<!-- 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. -->
Kodwo-Finetuned-distilbert-model
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: 0.6743
- Accuracy: 0.7499
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: 1e-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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.8463 | 0.5 | 500 | 0.7593 | 0.7143 |
0.731 | 1.0 | 1000 | 0.6925 | 0.7368 |
0.6175 | 1.5 | 1500 | 0.7037 | 0.7474 |
0.6318 | 2.0 | 2000 | 0.6743 | 0.7499 |
0.4903 | 2.51 | 2500 | 0.7241 | 0.7489 |
0.4907 | 3.01 | 3000 | 0.7573 | 0.7519 |
0.4136 | 3.51 | 3500 | 0.8098 | 0.7539 |
0.3975 | 4.01 | 4000 | 0.8294 | 0.7554 |
0.3568 | 4.51 | 4500 | 0.8680 | 0.7504 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1