AmharicNewsNonCleanedSmall
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: 0.1658
- Accuracy: 0.9570
- Precision: 0.9570
- Recall: 0.9570
- F1: 0.9569
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.2168 | 1.0 | 933 | 0.2913 | 0.8993 | 0.9102 | 0.8993 | 0.8973 |
0.1264 | 2.0 | 1866 | 0.1724 | 0.9438 | 0.9446 | 0.9438 | 0.9438 |
0.1203 | 3.0 | 2799 | 0.1627 | 0.9481 | 0.9498 | 0.9481 | 0.9482 |
0.1368 | 4.0 | 3732 | 0.1787 | 0.9455 | 0.9466 | 0.9455 | 0.9452 |
0.058 | 5.0 | 4665 | 0.1658 | 0.9570 | 0.9570 | 0.9570 | 0.9569 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 4