gzipbert_imdb_rpe_250k_v4
This model is a fine-tuned version of versae/gzip-bert on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 3.4034
- Accuracy: 0.4951
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: 1e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0425 | 1.0 | 1563 | 2.5908 | 0.5231 |
| 0.0357 | 2.0 | 3126 | 2.8405 | 0.5343 |
| 0.0291 | 3.0 | 4689 | 2.8759 | 0.5562 |
| 0.0313 | 4.0 | 6252 | 3.1563 | 0.5257 |
| 0.0288 | 5.0 | 7815 | 3.4034 | 0.4951 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 104
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for versae/gzipbert_imdb_rpe_250k_v4
Base model
versae/gzip-bert