<!-- 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-hausa-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: 0.1493
- Precision: 0.7153
- Recall: 0.5631
- F1: 0.6301
- Accuracy: 0.9588
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 |
---|---|---|---|---|---|---|---|
0.177 | 1.0 | 1312 | 0.1549 | 0.6557 | 0.4168 | 0.5097 | 0.9479 |
0.1412 | 2.0 | 2624 | 0.1386 | 0.6723 | 0.5262 | 0.5903 | 0.9539 |
0.1154 | 3.0 | 3936 | 0.1400 | 0.7078 | 0.5353 | 0.6096 | 0.9567 |
0.0921 | 4.0 | 5248 | 0.1418 | 0.7200 | 0.5496 | 0.6234 | 0.9585 |
0.0731 | 5.0 | 6560 | 0.1493 | 0.7153 | 0.5631 | 0.6301 | 0.9588 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3