<!-- 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. -->
finetuning-sentiment-model-20000-samples-imdb-v2
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: 0.3694
- Accuracy: 0.924
- F1: 0.9242
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2795 | 1.0 | 2500 | 0.2224 | 0.9275 | 0.9263 |
| 0.1877 | 2.0 | 5000 | 0.3141 | 0.9275 | 0.9274 |
| 0.1045 | 3.0 | 7500 | 0.3694 | 0.924 | 0.9242 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
