tiny-mlm-glue-cola-custom-tokenizer
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: nan
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: 3e-05
- 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: constant
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.2575 | 0.47 | 500 | 6.4792 |
| 6.4145 | 0.94 | 1000 | 6.4699 |
| 6.2252 | 1.4 | 1500 | 6.5489 |
| 6.0413 | 1.87 | 2000 | 6.3427 |
| 5.8394 | 2.34 | 2500 | 6.2134 |
| 5.825 | 2.81 | 3000 | nan |
| 5.8071 | 3.27 | 3500 | 6.1627 |
| 5.6601 | 3.74 | 4000 | 6.0835 |
| 5.686 | 4.21 | 4500 | 6.0319 |
| 5.6029 | 4.68 | 5000 | 5.9500 |
| 5.5236 | 5.14 | 5500 | 5.9621 |
| 5.586 | 5.61 | 6000 | 5.8955 |
| 5.5582 | 6.08 | 6500 | 6.0435 |
| 5.412 | 6.55 | 7000 | 6.0175 |
| 5.397 | 7.02 | 7500 | nan |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2