metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_gec_detect
results: []
bert_gec_detect
This model was trained from scratch on the QALB GEC dataset for a binary classification task, which is classifying whether a generated/given text is grammatically sound/correct.
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2169 | 1.0 | 1864 | 0.2219 | 0.9330 |
| 0.1933 | 2.0 | 3728 | 0.2413 | 0.9321 |
| 0.1632 | 3.0 | 5592 | 0.2905 | 0.9295 |
| 0.1323 | 4.0 | 7456 | 0.2807 | 0.9346 |
| 0.1168 | 5.0 | 9320 | 0.3174 | 0.9334 |
| 0.1018 | 6.0 | 11184 | 0.3848 | 0.9346 |
| 0.0688 | 7.0 | 13048 | 0.4739 | 0.9325 |
| 0.0585 | 8.0 | 14912 | 0.4750 | 0.9347 |
| 0.0545 | 9.0 | 16776 | 0.4894 | 0.9337 |
| 0.0497 | 10.0 | 18640 | 0.5135 | 0.9349 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.15.0