my_awesome_model
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: 1.3247
- Accuracy: 0.8114
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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 350 | 0.4073 | 0.8069 |
| 0.4154 | 2.0 | 700 | 0.4134 | 0.8192 |
| 0.2369 | 3.0 | 1050 | 0.4933 | 0.8133 |
| 0.2369 | 4.0 | 1400 | 0.7105 | 0.7994 |
| 0.1121 | 5.0 | 1750 | 1.0014 | 0.7881 |
| 0.0633 | 6.0 | 2100 | 1.0510 | 0.8036 |
| 0.0633 | 7.0 | 2450 | 1.1647 | 0.8074 |
| 0.0331 | 8.0 | 2800 | 1.2433 | 0.8012 |
| 0.0205 | 9.0 | 3150 | 1.3184 | 0.8055 |
| 0.0107 | 10.0 | 3500 | 1.3247 | 0.8114 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3