metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- turkish_ner
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: turkish-ner-fold-bBERT1
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: 0.6381292112564407
- name: Precision
type: precision
value: 0.6213817059050559
- name: Recall
type: recall
value: 0.6558044806517311
- name: Accuracy
type: accuracy
value: 0.9019425920556683
turkish-ner-fold-bBERT1
This model is a fine-tuned version of xlm-roberta-base on the turkish_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.3085
- F1: 0.6381
- Precision: 0.6214
- Recall: 0.6558
- Accuracy: 0.9019
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: 16
- 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 | F1 | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4015 | 1.0 | 500 | 0.3224 | 0.5739 | 0.5628 | 0.5855 | 0.8788 |
| 0.2729 | 2.0 | 1000 | 0.2923 | 0.6221 | 0.5852 | 0.6640 | 0.8923 |
| 0.2098 | 3.0 | 1500 | 0.2794 | 0.6402 | 0.6451 | 0.6353 | 0.9030 |
| 0.1613 | 4.0 | 2000 | 0.3026 | 0.6458 | 0.6236 | 0.6696 | 0.8991 |
| 0.1269 | 5.0 | 2500 | 0.3039 | 0.6528 | 0.6420 | 0.6640 | 0.9050 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0