neuroapps_sentiment_classifier
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: 0.2332
- Accuracy: 0.9319
Model description
This model outputs the sentiment value, either positive or negative from the sentence or phrase.
Intended uses & limitations
This model could be used for extracting sentiments from product reviews, product feedback, or general conversational text.
Training and evaluation data
his model is a fine-tuned version of distilbert-base-uncased on the imdb dataset.
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2335 | 1.0 | 1563 | 0.1892 | 0.9277 |
| 0.1487 | 2.0 | 3126 | 0.2332 | 0.9319 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
