metadata
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: aligned_source_5e-5
results: []
aligned_source_5e-5
This model is a fine-tuned version of Davlan/afro-xlmr-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1076
- Precision: 0.3551
- Recall: 0.2680
- F1: 0.3054
- Accuracy: 0.9711
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: 5e-05
- train_batch_size: 16
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1109 | 1.0 | 1016 | 0.0905 | 0.3897 | 0.0842 | 0.1385 | 0.9745 |
| 0.0994 | 2.0 | 2032 | 0.0896 | 0.3712 | 0.2191 | 0.2756 | 0.9729 |
| 0.0861 | 3.0 | 3048 | 0.0936 | 0.3626 | 0.2567 | 0.3006 | 0.9718 |
| 0.0698 | 4.0 | 4064 | 0.0989 | 0.3665 | 0.2639 | 0.3068 | 0.9718 |
| 0.0594 | 5.0 | 5080 | 0.1076 | 0.3551 | 0.2680 | 0.3054 | 0.9711 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3