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-05
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: 0.19467271181637857
- name: Precision
type: precision
value: 0.3664
- name: Recall
type: recall
value: 0.13254871695929
- name: Accuracy
type: accuracy
value: 0.8172224930461962
turkish-ner-mBERT-05
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: 0.5967
- F1: 0.1947
- Precision: 0.3664
- Recall: 0.1325
- Accuracy: 0.8172
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 250 | 0.6886 | 0.0090 | 0.1702 | 0.0046 | 0.8144 |
0.8103 | 2.0 | 500 | 0.6445 | 0.1025 | 0.2930 | 0.0621 | 0.8158 |
0.8103 | 3.0 | 750 | 0.6265 | 0.1546 | 0.3204 | 0.1019 | 0.8130 |
0.5809 | 4.0 | 1000 | 0.5952 | 0.1790 | 0.3878 | 0.1163 | 0.8224 |
0.5809 | 5.0 | 1250 | 0.5967 | 0.1947 | 0.3664 | 0.1325 | 0.8172 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0