cs221-afro-xlmr-large-76L-ibo-finetuned-10-epochs
This model is a fine-tuned version of Davlan/afro-xlmr-large-76L on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2882
- F1: 0.5895
- Roc Auc: 0.7541
- Accuracy: 0.5226
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 OptimizerNames.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 |
---|---|---|---|---|---|---|
0.3896 | 1.0 | 72 | 0.3613 | 0.0 | 0.5 | 0.2483 |
0.3309 | 2.0 | 144 | 0.3006 | 0.4248 | 0.6424 | 0.4306 |
0.2842 | 3.0 | 216 | 0.2790 | 0.5075 | 0.6902 | 0.4688 |
0.2382 | 4.0 | 288 | 0.2757 | 0.5273 | 0.7025 | 0.4792 |
0.207 | 5.0 | 360 | 0.2648 | 0.5700 | 0.7299 | 0.5243 |
0.1761 | 6.0 | 432 | 0.2687 | 0.5749 | 0.7380 | 0.5069 |
0.1427 | 7.0 | 504 | 0.2800 | 0.5777 | 0.7414 | 0.5243 |
0.1281 | 8.0 | 576 | 0.2855 | 0.5734 | 0.7446 | 0.5139 |
0.1165 | 9.0 | 648 | 0.2882 | 0.5895 | 0.7541 | 0.5226 |
0.113 | 10.0 | 720 | 0.2894 | 0.5811 | 0.7499 | 0.5191 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.