Edit model card

Mukayese: Turkish NLP Strikes Back

Summarization: mukayese/mbart-large-turkish-sum

This model is a fine-tuned version of facebook/mbart-large-50 on the mlsum/tu dataset.

It achieves the following results on the evaluation set:

  • Rouge1: 46.7011
  • Rouge2: 34.0087
  • Rougel: 41.5475
  • Rougelsum: 43.2108

Check this paper for more details on the model and the dataset.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10.0
  • mixed_precision_training: Native AMP
  • label_smoothing_factor: 0.1

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.8.2+cu111
  • Datasets 1.14.0
  • Tokenizers 0.10.3

Citation

@misc{safaya-etal-2022-mukayese,
    title={Mukayese: Turkish NLP Strikes Back},
    author={Ali Safaya and Emirhan Kurtuluş and Arda Göktoğan and Deniz Yuret},
    year={2022},
    eprint={2203.01215},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}
Downloads last month
22
Safetensors
Model size
611M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mukayese/mbart-large-turkish-summarization

Finetuned
(127)
this model

Dataset used to train mukayese/mbart-large-turkish-summarization

Evaluation results