---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-expense-ner
  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. -->

# distilbert-expense-ner

This model is a fine-tuned version of [Geotrend/distilbert-base-en-fr-de-no-da-cased](https://huggingface.co/Geotrend/distilbert-base-en-fr-de-no-da-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2115
- Precision: 0.9383
- Recall: 0.9345
- F1: 0.9364
- Accuracy: 0.9565

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 100  | 0.3620          | 0.8830    | 0.8673 | 0.8751 | 0.9167   |
| No log        | 2.0   | 200  | 0.2250          | 0.9176    | 0.9094 | 0.9134 | 0.9405   |
| No log        | 3.0   | 300  | 0.2174          | 0.9234    | 0.9167 | 0.9200 | 0.9433   |
| No log        | 4.0   | 400  | 0.2214          | 0.9213    | 0.9183 | 0.9198 | 0.9428   |
| 0.3742        | 5.0   | 500  | 0.2099          | 0.9241    | 0.9264 | 0.9253 | 0.9474   |
| 0.3742        | 6.0   | 600  | 0.1900          | 0.9412    | 0.9328 | 0.9370 | 0.9597   |
| 0.3742        | 7.0   | 700  | 0.2174          | 0.9318    | 0.9280 | 0.9299 | 0.9515   |
| 0.3742        | 8.0   | 800  | 0.1941          | 0.9360    | 0.9353 | 0.9357 | 0.9584   |
| 0.3742        | 9.0   | 900  | 0.2157          | 0.9368    | 0.9361 | 0.9365 | 0.9565   |
| 0.0315        | 10.0  | 1000 | 0.2115          | 0.9383    | 0.9345 | 0.9364 | 0.9565   |


### Framework versions

- Transformers 4.19.1
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1