metadata
library_name: transformers
license: mit
base_model: sercetexam9/afro-xlmr-base-sun-finetuned-augmentation-LUNAR
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: afro-xlmr-base-sun-finetuned-augmentation-LUNAR-sun
results: []
afro-xlmr-base-sun-finetuned-augmentation-LUNAR-sun
This model is a fine-tuned version of sercetexam9/afro-xlmr-base-sun-finetuned-augmentation-LUNAR on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2140
- F1: 0.6287
- Roc Auc: 0.7758
- Accuracy: 0.7098
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.1769 | 1.0 | 103 | 0.2140 | 0.6287 | 0.7758 | 0.7098 |
| 0.1889 | 2.0 | 206 | 0.2100 | 0.5116 | 0.6985 | 0.6854 |
| 0.1577 | 3.0 | 309 | 0.2106 | 0.5387 | 0.7090 | 0.6683 |
| 0.1265 | 4.0 | 412 | 0.2257 | 0.5563 | 0.7177 | 0.6634 |
| 0.1417 | 5.0 | 515 | 0.2375 | 0.5087 | 0.6901 | 0.6707 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0