tinybert_train_book_ent_15p_inv_wnli
This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_ent_15p_inv on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6957
- Accuracy: 0.5634
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.699 | 1.0 | 3 | 0.6957 | 0.5634 |
| 0.7035 | 2.0 | 6 | 0.7015 | 0.4930 |
| 0.6971 | 3.0 | 9 | 0.7234 | 0.4366 |
| 0.6922 | 4.0 | 12 | 0.7078 | 0.3944 |
| 0.6951 | 5.0 | 15 | 0.7077 | 0.5070 |
| 0.6934 | 6.0 | 18 | 0.7230 | 0.3380 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3