|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- wnut_17 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
base_model: xlm-roberta-large |
|
model-index: |
|
- name: xlm-roberta-large-WNUT-ner |
|
results: |
|
- task: |
|
type: token-classification |
|
name: Token Classification |
|
dataset: |
|
name: wnut_17 |
|
type: wnut_17 |
|
config: wnut_17 |
|
split: test |
|
args: wnut_17 |
|
metrics: |
|
- type: precision |
|
value: 0.7013977128335451 |
|
name: Precision |
|
- type: recall |
|
value: 0.5115848007414272 |
|
name: Recall |
|
- type: f1 |
|
value: 0.5916398713826366 |
|
name: F1 |
|
- type: accuracy |
|
value: 0.9570402667350603 |
|
name: Accuracy |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# xlm-roberta-large-WNUT-ner |
|
|
|
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the wnut_17 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3570 |
|
- Precision: 0.7014 |
|
- Recall: 0.5116 |
|
- F1: 0.5916 |
|
- Accuracy: 0.9570 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | 213 | 0.2223 | 0.5588 | 0.4495 | 0.4982 | 0.9504 | |
|
| No log | 2.0 | 426 | 0.2326 | 0.6602 | 0.4430 | 0.5302 | 0.9514 | |
|
| 0.1516 | 3.0 | 639 | 0.2792 | 0.6846 | 0.4124 | 0.5147 | 0.9520 | |
|
| 0.1516 | 4.0 | 852 | 0.2417 | 0.6510 | 0.5134 | 0.5741 | 0.9574 | |
|
| 0.0427 | 5.0 | 1065 | 0.2954 | 0.6850 | 0.4856 | 0.5683 | 0.9544 | |
|
| 0.0427 | 6.0 | 1278 | 0.3033 | 0.6761 | 0.4893 | 0.5677 | 0.9557 | |
|
| 0.0427 | 7.0 | 1491 | 0.3502 | 0.7007 | 0.4838 | 0.5724 | 0.9563 | |
|
| 0.0178 | 8.0 | 1704 | 0.3712 | 0.6995 | 0.4875 | 0.5745 | 0.9563 | |
|
| 0.0178 | 9.0 | 1917 | 0.3541 | 0.6951 | 0.4986 | 0.5807 | 0.9569 | |
|
| 0.0068 | 10.0 | 2130 | 0.3570 | 0.7014 | 0.5116 | 0.5916 | 0.9570 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|
