20230430-001-baseline-mbert-qa-ft-clickbait-spoiling
This model is a fine-tuned version of intanm/mBERT-squad on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.9090
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 |
|---|---|---|---|
| No log | 1.0 | 200 | 2.8250 |
| No log | 2.0 | 400 | 2.7890 |
| 2.5758 | 3.0 | 600 | 3.0925 |
| 2.5758 | 4.0 | 800 | 3.5365 |
| 1.1707 | 5.0 | 1000 | 3.9249 |
| 1.1707 | 6.0 | 1200 | 4.2093 |
| 1.1707 | 7.0 | 1400 | 4.4076 |
| 0.4982 | 8.0 | 1600 | 4.7308 |
| 0.4982 | 9.0 | 1800 | 4.8659 |
| 0.2732 | 10.0 | 2000 | 4.9090 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3