---
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-finetuned-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. -->

# roberta-finetuned-ner

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1322
- Precision: 0.9772
- Recall: 0.9782
- F1: 0.9777
- Accuracy: 0.9767

## 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: 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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 253  | 0.1694          | 0.9636    | 0.9555 | 0.9595 | 0.9617   |
| 0.4479        | 2.0   | 506  | 0.1374          | 0.9743    | 0.9762 | 0.9752 | 0.9743   |
| 0.4479        | 3.0   | 759  | 0.1322          | 0.9772    | 0.9782 | 0.9777 | 0.9767   |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6