|
--- |
|
language: |
|
- mn |
|
license: mit |
|
base_model: xlm-roberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlm-roberta-large-ner-demo |
|
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. --> |
|
|
|
# xlm-roberta-large-ner-demo |
|
|
|
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0976 |
|
- Precision: 0.9340 |
|
- Recall: 0.9404 |
|
- F1: 0.9372 |
|
- Accuracy: 0.9816 |
|
|
|
## 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: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1657 | 1.0 | 477 | 0.0866 | 0.8655 | 0.8978 | 0.8814 | 0.9752 | |
|
| 0.0716 | 2.0 | 954 | 0.0801 | 0.9135 | 0.9283 | 0.9208 | 0.9796 | |
|
| 0.0448 | 3.0 | 1431 | 0.0814 | 0.9244 | 0.9374 | 0.9309 | 0.9805 | |
|
| 0.0283 | 4.0 | 1908 | 0.0870 | 0.9256 | 0.9367 | 0.9311 | 0.9808 | |
|
| 0.017 | 5.0 | 2385 | 0.0976 | 0.9340 | 0.9404 | 0.9372 | 0.9816 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|