<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
xlmr-finetuned-igbo
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2323
- Precision: 0.7134
- Recall: 0.4641
- F1: 0.5623
- Accuracy: 0.9188
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.284 | 1.0 | 1257 | 0.2690 | 0.7177 | 0.2740 | 0.3966 | 0.9019 |
0.2383 | 2.0 | 2514 | 0.2597 | 0.7436 | 0.3418 | 0.4683 | 0.9101 |
0.2108 | 3.0 | 3771 | 0.2241 | 0.7097 | 0.4378 | 0.5416 | 0.9161 |
0.1925 | 4.0 | 5028 | 0.2323 | 0.7274 | 0.4343 | 0.5439 | 0.9173 |
0.1774 | 5.0 | 6285 | 0.2323 | 0.7134 | 0.4641 | 0.5623 | 0.9188 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3