metadata
library_name: transformers
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
datasets:
- turkish_ner
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: turkish-ner-ner-mt5-base
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: 0.5109507803635274
- name: Precision
type: precision
value: 0.5446371519853948
- name: Recall
type: recall
value: 0.481188757611194
- name: Accuracy
type: accuracy
value: 0.8782529367510026
turkish-ner-ner-mt5-base
This model is a fine-tuned version of google/mt5-base on the turkish_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.3759
- F1: 0.5110
- Precision: 0.5446
- Recall: 0.4812
- Accuracy: 0.8783
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 |
|---|---|---|---|---|---|---|---|
| 1.1325 | 1.0 | 625 | 0.6327 | 0.2185 | 0.4078 | 0.1492 | 0.8266 |
| 0.6808 | 2.0 | 1250 | 0.4405 | 0.4363 | 0.4780 | 0.4013 | 0.8588 |
| 0.5606 | 3.0 | 1875 | 0.3983 | 0.4817 | 0.5290 | 0.4421 | 0.8708 |
| 0.47 | 4.0 | 2500 | 0.3773 | 0.5074 | 0.5497 | 0.4711 | 0.8781 |
| 0.4555 | 5.0 | 3125 | 0.3759 | 0.5110 | 0.5446 | 0.4812 | 0.8783 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0