<!-- 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. -->
finetuning-covid19-tweets
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: 0.2771
- Accuracy: 0.9206
- F1: 0.9206
- Auc: 0.9206
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: 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 | Accuracy | F1 | Auc |
---|---|---|---|---|---|---|
No log | 1.0 | 133 | 0.2286 | 0.9149 | 0.9150 | 0.9156 |
No log | 2.0 | 266 | 0.2373 | 0.9159 | 0.9158 | 0.9182 |
No log | 3.0 | 399 | 0.2375 | 0.9216 | 0.9216 | 0.9224 |
0.1978 | 4.0 | 532 | 0.2616 | 0.9225 | 0.9225 | 0.9228 |
0.1978 | 5.0 | 665 | 0.2771 | 0.9206 | 0.9206 | 0.9206 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3