metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: bert-incl
results: []
bert-incl
This model is a fine-tuned version of dbmdz/bert-base-italian-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0004
- Acc: 1.0
- F1 Macro: 1.0
- F1 Weight: 1.0
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: 5e-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
- lr_scheduler_warmup_steps: 20
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Acc | F1 Macro | F1 Weight |
|---|---|---|---|---|---|---|
| 0.684 | 0.67 | 20 | 0.6378 | 0.5588 | 0.3585 | 0.4007 |
| 0.4681 | 1.33 | 40 | 0.1762 | 0.9559 | 0.9547 | 0.9556 |
| 0.0989 | 2.0 | 60 | 0.0058 | 1.0 | 1.0 | 1.0 |
| 0.0032 | 2.67 | 80 | 0.0009 | 1.0 | 1.0 | 1.0 |
| 0.0011 | 3.33 | 100 | 0.0005 | 1.0 | 1.0 | 1.0 |
| 0.0007 | 4.0 | 120 | 0.0004 | 1.0 | 1.0 | 1.0 |
| 0.0007 | 4.67 | 140 | 0.0004 | 1.0 | 1.0 | 1.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3