<!-- 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. -->
hate_detection_model
This model is a fine-tuned version of sangrimlee/bert-base-multilingual-cased-nsmc on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2937
- Accuracy: 0.7686
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 62 | 0.4613 | 0.7834 |
| No log | 2.0 | 124 | 0.5033 | 0.7516 |
| No log | 3.0 | 186 | 0.4699 | 0.7898 |
| No log | 4.0 | 248 | 0.5516 | 0.7516 |
| No log | 5.0 | 310 | 0.6990 | 0.7219 |
| No log | 6.0 | 372 | 0.6500 | 0.7665 |
| No log | 7.0 | 434 | 0.7347 | 0.7856 |
| No log | 8.0 | 496 | 0.9104 | 0.7389 |
| 0.3218 | 9.0 | 558 | 0.7689 | 0.8153 |
| 0.3218 | 10.0 | 620 | 0.9496 | 0.7792 |
| 0.3218 | 11.0 | 682 | 0.9598 | 0.7707 |
| 0.3218 | 12.0 | 744 | 1.2402 | 0.7091 |
| 0.3218 | 13.0 | 806 | 1.1616 | 0.7537 |
| 0.3218 | 14.0 | 868 | 1.0903 | 0.7771 |
| 0.3218 | 15.0 | 930 | 1.3674 | 0.7304 |
| 0.3218 | 16.0 | 992 | 1.1962 | 0.7728 |
| 0.0623 | 17.0 | 1054 | 1.3640 | 0.7452 |
| 0.0623 | 18.0 | 1116 | 1.3093 | 0.7622 |
| 0.0623 | 19.0 | 1178 | 1.3108 | 0.7707 |
| 0.0623 | 20.0 | 1240 | 1.2937 | 0.7686 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
