Hugging Face's logo

tuhanasinan
/
t5-base-turkish-reincames-hukuk

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Model card Files Community
t5-base-turkish-reincames-hukuk / README.md
tuhanasinan's picture
tuhanasinan
End of training
9e3c4b4 verified
preview code
|
raw
history blame contribute delete
1.72 kB
metadata
library_name: transformers
license: mit
base_model: Turkish-NLP/t5-efficient-base-turkish
tags:
  - generated_from_trainer
model-index:
  - name: t5-base-turkish-reincames-hukuk
    results: []

t5-base-turkish-reincames-hukuk

This model is a fine-tuned version of Turkish-NLP/t5-efficient-base-turkish on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9889

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: 0.0005
  • train_batch_size: 4
  • 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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.3603 1.0 2671 1.1303
0.9344 2.0 5342 0.9793
0.6756 3.0 8013 0.9169
0.4619 4.0 10684 0.9269
0.3474 5.0 13355 0.9889

Framework versions

  • Transformers 4.51.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.5.0
  • Tokenizers 0.21.0