|
--- |
|
base_model: SALT-NLP/FLANG-ELECTRA |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: FLANG-ELECTRA_bert-base-uncased |
|
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-ELECTRA_bert-base-uncased |
|
|
|
This model is a fine-tuned version of [SALT-NLP/FLANG-ELECTRA](https://huggingface.co/SALT-NLP/FLANG-ELECTRA) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4748 |
|
- Accuracy: 0.8705 |
|
- F1: 0.8705 |
|
- Precision: 0.8705 |
|
- Recall: 0.8705 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.6775 | 1.0 | 181 | 0.5462 | 0.7972 | 0.7894 | 0.7973 | 0.7972 | |
|
| 0.4966 | 2.0 | 362 | 0.3989 | 0.8612 | 0.8612 | 0.8633 | 0.8612 | |
|
| 0.2509 | 3.0 | 543 | 0.3791 | 0.8612 | 0.8620 | 0.8645 | 0.8612 | |
|
| 0.2241 | 4.0 | 724 | 0.5297 | 0.8471 | 0.8471 | 0.8501 | 0.8471 | |
|
| 0.2248 | 5.0 | 905 | 0.4748 | 0.8705 | 0.8705 | 0.8705 | 0.8705 | |
|
| 1.1108 | 6.0 | 1086 | 1.1042 | 0.3245 | 0.1590 | 0.1053 | 0.3245 | |
|
| 1.1122 | 7.0 | 1267 | 1.1028 | 0.3245 | 0.1590 | 0.1053 | 0.3245 | |
|
| 1.102 | 8.0 | 1448 | 1.0987 | 0.3510 | 0.1824 | 0.1232 | 0.3510 | |
|
| 1.1015 | 9.0 | 1629 | 1.1069 | 0.3245 | 0.1590 | 0.1053 | 0.3245 | |
|
| 1.0908 | 10.0 | 1810 | 1.1022 | 0.3510 | 0.1824 | 0.1232 | 0.3510 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.1 |
|
|
