metadata
license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: prova_modello
results: []
prova_modello
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0881
- Accuracy: 0.9867
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: 16
- eval_batch_size: 16
- 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 | Accuracy |
|---|---|---|---|---|
| 0.1013 | 1.6 | 300 | 0.1481 | 0.965 |
| 0.0026 | 3.19 | 600 | 0.0905 | 0.98 |
| 0.002 | 4.79 | 900 | 0.0751 | 0.9867 |
| 0.001 | 6.38 | 1200 | 0.0892 | 0.985 |
| 0.0004 | 7.98 | 1500 | 0.0747 | 0.99 |
| 0.0004 | 9.57 | 1800 | 0.0881 | 0.9867 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0