Afro Xlmr

--- library_name: transformers license: mit base_model: Davlan/afro-xlmr-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: afro-xlmr results: [] --- # afro-xlmr This model is a fine-tuned version of [Davlan/afro-xlmr-base](https://huggingface.co/Davlan/afro-xlmr-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.9035 - Accuracy: 0.8276 - Macro Precision: 0.8389 - Macro Recall: 0.8250 - Macro F1: 0.8246 ## 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: 1 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro Precision | Macro Recall | Macro F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:| | 1.513 | 1.0 | 942 | 1.3564 | 0.5545 | 0.5614 | 0.5369 | 0.5135 | | 1.3144 | 2.0 | 1884 | 1.3037 | 0.7376 | 0.7197 | 0.7254 | 0.7128 | | 0.7612 | 3.0 | 2826 | 1.3537 | 0.7624 | 0.7751 | 0.7540 | 0.7482 | | 0.9967 | 4.0 | 3768 | 1.4767 | 0.7574 | 0.7341 | 0.7409 | 0.7320 | | 0.303 | 5.0 | 4710 | 1.5426 | 0.7574 | 0.7455 | 0.7433 | 0.7412 | ### Framework versions - Transformers 4.45.0 - Pytorch 2.10.0+cu128 - Datasets 2.16.1 - Tokenizers 0.20.3