<!-- 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. -->
hw1_distilbert-base-uncased
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: 0.2028
- Precision: 0.8302
- Recall: 0.8881
- F1: 0.8582
- Accuracy: 0.9449
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 32
- 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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 59 | 0.2135 | 0.7672 | 0.8528 | 0.8078 | 0.9317 |
No log | 2.0 | 118 | 0.1760 | 0.8181 | 0.8916 | 0.8533 | 0.9397 |
No log | 3.0 | 177 | 0.1759 | 0.8183 | 0.8963 | 0.8555 | 0.9442 |
No log | 4.0 | 236 | 0.1900 | 0.8336 | 0.8837 | 0.8579 | 0.9448 |
No log | 5.0 | 295 | 0.2028 | 0.8302 | 0.8881 | 0.8582 | 0.9449 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3