<!-- 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. -->
OLID_OFFENSIVE_BERT_MULTILINGUAL
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: 0.6444
- Macro F1: 0.7636
- Micro F1: 0.7927
- Accuracy: 0.7927
Performance on test set:
-
Accuracy: 0.9022540551927534
-
F1 score: 0.8855180494749837
-
Precision: 0.8690382339788112
-
Recall : 0.9122739652138543
-
Matthews Correlation Coefficient: 0.7801150070033589
-
Precision of each class: [0.97256778 0.76550868]
-
Recall of each class: [0.88969945 0.93484848]
-
F1 score of each class: [0.92928985 0.84174625]
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 |
|---|---|---|---|---|---|---|
| 0.5568 | 1.0 | 744 | 0.4563 | 0.7641 | 0.7973 | 0.7973 |
| 0.4507 | 2.0 | 1488 | 0.4442 | 0.7657 | 0.8041 | 0.8041 |
| 0.3033 | 3.0 | 2232 | 0.5168 | 0.7672 | 0.7927 | 0.7927 |
| 0.2661 | 4.0 | 2976 | 0.6444 | 0.7636 | 0.7927 | 0.7927 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
