metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Basque_Dialects_Classification
results: []
widget:
- text: Gaur eskolara etorri naiz
example_title: Example 1
- text: Gaur eskolara etorri naz
example_title: Example 2
Basque_Dialects_Classification
This model is a fine-tuned version of ixa-ehu/roberta-eus-cc100-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4558
- F1: 0.6846
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: 7.2193610624691235e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.7
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.4126 | 1.0 | 9611 | 1.4626 | 0.5893 |
| 1.3446 | 2.0 | 19222 | 1.5642 | 0.6421 |
| 1.0157 | 3.0 | 28833 | 1.5049 | 0.6596 |
| 1.3012 | 4.0 | 38444 | 1.4939 | 0.6708 |
| 1.0824 | 5.0 | 48055 | 1.4558 | 0.6846 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1