metadata
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: flipped_1
results: []
flipped_1
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: 0.2120
- Precision: 0.4142
- Recall: 0.2832
- F1: 0.3364
- Accuracy: 0.9406
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 |
|---|---|---|---|---|---|---|---|
| 0.1878 | 1.0 | 1283 | 0.1780 | 0.4154 | 0.1742 | 0.2455 | 0.9427 |
| 0.1676 | 2.0 | 2566 | 0.1739 | 0.4377 | 0.2218 | 0.2944 | 0.9435 |
| 0.1459 | 3.0 | 3849 | 0.1828 | 0.4420 | 0.2425 | 0.3132 | 0.9435 |
| 0.1217 | 4.0 | 5132 | 0.1966 | 0.4147 | 0.2886 | 0.3404 | 0.9406 |
| 0.1024 | 5.0 | 6415 | 0.2120 | 0.4142 | 0.2832 | 0.3364 | 0.9406 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3