 1.97  | 120  | 1.2183          | 0.5702   |
| 0.1614        | 2.3   | 140  | 1.4761          | 0.6570   |
| 0.1842        | 2.62  | 160  | 1.8172          | 0.6002   |
| 0.2124        | 2.95  | 180  | 0.9596          | 0.7211   |
| 0.1016        | 3.28  | 200  | 1.3150          | 0.6952   |
| 0.0949        | 3.61  | 220  | 1.5779          | 0.6498   |
| 0.102         | 3.93  | 240  | 1.9178          | 0.5775   |
| 0.0542        | 4.26  | 260  | 2.0914          | 0.6074   |
| 0.059         | 4.59  | 280  | 1.7965          | 0.6560   |
| 0.0578        | 4.92  | 300  | 2.0358          | 0.5279   |
| 0.0335        | 5.25  | 320  | 1.5614          | 0.6829   |
| 0.0414        | 5.57  | 340  | 1.8126          | 0.6405   |
| 0.0263        | 5.9   | 360  | 1.4405          | 0.6798   |
| 0.0257        | 6.23  | 380  | 1.0230          | 0.7417   |
| 0.0123        | 6.56  | 400  | 1.9126          | 0.6818   |
| 0.0218        | 6.89  | 420  | 1.8622          | 0.6860   |
| 0.0063        | 7.21  | 440  | 2.0173          | 0.6705   |
| 0.014         | 7.54  | 460  | 1.9129          | 0.6870   |
| 0.0037        | 7.87  | 480  | 1.7622          | 0.7035   |
| 0.0155        | 8.2   | 500  | 1.7379          | 0.7004   |
| 0.0087        | 8.52  | 520  | 1.7150          | 0.6994   |
| 0.0055        | 8.85  | 540  | 1.7286          | 0.7025   |
| 0.0051        | 9.18  | 560  | 1.7418          | 0.7014   |
| 0.0049        | 9.51  | 580  | 1.7468          | 0.7035   |
| 0.0056        | 9.84  | 600  | 1.7474          | 0.7045   |


### Framework versions

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