metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: bert-base-multilingual-cased-afr
results: []
bert-base-multilingual-cased-afr
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1355
- Accuracy: 0.8259
- F1 Binary: 0.5345
- Precision: 0.3930
- Recall: 0.8352
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: 3e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 18
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Binary | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 92 | 0.0673 | 0.7408 | 0.4470 | 0.3002 | 0.875 |
| No log | 2.0 | 184 | 0.1188 | 0.8190 | 0.5250 | 0.3828 | 0.8352 |
| No log | 3.0 | 276 | 0.0909 | 0.8279 | 0.5358 | 0.3957 | 0.8295 |
| No log | 4.0 | 368 | 0.1355 | 0.8259 | 0.5345 | 0.3930 | 0.8352 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0