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: 0.0340
F1: 0.9499
Precision: 0.9514
Recall: 0.9483
Accuracy: 0.9900

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
0.3699	1.0	625	0.2191	0.6830	0.6971	0.6693	0.9216
0.2451	2.0	1250	0.1407	0.8042	0.8068	0.8017	0.9527
0.1818	3.0	1875	0.0799	0.8785	0.8828	0.8742	0.9733
0.0964	4.0	2500	0.0489	0.9295	0.9252	0.9339	0.9852
0.0635	5.0	3125	0.0340	0.9499	0.9514	0.9483	0.9900

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0

meryemmm22/turkish-ner-mBERT-03

turkish-ner-mBERT-03

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

meryemmm22/
turkish-ner-mBERT-03