distilbert-base-uncased_latest_Nov2023
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: 0.3732
- Accuracy: 0.746
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.654 | 0.2 | 100 | 0.5822 | 0.564 |
0.5426 | 0.4 | 200 | 0.4772 | 0.7125 |
0.4676 | 0.6 | 300 | 0.4183 | 0.724 |
0.4283 | 0.8 | 400 | 0.4053 | 0.715 |
0.4192 | 1.0 | 500 | 0.3918 | 0.7285 |
0.4063 | 1.2 | 600 | 0.3871 | 0.734 |
0.3752 | 1.4 | 700 | 0.3873 | 0.747 |
0.3779 | 1.6 | 800 | 0.3734 | 0.749 |
0.357 | 1.8 | 900 | 0.3754 | 0.736 |
0.3359 | 2.0 | 1000 | 0.3732 | 0.746 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 9