<!-- 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. -->
bert-base-uncased-english-sentweet-profane
This model is a fine-tuned version of textattack/bert-base-uncased-MNLI on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9193
- Accuracy: 0.7951
- Precision: 0.8047
- Recall: 0.8042
- F1: 0.7951
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 | 0.4563 | 0.8160 | 0.8317 | 0.8275 | 0.8159 |
| No log | 2.0 | 162 | 0.4613 | 0.8125 | 0.8271 | 0.8236 | 0.8124 |
| No log | 3.0 | 243 | 0.5956 | 0.7882 | 0.8012 | 0.7987 | 0.7881 |
| No log | 4.0 | 324 | 0.7474 | 0.7847 | 0.7950 | 0.7941 | 0.7847 |
| No log | 5.0 | 405 | 0.8416 | 0.8021 | 0.8029 | 0.8061 | 0.8017 |
| No log | 6.0 | 486 | 0.9193 | 0.7951 | 0.8047 | 0.8042 | 0.7951 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0
