metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-imdb
results: []
distilbert-base-uncased-finetuned-imdb
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4294
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 |
|---|---|---|---|
| 2.2498 | 1.0 | 3 | 1.1873 |
| 1.2651 | 2.0 | 6 | 1.2470 |
| 1.1038 | 3.0 | 9 | 0.6763 |
| 0.8357 | 4.0 | 12 | 0.5234 |
| 0.7296 | 5.0 | 15 | 0.4972 |
| 0.6506 | 6.0 | 18 | 0.4935 |
| 0.66 | 7.0 | 21 | 0.4576 |
| 0.5508 | 8.0 | 24 | 0.4905 |
| 0.5088 | 9.0 | 27 | 0.5120 |
| 0.4866 | 10.0 | 30 | 0.4520 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.10.0
- Datasets 2.6.1
- Tokenizers 0.13.2