<!-- 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. -->
my_awesome_model
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: 0.6268
- Accuracy: 0.5833
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5998 | 1.0 | 6 | 0.7076 | 0.5417 |
0.5384 | 2.0 | 12 | 0.6929 | 0.5417 |
0.4793 | 3.0 | 18 | 0.6850 | 0.5417 |
0.4221 | 4.0 | 24 | 0.6849 | 0.5417 |
0.3747 | 5.0 | 30 | 0.6591 | 0.5417 |
0.3214 | 6.0 | 36 | 0.6371 | 0.5833 |
0.2857 | 7.0 | 42 | 0.6286 | 0.5833 |
0.2549 | 8.0 | 48 | 0.6281 | 0.5833 |
0.2333 | 9.0 | 54 | 0.6290 | 0.5833 |
0.2196 | 10.0 | 60 | 0.6268 | 0.5833 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3