AIKIA_0.6_OFFENSIVE_BERT_MULTILINGUAL1
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7624
- Macro F1: 0.7128
- Micro F1: 0.7601
- Accuracy: 0.7601
Performance on test set:
-
Accuracy: 0.7973856209150327
-
F1 score: 0.7760745870386702
-
Precision: 0.775117096128912
-
Recall : 0.7770859985785359
-
Matthews Correlation Coefficient: 0.5521995845956664
-
Precision of each class: [0.84854564 0.70168856]
-
Recall of each class: [0.84179104 0.71238095]
-
F1 score of each class: [0.84515485 0.70699433]
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Micro F1 | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 338 | 0.5701 | 0.7024 | 0.7122 | 0.7122 |
| 0.5808 | 2.0 | 676 | 0.5888 | 0.7221 | 0.7528 | 0.7528 |
| 0.4027 | 3.0 | 1014 | 0.6163 | 0.7265 | 0.7528 | 0.7528 |
| 0.4027 | 4.0 | 1352 | 0.7624 | 0.7128 | 0.7601 | 0.7601 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3