nlp-mini-prj
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
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: 5e-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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0841 | 3.76 | 500 | 0.0005 |
| 0.0015 | 7.52 | 1000 | 0.0002 |
| 0.0011 | 11.28 | 1500 | 0.0001 |
| 0.0042 | 15.04 | 2000 | 0.0001 |
| 0.0008 | 18.8 | 2500 | 0.0001 |
| 0.0004 | 22.56 | 3000 | 0.0001 |
| 0.0001 | 26.32 | 3500 | 0.0000 |
| 0.0001 | 30.08 | 4000 | 0.0000 |
| 0.0001 | 33.83 | 4500 | 0.0000 |
| 0.0001 | 37.59 | 5000 | 0.0000 |
| 0.0 | 41.35 | 5500 | 0.0000 |
| 0.0 | 45.11 | 6000 | 0.0000 |
| 0.0 | 48.87 | 6500 | 0.0000 |
| 0.0 | 52.63 | 7000 | 0.0000 |
| 0.0 | 56.39 | 7500 | 0.0000 |
| 0.0 | 60.15 | 8000 | 0.0000 |
| 0.0 | 63.91 | 8500 | 0.0000 |
| 0.0 | 67.67 | 9000 | 0.0000 |
| 0.0 | 71.43 | 9500 | 0.0000 |
| 0.0 | 75.19 | 10000 | 0.0000 |
| 0.0 | 78.95 | 10500 | 0.0000 |
| 0.0 | 82.71 | 11000 | 0.0000 |
| 0.0 | 86.47 | 11500 | 0.0000 |
| 0.0 | 90.23 | 12000 | 0.0000 |
| 0.0 | 93.98 | 12500 | 0.0000 |
| 0.0 | 97.74 | 13000 | 0.0000 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 1