metadata
base_model: SALT-NLP/FLANG-ELECTRA
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: FLANG-ELECTRA_roberta-base
results: []
FLANG-ELECTRA_roberta-base
This model is a fine-tuned version of SALT-NLP/FLANG-ELECTRA on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4678
- Accuracy: 0.8736
- F1: 0.8728
- Precision: 0.8738
- Recall: 0.8736
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 |
|---|---|---|---|---|---|---|---|
| 0.6813 | 1.0 | 181 | 0.5968 | 0.7457 | 0.7326 | 0.7488 | 0.7457 |
| 0.4427 | 2.0 | 362 | 0.5072 | 0.8222 | 0.8200 | 0.8321 | 0.8222 |
| 0.2366 | 3.0 | 543 | 0.4216 | 0.8518 | 0.8509 | 0.8523 | 0.8518 |
| 0.2022 | 4.0 | 724 | 0.5838 | 0.8518 | 0.8501 | 0.8526 | 0.8518 |
| 0.1299 | 5.0 | 905 | 0.4678 | 0.8736 | 0.8728 | 0.8738 | 0.8736 |
| 0.2016 | 6.0 | 1086 | 0.5147 | 0.8362 | 0.8346 | 0.8355 | 0.8362 |
| 0.1255 | 7.0 | 1267 | 0.6612 | 0.8471 | 0.8438 | 0.8549 | 0.8471 |
| 0.1713 | 8.0 | 1448 | 0.8831 | 0.8003 | 0.7992 | 0.8107 | 0.8003 |
| 0.092 | 9.0 | 1629 | 0.6286 | 0.8440 | 0.8434 | 0.8525 | 0.8440 |
| 0.0476 | 10.0 | 1810 | 0.7429 | 0.8690 | 0.8692 | 0.8697 | 0.8690 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1