distilbert-base-uncased-finetuned-ft1500_norm300_aug9
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0639
- Mse: 4.2557
- Mae: 1.3660
- R2: 0.4773
- Accuracy: 0.3664
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|---|---|
| 0.7595 | 1.0 | 3242 | 1.1009 | 4.4036 | 1.4148 | 0.4591 | 0.3440 |
| 0.6024 | 2.0 | 6484 | 1.0896 | 4.3582 | 1.3732 | 0.4647 | 0.3690 |
| 0.3745 | 3.0 | 9726 | 1.0639 | 4.2557 | 1.3660 | 0.4773 | 0.3664 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1