target_classification_ita2
This model is a fine-tuned version of Musixmatch/umberto-commoncrawl-cased-v1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3451
- F1: 0.4422
- Roc Auc: 0.6814
- Accuracy: 0.8127
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4759 | 1.0 | 897 | 0.2585 | 0.0794 | 0.5170 | 0.8093 |
| 0.3547 | 2.0 | 1794 | 0.2457 | 0.2517 | 0.5753 | 0.8230 |
| 0.2756 | 3.0 | 2691 | 0.2561 | 0.4138 | 0.6693 | 0.8007 |
| 0.1996 | 4.0 | 3588 | 0.2704 | 0.3929 | 0.6400 | 0.8299 |
| 0.1529 | 5.0 | 4485 | 0.3451 | 0.4422 | 0.6814 | 0.8127 |
| 0.1057 | 6.0 | 5382 | 0.4442 | 0.3605 | 0.6279 | 0.8196 |
| 0.0644 | 7.0 | 6279 | 0.4965 | 0.3858 | 0.6518 | 0.7973 |
| 0.045 | 8.0 | 7176 | 0.5365 | 0.3867 | 0.6440 | 0.8179 |
| 0.0328 | 9.0 | 8073 | 0.5268 | 0.4046 | 0.6478 | 0.8316 |
| 0.0275 | 10.0 | 8970 | 0.5573 | 0.4044 | 0.6533 | 0.8213 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 3