tinybert_book_ent_15p_b
This model is a fine-tuned version of distilbert-base-uncased on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld dataset. It achieves the following results on the evaluation set:
- Loss: 2.3713
- Accuracy: 0.6418
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: 200
- eval_batch_size: 200
- 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
- lr_scheduler_warmup_steps: 10000
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.2253 | 8.7413 | 10000 | 3.0388 | 0.5513 |
| 2.3768 | 17.4825 | 20000 | 2.3713 | 0.6418 |
Framework versions
- Transformers 4.51.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1