metadata
library_name: transformers
license: mit
base_model: prajjwal1/bert-tiny
tags:
- generated_from_trainer
model-index:
- name: results_tinybert
results: []
results_tinybert
This model is a fine-tuned version of prajjwal1/bert-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1869
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: 16
- eval_batch_size: 16
- seed: 42
- 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: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.22 | 1.0 | 1399 | 0.1804 |
| 0.1415 | 2.0 | 2798 | 0.1627 |
| 0.1872 | 3.0 | 4197 | 0.1736 |
| 0.1603 | 4.0 | 5596 | 0.1807 |
| 0.1039 | 5.0 | 6995 | 0.1869 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Tokenizers 0.21.1