|
--- |
|
language: |
|
- mn |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: mongolian-xlm-roberta-base-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. --> |
|
|
|
# mongolian-xlm-roberta-base-demo |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1177 |
|
- Precision: 0.9262 |
|
- Recall: 0.9332 |
|
- F1: 0.9297 |
|
- Accuracy: 0.9785 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1979 | 1.0 | 477 | 0.1015 | 0.8713 | 0.8958 | 0.8834 | 0.9692 | |
|
| 0.0839 | 2.0 | 954 | 0.0965 | 0.9050 | 0.9125 | 0.9088 | 0.9743 | |
|
| 0.0604 | 3.0 | 1431 | 0.0844 | 0.9217 | 0.9258 | 0.9237 | 0.9771 | |
|
| 0.0455 | 4.0 | 1908 | 0.0955 | 0.9154 | 0.9283 | 0.9218 | 0.9774 | |
|
| 0.0337 | 5.0 | 2385 | 0.0923 | 0.9228 | 0.9318 | 0.9273 | 0.9787 | |
|
| 0.0254 | 6.0 | 2862 | 0.1055 | 0.9213 | 0.9303 | 0.9258 | 0.9776 | |
|
| 0.02 | 7.0 | 3339 | 0.1075 | 0.9244 | 0.9329 | 0.9286 | 0.9785 | |
|
| 0.0149 | 8.0 | 3816 | 0.1142 | 0.9262 | 0.9329 | 0.9295 | 0.9788 | |
|
| 0.0126 | 9.0 | 4293 | 0.1149 | 0.9219 | 0.9306 | 0.9262 | 0.9780 | |
|
| 0.01 | 10.0 | 4770 | 0.1177 | 0.9262 | 0.9332 | 0.9297 | 0.9785 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
