metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
datasets:
- turkish_ner
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: turkish-ner-mBERT-03
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: 0.6292585170340682
- name: Precision
type: precision
value: 0.6108949416342413
- name: Recall
type: recall
value: 0.6487603305785123
- name: Accuracy
type: accuracy
value: 0.9264194669756662
turkish-ner-mBERT-03
This model is a fine-tuned version of bert-base-multilingual-cased on the turkish_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.2311
- F1: 0.6293
- Precision: 0.6109
- Recall: 0.6488
- Accuracy: 0.9264
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 7 | 0.5637 | 0.0315 | 0.3333 | 0.0165 | 0.8262 |
| No log | 2.0 | 14 | 0.3862 | 0.4383 | 0.4518 | 0.4256 | 0.8766 |
| No log | 3.0 | 21 | 0.3054 | 0.5720 | 0.5404 | 0.6074 | 0.9085 |
| No log | 4.0 | 28 | 0.2460 | 0.6173 | 0.6320 | 0.6033 | 0.9200 |
| No log | 5.0 | 35 | 0.2311 | 0.6293 | 0.6109 | 0.6488 | 0.9264 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.3.2
- Tokenizers 0.21.0