netflix_listed_classifier
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0966
- Accuracy: 0.6009
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: 2e-05
- 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: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 317 | 1.2329 | 0.6002 |
| 0.548 | 2.0 | 634 | 1.4183 | 0.5970 |
| 0.548 | 3.0 | 951 | 1.6994 | 0.5868 |
| 0.2387 | 4.0 | 1268 | 1.9693 | 0.5954 |
| 0.1101 | 5.0 | 1585 | 2.2222 | 0.5907 |
| 0.1101 | 6.0 | 1902 | 2.3266 | 0.6128 |
| 0.0633 | 7.0 | 2219 | 2.6788 | 0.5883 |
| 0.0235 | 8.0 | 2536 | 2.7333 | 0.5986 |
| 0.0235 | 9.0 | 2853 | 2.8113 | 0.5978 |
| 0.0128 | 10.0 | 3170 | 2.9943 | 0.5986 |
| 0.0128 | 11.0 | 3487 | 2.9844 | 0.5970 |
| 0.0051 | 12.0 | 3804 | 3.0898 | 0.5899 |
| 0.0039 | 13.0 | 4121 | 3.0445 | 0.6025 |
| 0.0039 | 14.0 | 4438 | 3.0800 | 0.6009 |
| 0.002 | 15.0 | 4755 | 3.1041 | 0.6017 |
| 0.0017 | 16.0 | 5072 | 3.0966 | 0.6009 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2