metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: BasqueBerta-base-FT
results: []
BasqueBerta-base-FT
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3019
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- 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 |
|---|---|---|---|
| No log | 1.0 | 65 | 3.3258 |
| No log | 2.0 | 130 | 3.0231 |
| No log | 3.0 | 195 | 3.0215 |
| No log | 4.0 | 260 | 2.9057 |
| No log | 5.0 | 325 | 2.6933 |
| No log | 6.0 | 390 | 2.7688 |
| No log | 7.0 | 455 | 2.4967 |
| 2.917 | 8.0 | 520 | 2.4606 |
| 2.917 | 9.0 | 585 | 2.4320 |
| 2.917 | 10.0 | 650 | 2.3019 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0