bert_base_train
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: 5.7322
- Accuracy: 0.1561
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: 96
- eval_batch_size: 96
- seed: 10
- optimizer: Use OptimizerNames.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 |
|---|---|---|---|---|
| 6.0295 | 4.1982 | 10000 | 5.9747 | 0.1518 |
| 5.8426 | 8.3963 | 20000 | 5.8500 | 0.1529 |
| 5.767 | 12.5945 | 30000 | 5.8018 | 0.1552 |
| 5.7154 | 16.7926 | 40000 | 5.7855 | 0.1538 |
| 5.6864 | 20.9908 | 50000 | 5.7779 | 0.1527 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1