metadata
library_name: transformers
license: mit
base_model: sercetexam9/afro-xlmr-base-amh-finetuned-augmentation-LUNAR
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: afro-xlmr-base-amh-finetuned-augmentation-LUNAR-amh-MICRO
results: []
afro-xlmr-base-amh-finetuned-augmentation-LUNAR-amh-MICRO
This model is a fine-tuned version of sercetexam9/afro-xlmr-base-amh-finetuned-augmentation-LUNAR on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1393
- F1: 0.8933
- Roc Auc: 0.9321
- Accuracy: 0.7887
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 |
|---|---|---|---|---|---|---|
| 0.08 | 1.0 | 925 | 0.1458 | 0.8781 | 0.9324 | 0.7658 |
| 0.0517 | 2.0 | 1850 | 0.1393 | 0.8933 | 0.9321 | 0.7887 |
| 0.0441 | 3.0 | 2775 | 0.1702 | 0.8838 | 0.9216 | 0.7751 |
| 0.0284 | 4.0 | 3700 | 0.1980 | 0.8843 | 0.9291 | 0.7751 |
| 0.0127 | 5.0 | 4625 | 0.2304 | 0.8684 | 0.9221 | 0.7388 |
| 0.0137 | 6.0 | 5550 | 0.2428 | 0.8755 | 0.9261 | 0.7591 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0