metadata
base_model: Musixmatch/umberto-commoncrawl-cased-v1
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: irony_classification_ita_base
results: []
irony_classification_ita_base
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: 0.9229
- F1: 0.7035
- Roc Auc: 0.7635
- Accuracy: 0.6124
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 | 485 | 0.4856 | 0.6741 | 0.7414 | 0.5845 |
| 0.5349 | 2.0 | 970 | 0.5023 | 0.6423 | 0.7255 | 0.6175 |
| 0.4217 | 3.0 | 1455 | 0.5592 | 0.6433 | 0.7265 | 0.6113 |
| 0.3188 | 4.0 | 1940 | 0.6664 | 0.6549 | 0.7322 | 0.6134 |
| 0.2303 | 5.0 | 2425 | 0.8518 | 0.6122 | 0.7071 | 0.6062 |
| 0.1588 | 6.0 | 2910 | 0.9229 | 0.7035 | 0.7635 | 0.6124 |
| 0.1123 | 7.0 | 3395 | 0.9859 | 0.6677 | 0.7406 | 0.6082 |
| 0.0761 | 8.0 | 3880 | 1.0392 | 0.6875 | 0.7536 | 0.6206 |
| 0.0524 | 9.0 | 4365 | 1.0789 | 0.6846 | 0.7515 | 0.6206 |
| 0.0461 | 10.0 | 4850 | 1.0948 | 0.6947 | 0.7583 | 0.6206 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1