CVR123's picture
MuRIL_for_TamilQC
651ad28 verified
metadata
base_model: google/muril-large-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - accuracy
model-index:
  - name: Muril-base-finetune-Tamil-qc
    results: []

Muril-base-finetune-Tamil-qc

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

  • Loss: 0.7585
  • Precision: 0.8899
  • Recall: 0.8887
  • Accuracy: 0.8887
  • F1-score: 0.8892

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: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall Accuracy F1-score
0.7778 1.0 155 0.4237 0.8573 0.8664 0.8664 0.8605
0.2769 2.0 310 0.3965 0.8789 0.8765 0.8765 0.8769
0.1657 3.0 465 0.4423 0.8889 0.8866 0.8866 0.8870
0.0975 4.0 620 0.5887 0.8824 0.8785 0.8785 0.8798
0.067 5.0 775 0.6212 0.8882 0.8846 0.8846 0.8858
0.034 6.0 930 0.6018 0.8948 0.8927 0.8927 0.8934
0.0249 7.0 1085 0.7035 0.8902 0.8887 0.8887 0.8893
0.0206 8.0 1240 0.7113 0.8936 0.8927 0.8927 0.8931
0.0122 9.0 1395 0.7400 0.8899 0.8887 0.8887 0.8892
0.0043 10.0 1550 0.7585 0.8899 0.8887 0.8887 0.8892

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2