IMDB Sentiment Analysis
This model is a fine-tuned version of google/electra-small-discriminator on the IMDB sentiment dataset. It achieves the following results on the evaluation set:
- Loss: 0.2403
- Accuracy: 0.9314
- F1: 0.9314
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: 0.0002
- train_batch_size: 48
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.3176 | 1.0 | 834 | 0.2002 | 0.9228 | 0.9228 |
| 0.1522 | 2.0 | 1668 | 0.2017 | 0.9281 | 0.9281 |
| 0.073 | 3.0 | 2502 | 0.2403 | 0.9314 | 0.9314 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cpu
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 3