README.md

metadata

license: mit
base_model: alayaran/bodo-roberta-base-sentencepiece-mlm
tags:
  - generated_from_trainer
datasets:
  - alayaran/bodo-monolingual-dataset
metrics:
  - accuracy
model-index:
  - name: bodo-roberta-base-sentencepiece-mlm
    results:
      - task:
          name: Masked Language Modeling
          type: fill-mask
        dataset:
          name: alayaran/bodo-monolingual-dataset
          type: alayaran/bodo-monolingual-dataset
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.1152087425920729
widget:
  - text: बिजाथि महरै <mask> मोनबो थांखि गैया ।
    example_title: फोसावनायनि
  - text: देहा गोनां जानायनि <mask> थांनानै थानायल’ख्रुइ गोबांसिन।
    example_title: ओंथिआ
language:
  - brx

bodo-roberta-base-sentencepiece-mlm

This model is a fine-tuned version of alayaran/bodo-roberta-base-sentencepiece-mlm on the alayaran/bodo-monolingual-dataset dataset. It achieves the following results on the evaluation set:

• Loss: 7.6855
• Accuracy: 0.1152

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: 0.0003
• train_batch_size: 96
• eval_batch_size: 96
• seed: 42
• optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 18.0

Training results

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3