# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("funmidab/mbeukman-finetuned")
model = AutoModelForTokenClassification.from_pretrained("funmidab/mbeukman-finetuned")Quick Links
mbeukman-finetuned
This model is a fine-tuned version of mbeukman/xlm-roberta-base-finetuned-yoruba-finetuned-ner-yoruba on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1239
- Precision: 0.7778
- Recall: 0.7799
- F1: 0.7789
- Accuracy: 0.9612
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 125 | 0.1634 | 0.7278 | 0.7521 | 0.7397 | 0.9539 |
| No log | 2.0 | 250 | 0.1287 | 0.7837 | 0.7772 | 0.7804 | 0.9630 |
| No log | 3.0 | 375 | 0.1264 | 0.7609 | 0.7799 | 0.7703 | 0.9598 |
| 0.1504 | 4.0 | 500 | 0.1209 | 0.7560 | 0.7939 | 0.7745 | 0.9622 |
| 0.1504 | 5.0 | 625 | 0.1239 | 0.7778 | 0.7799 | 0.7789 | 0.9612 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Downloads last month
- 5
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="funmidab/mbeukman-finetuned")