<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
netflix_rating_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: 3.7214
- Accuracy: 0.4921
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 | 1.2448 | 0.4692 |
1.2581 | 2.0 | 634 | 1.1866 | 0.4976 |
1.2581 | 3.0 | 951 | 1.2496 | 0.4968 |
0.9032 | 4.0 | 1268 | 1.3886 | 0.5024 |
0.511 | 5.0 | 1585 | 1.6567 | 0.4842 |
0.511 | 6.0 | 1902 | 1.9508 | 0.4858 |
0.2425 | 7.0 | 2219 | 2.2587 | 0.4921 |
0.1197 | 8.0 | 2536 | 2.5835 | 0.4819 |
0.1197 | 9.0 | 2853 | 2.9177 | 0.4921 |
0.0571 | 10.0 | 3170 | 3.2303 | 0.4803 |
0.0571 | 11.0 | 3487 | 3.3902 | 0.4787 |
0.0245 | 12.0 | 3804 | 3.5701 | 0.4826 |
0.0124 | 13.0 | 4121 | 3.6457 | 0.4756 |
0.0124 | 14.0 | 4438 | 3.6836 | 0.4937 |
0.0112 | 15.0 | 4755 | 3.7015 | 0.4897 |
0.0073 | 16.0 | 5072 | 3.7214 | 0.4921 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2