<!-- 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. -->
fine-tuned-ai-ss-hs-01
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:
- AUC: 0.88609
- Precision: 0.8514
- Accuracy: 0.8101
- F1: 0.7875
- Recall: 0.7326
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: 1.1207606211860595e-05
- train_batch_size: 16
- eval_batch_size: 4
- seed: 2
- 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 | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 357 | 1.0285 | 0.6955 | 0.5657 | 0.8987 | 0.4128 |
| 0.5857 | 2.0 | 714 | 1.0350 | 0.7207 | 0.6296 | 0.8673 | 0.4942 |
| 0.51 | 3.0 | 1071 | 0.7467 | 0.8156 | 0.7975 | 0.8442 | 0.7558 |
| 0.51 | 4.0 | 1428 | 0.8376 | 0.8101 | 0.7875 | 0.8514 | 0.7326 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Tokenizers 0.12.1
