Goodreads_Books_Reviews_BERT_50
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9665
- F1: 0.6343
- Accuracy: 0.6343
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| 0.9881 | 1.0 | 4219 | 0.9548 | 0.6185 | 0.6183 |
| 0.8735 | 2.0 | 8438 | 0.9506 | 0.6278 | 0.626 |
| 0.7147 | 3.0 | 12657 | 0.9665 | 0.6343 | 0.6343 |
| 0.6294 | 4.0 | 16876 | 1.0249 | 0.6341 | 0.6334 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1