deberta_finetuned_yahoo_answers_topics
This model is a fine-tuned version of distilbert-base-uncased on the yahoo_answers_topics dataset. It achieves the following results on the evaluation set:
- Loss: 0.9096
- Accuracy: 0.7119
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
- training_steps: 30000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1025 | 0.03 | 5000 | 1.0702 | 0.6717 |
| 1.0132 | 0.06 | 10000 | 0.9976 | 0.6834 |
| 0.8688 | 0.09 | 15000 | 0.9770 | 0.6961 |
| 0.9964 | 0.11 | 20000 | 0.9356 | 0.7020 |
| 0.9338 | 0.14 | 25000 | 0.9259 | 0.7090 |
| 0.9059 | 0.17 | 30000 | 0.9096 | 0.7119 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1