metadata
library_name: transformers
license: mit
base_model: Davlan/afro-xlmr-large-76L
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: cs221-afro-xlmr-large-76L-orm-finetuned-10-epochs
results: []
cs221-afro-xlmr-large-76L-orm-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: 0.2347
- F1: 0.6000
- Roc Auc: 0.7566
- Accuracy: 0.5843
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 |
|---|---|---|---|---|---|---|
| 0.3477 | 1.0 | 87 | 0.3587 | 0.0354 | 0.5080 | 0.2369 |
| 0.3192 | 2.0 | 174 | 0.3032 | 0.1766 | 0.5570 | 0.3924 |
| 0.2639 | 3.0 | 261 | 0.2631 | 0.3089 | 0.6130 | 0.5334 |
| 0.2128 | 4.0 | 348 | 0.2350 | 0.5180 | 0.7115 | 0.5858 |
| 0.1789 | 5.0 | 435 | 0.2314 | 0.5112 | 0.7075 | 0.5901 |
| 0.1465 | 6.0 | 522 | 0.2347 | 0.6000 | 0.7566 | 0.5843 |
| 0.1321 | 7.0 | 609 | 0.2457 | 0.5844 | 0.7496 | 0.5872 |
| 0.094 | 8.0 | 696 | 0.2412 | 0.5649 | 0.7271 | 0.6032 |
| 0.0867 | 9.0 | 783 | 0.2450 | 0.5755 | 0.7326 | 0.6119 |
| 0.0866 | 10.0 | 870 | 0.2466 | 0.5756 | 0.7349 | 0.6061 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0