mbert_mar-deva

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

mar-Deva

This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7135
• Accuracy: 0.8574

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 100000

Citation Information

If you use this model in your work, please cite the following paper. Additionally, if you require more details on training and performance, refer to the paper:

@misc{gurgurov2025smallmodelsbigimpact,
    title={Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages}, 
    author={Daniil Gurgurov and Ivan Vykopal and Josef van Genabith and Simon Ostermann},
    year={2025},
    eprint={2502.10140},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2502.10140}, 
}