|
--- |
|
language: |
|
- mn |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilbert-base-multilingual-cased-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. --> |
|
|
|
# distilbert-base-multilingual-cased-ner-demo |
|
|
|
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1687 |
|
- Precision: 0.8684 |
|
- Recall: 0.8891 |
|
- F1: 0.8786 |
|
- Accuracy: 0.9693 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2009 | 1.0 | 572 | 0.1271 | 0.8074 | 0.8440 | 0.8253 | 0.9590 | |
|
| 0.0951 | 2.0 | 1144 | 0.1069 | 0.8469 | 0.8768 | 0.8616 | 0.9671 | |
|
| 0.063 | 3.0 | 1716 | 0.1136 | 0.8486 | 0.8783 | 0.8632 | 0.9680 | |
|
| 0.0444 | 4.0 | 2288 | 0.1221 | 0.8506 | 0.8808 | 0.8654 | 0.9675 | |
|
| 0.0303 | 5.0 | 2860 | 0.1389 | 0.8576 | 0.8823 | 0.8698 | 0.9677 | |
|
| 0.0217 | 6.0 | 3432 | 0.1457 | 0.8683 | 0.8878 | 0.8779 | 0.9685 | |
|
| 0.0157 | 7.0 | 4004 | 0.1542 | 0.8661 | 0.8873 | 0.8766 | 0.9692 | |
|
| 0.0121 | 8.0 | 4576 | 0.1615 | 0.8730 | 0.8878 | 0.8803 | 0.9694 | |
|
| 0.0094 | 9.0 | 5148 | 0.1675 | 0.8683 | 0.8883 | 0.8782 | 0.9688 | |
|
| 0.0077 | 10.0 | 5720 | 0.1687 | 0.8684 | 0.8891 | 0.8786 | 0.9693 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
