|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: finetuned_distilbert_fa_zwnj_base_ner |
|
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. --> |
|
|
|
# finetuned_distilbert_fa_zwnj_base_ner |
|
|
|
This model is a fine-tuned version of [HooshvareLab/distilbert-fa-zwnj-base](https://huggingface.co/HooshvareLab/distilbert-fa-zwnj-base) on the mixed NER dataset collected from ARMAN, PEYMA, and WikiANN. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0343 |
|
- Precision: 0.9416 |
|
- Recall: 0.9549 |
|
- F1: 0.9482 |
|
- Accuracy: 0.9938 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1456 | 1.0 | 1821 | 0.0699 | 0.7847 | 0.8037 | 0.7941 | 0.9773 | |
|
| 0.0551 | 2.0 | 3642 | 0.0456 | 0.8574 | 0.8875 | 0.8722 | 0.9858 | |
|
| 0.0283 | 3.0 | 5463 | 0.0333 | 0.8957 | 0.9225 | 0.9089 | 0.9902 | |
|
| 0.0161 | 4.0 | 7284 | 0.0299 | 0.9229 | 0.9374 | 0.9301 | 0.9921 | |
|
| 0.0103 | 5.0 | 9105 | 0.0298 | 0.9314 | 0.9471 | 0.9392 | 0.9929 | |
|
| 0.0069 | 6.0 | 10926 | 0.0323 | 0.9305 | 0.9513 | 0.9408 | 0.9930 | |
|
| 0.0045 | 7.0 | 12747 | 0.0337 | 0.9363 | 0.9510 | 0.9436 | 0.9933 | |
|
| 0.0031 | 8.0 | 14568 | 0.0339 | 0.9395 | 0.9526 | 0.9460 | 0.9937 | |
|
| 0.0024 | 9.0 | 16389 | 0.0334 | 0.9392 | 0.9545 | 0.9468 | 0.9938 | |
|
| 0.0017 | 10.0 | 18210 | 0.0343 | 0.9416 | 0.9549 | 0.9482 | 0.9938 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.2 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
