<!-- 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. -->
news_classifier-distilbert-base-uncased-subject-only
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: 0.9128
- Accuracy: 0.6719
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 |
---|---|---|---|---|
No log | 1.0 | 48 | 1.1869 | 0.5417 |
No log | 2.0 | 96 | 0.9940 | 0.5833 |
No log | 3.0 | 144 | 0.9497 | 0.5833 |
No log | 4.0 | 192 | 0.8526 | 0.6146 |
No log | 5.0 | 240 | 0.8595 | 0.6510 |
No log | 6.0 | 288 | 0.8548 | 0.6562 |
No log | 7.0 | 336 | 0.8727 | 0.6823 |
No log | 8.0 | 384 | 0.9072 | 0.6667 |
No log | 9.0 | 432 | 0.9282 | 0.6667 |
No log | 10.0 | 480 | 0.9128 | 0.6719 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3