metadata
library_name: transformers
license: mit
base_model: dbmdz/bert-base-italian-xxl-cased
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: bert-base-italian-xxl-cased-sentence-splitter
results: []
bert-base-italian-xxl-cased-sentence-splitter
This model is a fine-tuned version of dbmdz/bert-base-italian-xxl-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0026
- F1: 0.9907
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 49 | 0.0033 | 0.9846 |
| No log | 2.0 | 98 | 0.0025 | 0.9846 |
| No log | 3.0 | 147 | 0.0030 | 0.9861 |
| No log | 4.0 | 196 | 0.0033 | 0.9801 |
| No log | 5.0 | 245 | 0.0025 | 0.9892 |
| No log | 6.0 | 294 | 0.0029 | 0.9877 |
| No log | 7.0 | 343 | 0.0030 | 0.9907 |
| No log | 8.0 | 392 | 0.0023 | 0.9892 |
| No log | 9.0 | 441 | 0.0023 | 0.9907 |
| No log | 10.0 | 490 | 0.0031 | 0.9907 |
| 0.0128 | 11.0 | 539 | 0.0021 | 0.9922 |
| 0.0128 | 12.0 | 588 | 0.0038 | 0.9907 |
| 0.0128 | 13.0 | 637 | 0.0046 | 0.9891 |
| 0.0128 | 14.0 | 686 | 0.0030 | 0.9892 |
| 0.0128 | 15.0 | 735 | 0.0024 | 0.9907 |
| 0.0128 | 16.0 | 784 | 0.0023 | 0.9907 |
| 0.0128 | 17.0 | 833 | 0.0024 | 0.9907 |
| 0.0128 | 18.0 | 882 | 0.0023 | 0.9907 |
| 0.0128 | 19.0 | 931 | 0.0023 | 0.9907 |
| 0.0128 | 20.0 | 980 | 0.0024 | 0.9907 |
| 0.0002 | 21.0 | 1029 | 0.0024 | 0.9907 |
| 0.0002 | 22.0 | 1078 | 0.0024 | 0.9907 |
| 0.0002 | 23.0 | 1127 | 0.0024 | 0.9907 |
| 0.0002 | 24.0 | 1176 | 0.0025 | 0.9907 |
| 0.0002 | 25.0 | 1225 | 0.0025 | 0.9907 |
| 0.0002 | 26.0 | 1274 | 0.0025 | 0.9907 |
| 0.0002 | 27.0 | 1323 | 0.0025 | 0.9907 |
| 0.0002 | 28.0 | 1372 | 0.0026 | 0.9907 |
| 0.0002 | 29.0 | 1421 | 0.0026 | 0.9907 |
| 0.0002 | 30.0 | 1470 | 0.0026 | 0.9907 |
Framework versions
- Transformers 4.55.0
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4