metadata
base_model: SALT-NLP/FLANG-BERT
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: FLANG-BERT_flang-bert
results: []
FLANG-BERT_flang-bert
This model is a fine-tuned version of SALT-NLP/FLANG-BERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4908
- Accuracy: 0.8487
- F1: 0.8486
- Precision: 0.8489
- Recall: 0.8487
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 |
|---|---|---|---|---|---|---|---|
| 0.8968 | 1.0 | 91 | 0.8147 | 0.6256 | 0.5775 | 0.6185 | 0.6256 |
| 0.5694 | 2.0 | 182 | 0.4893 | 0.8097 | 0.8101 | 0.8124 | 0.8097 |
| 0.3393 | 3.0 | 273 | 0.4303 | 0.8471 | 0.8472 | 0.8474 | 0.8471 |
| 0.2442 | 4.0 | 364 | 0.5042 | 0.8487 | 0.8462 | 0.8512 | 0.8487 |
| 0.1807 | 5.0 | 455 | 0.4908 | 0.8487 | 0.8486 | 0.8489 | 0.8487 |
| 0.1061 | 6.0 | 546 | 0.5168 | 0.8409 | 0.8396 | 0.8405 | 0.8409 |
| 0.1287 | 7.0 | 637 | 0.6537 | 0.8440 | 0.8438 | 0.8470 | 0.8440 |
| 0.1079 | 8.0 | 728 | 0.6641 | 0.8315 | 0.8319 | 0.8345 | 0.8315 |
| 0.0693 | 9.0 | 819 | 0.8833 | 0.8346 | 0.8344 | 0.8363 | 0.8346 |
| 0.1084 | 10.0 | 910 | 0.8721 | 0.7941 | 0.7947 | 0.7972 | 0.7941 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1