target_classification_ita_correlations
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: 0.2819
- F1: 0.4706
- Roc Auc: 0.6871
- Accuracy: 0.8351
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 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 291 | 0.2433 | 0.0 | 0.5 | 0.8265 |
| 0.2713 | 2.0 | 582 | 0.2193 | 0.3151 | 0.5994 | 0.8402 |
| 0.2713 | 3.0 | 873 | 0.2360 | 0.3922 | 0.6318 | 0.8488 |
| 0.1809 | 4.0 | 1164 | 0.2863 | 0.2985 | 0.5898 | 0.8488 |
| 0.1809 | 5.0 | 1455 | 0.3117 | 0.25 | 0.5735 | 0.8351 |
| 0.1173 | 6.0 | 1746 | 0.2819 | 0.4706 | 0.6871 | 0.8351 |
| 0.0808 | 7.0 | 2037 | 0.3277 | 0.3226 | 0.6053 | 0.8282 |
| 0.0808 | 8.0 | 2328 | 0.3416 | 0.3797 | 0.6294 | 0.8402 |
| 0.0507 | 9.0 | 2619 | 0.3316 | 0.4046 | 0.6478 | 0.8299 |
| 0.0507 | 10.0 | 2910 | 0.3661 | 0.3659 | 0.6266 | 0.8299 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1