results
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: 0.2919
- Precision: 0.8957
- Recall: 0.8226
- F1: 0.8576
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: 0.0001
- 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.3611 | 0.2 | 500 | 0.3194 | 0.8640 | 0.8324 | 0.8479 |
| 0.3106 | 0.4 | 1000 | 0.3039 | 0.8905 | 0.8013 | 0.8435 |
| 0.3027 | 0.6 | 1500 | 0.2954 | 0.9022 | 0.7927 | 0.8439 |
| 0.2952 | 0.81 | 2000 | 0.2864 | 0.8966 | 0.8185 | 0.8558 |
| 0.2905 | 1.01 | 2500 | 0.2875 | 0.8973 | 0.8150 | 0.8542 |
| 0.2605 | 1.21 | 3000 | 0.2841 | 0.8924 | 0.8369 | 0.8637 |
| 0.2591 | 1.41 | 3500 | 0.2820 | 0.8926 | 0.8444 | 0.8678 |
| 0.2574 | 1.61 | 4000 | 0.2826 | 0.8916 | 0.8359 | 0.8629 |
| 0.2602 | 1.81 | 4500 | 0.2764 | 0.8989 | 0.8291 | 0.8626 |
| 0.2561 | 2.01 | 5000 | 0.2813 | 0.8891 | 0.8454 | 0.8667 |
| 0.2195 | 2.22 | 5500 | 0.2869 | 0.9072 | 0.8110 | 0.8564 |
| 0.2209 | 2.42 | 6000 | 0.2845 | 0.9002 | 0.8216 | 0.8591 |
| 0.2178 | 2.62 | 6500 | 0.2827 | 0.8991 | 0.8285 | 0.8624 |
| 0.22 | 2.82 | 7000 | 0.2919 | 0.8957 | 0.8226 | 0.8576 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2