metadata
license: mit
base_model: prajjwal1/bert-tiny
tags:
- generated_from_trainer
model-index:
- name: bert-tiny-domain-adapted-imdb
results: []
datasets:
- imdb
language:
- en
metrics:
- perplexity
pipeline_tag: fill-mask
widget:
- text: This is a great [MASK].
example_title: Example
bert-tiny-domain-adapted-imdb
This model is a fine-tuned version of prajjwal1/bert-tiny on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 3.6873
- Perplexity: 39.94
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.1563 | 1.0 | 782 | 3.7462 |
| 4.0555 | 2.0 | 1564 | 3.6977 |
| 4.0285 | 3.0 | 2346 | 3.6963 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2