<!-- 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. -->
bert-finetuned-promo
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0383
- Mse: 0.0383
- Mae: 0.0466
- R2: 0.9586
- Accuracy: 0.9839
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.57 | 1.0 | 950 | 0.1458 | 0.1458 | 0.1299 | 0.8426 | 0.9335 |
| 0.0698 | 2.0 | 1900 | 0.0514 | 0.0514 | 0.0578 | 0.9445 | 0.9664 |
| 0.0306 | 3.0 | 2850 | 0.0383 | 0.0383 | 0.0466 | 0.9586 | 0.9839 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
