metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-finetuning-italian
results: []
distilbert-finetuning-italian
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7252
- Model Preparation Time: 0.0016
- Accuracy: 0.7297
- F1 Macro: 0.7254
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy | F1 Macro |
|---|---|---|---|---|---|---|
| No log | 1.0 | 320 | 0.6796 | 0.0016 | 0.7188 | 0.7131 |
| 0.9005 | 2.0 | 640 | 0.6630 | 0.0016 | 0.7438 | 0.7456 |
| 0.9005 | 3.0 | 960 | 0.6307 | 0.0016 | 0.7453 | 0.7447 |
| 0.537 | 4.0 | 1280 | 0.6060 | 0.0016 | 0.7734 | 0.7699 |
| 0.3829 | 5.0 | 1600 | 0.6971 | 0.0016 | 0.7297 | 0.7317 |
| 0.3829 | 6.0 | 1920 | 0.6877 | 0.0016 | 0.7625 | 0.7634 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0