metadata
library_name: transformers
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
datasets:
- masakhaner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: afro-xlmr-base-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: masakhaner
type: masakhaner
config: amh
split: validation
args: amh
metrics:
- name: Precision
type: precision
value: 0.6377952755905512
- name: Recall
type: recall
value: 0.7408536585365854
- name: F1
type: f1
value: 0.6854724964739068
- name: Accuracy
type: accuracy
value: 0.9539116048215552
afro-xlmr-base-finetuned-ner
This model is a fine-tuned version of Davlan/afro-xlmr-base on the masakhaner dataset. It achieves the following results on the evaluation set:
- Loss: 0.1729
- Precision: 0.6378
- Recall: 0.7409
- F1: 0.6855
- Accuracy: 0.9539
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 219 | 0.2089 | 0.55 | 0.6707 | 0.6044 | 0.9310 |
| No log | 2.0 | 438 | 0.1602 | 0.6305 | 0.7439 | 0.6825 | 0.9536 |
| 0.2795 | 3.0 | 657 | 0.1729 | 0.6378 | 0.7409 | 0.6855 | 0.9539 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0