metadata
library_name: transformers
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- turkish_ner
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: xlm-turkish-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: turkish_ner
type: turkish_ner
config: default
split: train
args: default
metrics:
- name: F1
type: f1
value: 0.657840245968501
- name: Precision
type: precision
value: 0.6669776910679447
- name: Recall
type: recall
value: 0.6489497792266744
- name: Accuracy
type: accuracy
value: 0.9113795745182391
xlm-turkish-ner
This model is a fine-tuned version of xlm-roberta-large on the turkish_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.2836
- F1: 0.6578
- Precision: 0.6670
- Recall: 0.6489
- Accuracy: 0.9114
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2704 | 1.0 | 1250 | 0.2745 | 0.6153 | 0.6250 | 0.6059 | 0.8985 |
| 0.2047 | 2.0 | 2500 | 0.2656 | 0.6372 | 0.6429 | 0.6315 | 0.9046 |
| 0.1646 | 3.0 | 3750 | 0.2628 | 0.6560 | 0.6839 | 0.6303 | 0.9109 |
| 0.1256 | 4.0 | 5000 | 0.2895 | 0.6561 | 0.6641 | 0.6482 | 0.9092 |
| 0.0953 | 5.0 | 6250 | 0.3224 | 0.6555 | 0.6554 | 0.6556 | 0.9088 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0