|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-finetuned-ner-synonym-replacement |
|
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. --> |
|
|
|
# bert-finetuned-ner-synonym-replacement |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the combined training dataset(tweetner7(train_2021)+augmented dataset(train_2021) using synonym replacment technique. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4556 |
|
- Precision: 0.6825 |
|
- Recall: 0.6704 |
|
- F1: 0.6764 |
|
- Accuracy: 0.8792 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.5491 | 1.0 | 624 | 0.4161 | 0.7217 | 0.6308 | 0.6732 | 0.8813 | |
|
| 0.3284 | 2.0 | 1248 | 0.4195 | 0.7077 | 0.6485 | 0.6768 | 0.8820 | |
|
| 0.2522 | 3.0 | 1872 | 0.4556 | 0.6825 | 0.6704 | 0.6764 | 0.8792 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.1 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.12.1 |
|
|
