metadata
library_name: transformers
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: turkish-ner-mt5-base-wikiann
results: []
turkish-ner-mt5-base-wikiann
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3629
- F1: 0.6021
- Precision: 0.5864
- Recall: 0.6187
- Accuracy: 0.9039
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 |
|---|---|---|---|---|---|---|---|
| 1.621 | 1.0 | 625 | 0.5473 | 0.5291 | 0.5167 | 0.5421 | 0.8563 |
| 0.7118 | 2.0 | 1250 | 0.4740 | 0.5633 | 0.5512 | 0.5759 | 0.8744 |
| 0.581 | 3.0 | 1875 | 0.3952 | 0.5865 | 0.5680 | 0.6061 | 0.8965 |
| 0.4918 | 4.0 | 2500 | 0.3709 | 0.5998 | 0.5839 | 0.6166 | 0.9023 |
| 0.4552 | 5.0 | 3125 | 0.3629 | 0.6021 | 0.5864 | 0.6187 | 0.9039 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0