berttiny-hate_speech18-bothpretrained
This model is a fine-tuned version of agvidit1/GoogleTinyBert_HateSpeech_pretrain on the hate_speech18 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4682
- Accuracy: 0.8798
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: 7.12739424754752e-05
- train_batch_size: 16
- eval_batch_size: 128
- seed: 34
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4804 | 1.0 | 479 | 0.4778 | 0.8624 |
| 0.4592 | 2.0 | 958 | 0.4688 | 0.8761 |
| 0.4471 | 3.0 | 1437 | 0.4681 | 0.8780 |
| 0.4405 | 4.0 | 1916 | 0.4682 | 0.8798 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0