bert-finetuned-am
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4629
- Precision: 0.3961
- Recall: 0.6021
- F1: 0.4779
- Accuracy: 0.8443
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 41 | 0.7587 | 0.2544 | 0.4027 | 0.3118 | 0.7235 |
No log | 2.0 | 82 | 0.5670 | 0.2003 | 0.4082 | 0.2687 | 0.8011 |
No log | 3.0 | 123 | 0.4773 | 0.2355 | 0.4525 | 0.3098 | 0.8238 |
No log | 4.0 | 164 | 0.4514 | 0.2963 | 0.5166 | 0.3766 | 0.8292 |
No log | 5.0 | 205 | 0.4409 | 0.3261 | 0.5491 | 0.4092 | 0.8384 |
No log | 6.0 | 246 | 0.4426 | 0.3558 | 0.5839 | 0.4422 | 0.8460 |
No log | 7.0 | 287 | 0.4629 | 0.3961 | 0.6021 | 0.4779 | 0.8443 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3