cs221-xlm-roberta-large-finetuned-amharic-amh-finetuned-10-epochs
This model is a fine-tuned version of Davlan/xlm-roberta-large-finetuned-amharic on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3308
- F1: 0.7601
- Roc Auc: 0.8433
- Accuracy: 0.5357
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4459 | 1.0 | 74 | 0.3879 | 0.5666 | 0.7092 | 0.2517 |
| 0.2993 | 2.0 | 148 | 0.2981 | 0.7242 | 0.8187 | 0.4677 |
| 0.2464 | 3.0 | 222 | 0.2667 | 0.7340 | 0.8157 | 0.5085 |
| 0.2048 | 4.0 | 296 | 0.2851 | 0.7442 | 0.8234 | 0.5340 |
| 0.1636 | 5.0 | 370 | 0.2793 | 0.7599 | 0.8411 | 0.5357 |
| 0.1079 | 6.0 | 444 | 0.3041 | 0.7557 | 0.8394 | 0.5153 |
| 0.0878 | 7.0 | 518 | 0.3138 | 0.7491 | 0.8343 | 0.5221 |
| 0.0725 | 8.0 | 592 | 0.3308 | 0.7601 | 0.8433 | 0.5357 |
| 0.0559 | 9.0 | 666 | 0.3371 | 0.7557 | 0.8385 | 0.5340 |
| 0.0573 | 10.0 | 740 | 0.3383 | 0.7546 | 0.8384 | 0.5289 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0