<!-- 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-igbo-5e-5
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: 0.2368
- Precision: 0.7064
- Recall: 0.5075
- F1: 0.5907
- Accuracy: 0.9212
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: 5e-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 |
|---|---|---|---|---|---|---|---|
| 0.2768 | 1.0 | 1257 | 0.2611 | 0.7212 | 0.3117 | 0.4353 | 0.9055 |
| 0.2299 | 2.0 | 2514 | 0.2606 | 0.7395 | 0.3797 | 0.5018 | 0.9134 |
| 0.1966 | 3.0 | 3771 | 0.2224 | 0.7252 | 0.4496 | 0.5550 | 0.9186 |
| 0.1697 | 4.0 | 5028 | 0.2290 | 0.7273 | 0.4775 | 0.5765 | 0.9208 |
| 0.1449 | 5.0 | 6285 | 0.2368 | 0.7064 | 0.5075 | 0.5907 | 0.9212 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
