<!-- 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. -->
fBERT-hate-offensive-normal-speech-lr-2e-05
This model is a fine-tuned version of diptanu/fBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0152
- Accuracy: 0.9935
- Weighted f1: 0.9935
- Weighted recall: 0.9935
- Weighted precision: 0.9936
- Micro f1: 0.9935
- Micro recall: 0.9935
- Micro precision: 0.9935
- Macro f1: 0.9932
- Macro recall: 0.9938
- Macro precision: 0.9927
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: 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted f1 | Weighted recall | Weighted precision | Micro f1 | Micro recall | Micro precision | Macro f1 | Macro recall | Macro precision |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.4897 | 1.0 | 153 | 0.0784 | 0.9739 | 0.9741 | 0.9739 | 0.9755 | 0.9739 | 0.9739 | 0.9739 | 0.9730 | 0.9744 | 0.9729 |
0.0723 | 2.0 | 306 | 0.0183 | 0.9967 | 0.9967 | 0.9967 | 0.9968 | 0.9967 | 0.9967 | 0.9967 | 0.9964 | 0.9965 | 0.9963 |
0.027 | 3.0 | 459 | 0.0226 | 0.9935 | 0.9935 | 0.9935 | 0.9936 | 0.9935 | 0.9935 | 0.9935 | 0.9932 | 0.9938 | 0.9927 |
0.0139 | 4.0 | 612 | 0.0194 | 0.9902 | 0.9903 | 0.9902 | 0.9905 | 0.9902 | 0.9902 | 0.9902 | 0.9896 | 0.9903 | 0.9891 |
0.0119 | 5.0 | 765 | 0.0152 | 0.9935 | 0.9935 | 0.9935 | 0.9936 | 0.9935 | 0.9935 | 0.9935 | 0.9932 | 0.9938 | 0.9927 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.13.3