<!-- 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. -->
distilbert-base-uncased-finetuned-imdb
This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 2.6268
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5545 | 1.0 | 157 | 2.6856 |
| 2.6118 | 2.0 | 314 | 2.6564 |
| 2.6601 | 3.0 | 471 | 2.6587 |
| 2.6754 | 4.0 | 628 | 2.6165 |
| 2.6586 | 5.0 | 785 | 2.6146 |
| 2.6329 | 6.0 | 942 | 2.6220 |
| 2.6282 | 7.0 | 1099 | 2.5967 |
| 2.6281 | 8.0 | 1256 | 2.6424 |
| 2.6074 | 9.0 | 1413 | 2.6141 |
| 2.6061 | 10.0 | 1570 | 2.5978 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
