|
--- |
|
language: |
|
- mn |
|
license: mit |
|
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: 0.1273 |
|
- Precision: 0.8961 |
|
- Recall: 0.9143 |
|
- F1: 0.9051 |
|
- Accuracy: 0.9775 |
|
|
|
## 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: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.4849 | 1.0 | 64 | 0.1678 | 0.7415 | 0.7950 | 0.7673 | 0.9511 | |
|
| 0.1432 | 2.0 | 128 | 0.1370 | 0.8276 | 0.8591 | 0.8430 | 0.9667 | |
|
| 0.096 | 3.0 | 192 | 0.1122 | 0.8096 | 0.8593 | 0.8337 | 0.9685 | |
|
| 0.0607 | 4.0 | 256 | 0.1246 | 0.8550 | 0.8829 | 0.8687 | 0.9725 | |
|
| 0.0363 | 5.0 | 320 | 0.1153 | 0.8878 | 0.9089 | 0.8982 | 0.9768 | |
|
| 0.0228 | 6.0 | 384 | 0.1229 | 0.8974 | 0.9148 | 0.9060 | 0.9775 | |
|
| 0.0147 | 7.0 | 448 | 0.1273 | 0.8961 | 0.9143 | 0.9051 | 0.9775 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
