<!-- 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-base-finetuned-igbo-2e-4
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: 0.3850
- Precision: 0.0223
- Recall: 0.0016
- F1: 0.0029
- Accuracy: 0.8715
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.3879 | 1.0 | 1257 | 0.3848 | 0.0223 | 0.0016 | 0.0029 | 0.8715 |
0.3885 | 2.0 | 2514 | 0.3861 | 0.0223 | 0.0016 | 0.0029 | 0.8715 |
0.3823 | 3.0 | 3771 | 0.3847 | 0.0223 | 0.0016 | 0.0029 | 0.8715 |
0.3855 | 4.0 | 5028 | 0.3848 | 0.0223 | 0.0016 | 0.0029 | 0.8715 |
0.3846 | 5.0 | 6285 | 0.3850 | 0.0223 | 0.0016 | 0.0029 | 0.8715 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3