|
--- |
|
base_model: SALT-NLP/FLANG-BERT |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: FLANG-BERT_roberta-base |
|
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. --> |
|
|
|
# FLANG-BERT_roberta-base |
|
|
|
This model is a fine-tuned version of [SALT-NLP/FLANG-BERT](https://huggingface.co/SALT-NLP/FLANG-BERT) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5101 |
|
- Accuracy: 0.8643 |
|
- F1: 0.8637 |
|
- Precision: 0.8638 |
|
- Recall: 0.8643 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.841 | 1.0 | 91 | 0.7542 | 0.6895 | 0.6505 | 0.7281 | 0.6895 | |
|
| 0.4766 | 2.0 | 182 | 0.4469 | 0.8159 | 0.8161 | 0.8201 | 0.8159 | |
|
| 0.3539 | 3.0 | 273 | 0.3916 | 0.8456 | 0.8459 | 0.8473 | 0.8456 | |
|
| 0.2452 | 4.0 | 364 | 0.4667 | 0.8362 | 0.8348 | 0.8369 | 0.8362 | |
|
| 0.1646 | 5.0 | 455 | 0.4408 | 0.8643 | 0.8636 | 0.8643 | 0.8643 | |
|
| 0.1273 | 6.0 | 546 | 0.5101 | 0.8643 | 0.8637 | 0.8638 | 0.8643 | |
|
| 0.1052 | 7.0 | 637 | 0.7249 | 0.8393 | 0.8369 | 0.8413 | 0.8393 | |
|
| 0.0889 | 8.0 | 728 | 0.5791 | 0.8424 | 0.8413 | 0.8419 | 0.8424 | |
|
| 0.0846 | 9.0 | 819 | 0.5522 | 0.8580 | 0.8576 | 0.8577 | 0.8580 | |
|
| 0.0764 | 10.0 | 910 | 0.7277 | 0.8549 | 0.8549 | 0.8555 | 0.8549 | |
|
| 0.1531 | 11.0 | 1001 | 0.6068 | 0.8424 | 0.8407 | 0.8441 | 0.8424 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.1 |
|
|
