---
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- uner_all
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: uner_all
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: uner_all
      type: uner_all
      config: default
      split: None
    metrics:
    - name: Precision
      type: precision
      value: 0.8566170026292725
    - name: Recall
      type: recall
      value: 0.8522846180676665
    - name: F1
      type: f1
      value: 0.8544453186467348
    - name: Accuracy
      type: accuracy
      value: 0.9842612991521463
---

<!-- 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. -->

# uner_all

This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the uner_all dataset.
The uner_all dataset combines all training datasets in UNER.
It achieves the following results on the evaluation set:
- Loss: 0.1180
- Precision: 0.8566
- Recall: 0.8523
- F1: 0.8544
- Accuracy: 0.9843

## 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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0

### Training results



### Framework versions

- Transformers 4.31.0
- Pytorch 1.10.1+cu113
- Datasets 2.14.4
- Tokenizers 0.13.3