bert-base-cased-english-sentweet-Targeted-Insult
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7559
- Accuracy: 0.8021
- Precision: 0.8122
- Recall: 0.8108
- F1: 0.8021
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: 5e-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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | 0.4820 | 0.8090 | 0.8323 | 0.8219 | 0.8085 |
| No log | 2.0 | 162 | 0.4688 | 0.8229 | 0.8441 | 0.8352 | 0.8226 |
| No log | 3.0 | 243 | 0.5383 | 0.8056 | 0.8185 | 0.8153 | 0.8055 |
| No log | 4.0 | 324 | 0.5501 | 0.8056 | 0.8148 | 0.8139 | 0.8055 |
| No log | 5.0 | 405 | 0.6789 | 0.7847 | 0.7883 | 0.7902 | 0.7846 |
| No log | 6.0 | 486 | 0.7559 | 0.8021 | 0.8122 | 0.8108 | 0.8021 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0