metadata
base_model: Musixmatch/umberto-commoncrawl-cased-v1
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: target_classification_ita
results: []
target_classification_ita
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: 0.6432
- F1: 0.7407
- Roc Auc: 0.7843
- Accuracy: 0.6735
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 |
|---|---|---|---|---|---|---|
| 0.5508 | 1.0 | 1037 | 0.5281 | 0.6704 | 0.7301 | 0.6151 |
| 0.4816 | 2.0 | 2074 | 0.4964 | 0.7109 | 0.7631 | 0.6770 |
| 0.4004 | 3.0 | 3111 | 0.5246 | 0.7299 | 0.7743 | 0.6701 |
| 0.3353 | 4.0 | 4148 | 0.5791 | 0.7310 | 0.7767 | 0.6718 |
| 0.2731 | 5.0 | 5185 | 0.6432 | 0.7407 | 0.7843 | 0.6735 |
| 0.2271 | 6.0 | 6222 | 0.6896 | 0.7248 | 0.7710 | 0.6460 |
| 0.1842 | 7.0 | 7259 | 0.7441 | 0.7271 | 0.7757 | 0.6667 |
| 0.15 | 8.0 | 8296 | 0.8640 | 0.7301 | 0.7769 | 0.6632 |
| 0.1123 | 9.0 | 9333 | 0.9447 | 0.7356 | 0.7812 | 0.6701 |
| 0.0973 | 10.0 | 10370 | 0.9652 | 0.7310 | 0.7773 | 0.6632 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1