ironita_finetuned_correlations
This model is a fine-tuned version of lupobricco/irony_classification_ita_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2372
- F1: 0.5152
- Roc Auc: 0.7176
- Accuracy: 0.8419
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 | 0.2090 | 0.35 | 0.6183 | 0.8282 |
0.2333 | 2.0 | 582 | 0.2372 | 0.5152 | 0.7176 | 0.8419 |
0.2333 | 3.0 | 873 | 0.3356 | 0.3924 | 0.6345 | 0.8436 |
0.1292 | 4.0 | 1164 | 0.3644 | 0.3399 | 0.6114 | 0.8351 |
0.1292 | 5.0 | 1455 | 0.4006 | 0.2973 | 0.5933 | 0.8316 |
0.0666 | 6.0 | 1746 | 0.4199 | 0.3288 | 0.6045 | 0.8402 |
0.0346 | 7.0 | 2037 | 0.4441 | 0.4134 | 0.6552 | 0.8282 |
0.0346 | 8.0 | 2328 | 0.4483 | 0.4382 | 0.6659 | 0.8385 |
0.019 | 9.0 | 2619 | 0.4600 | 0.4070 | 0.6483 | 0.8333 |
0.019 | 10.0 | 2910 | 0.4580 | 0.4432 | 0.6668 | 0.8402 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 6
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for lupobricco/ironita_finetuned_correlations
Base model
Musixmatch/umberto-commoncrawl-cased-v1
Finetuned
lupobricco/irony_classification_ita_base