CVR123's picture
MuRIL_for_TamilQC
f9c9402 verified
metadata
license: apache-2.0
base_model: google/muril-base-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - accuracy
model-index:
  - name: Muril-base-finetune-Tamil-questions
    results: []

Muril-base-finetune-Tamil-questions

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

  • Loss: 0.4081
  • Precision: 0.9205
  • Recall: 0.9198
  • Accuracy: 0.9198
  • F1-score: 0.9199

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: 16
  • eval_batch_size: 16
  • 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
1.5732 1.0 305 1.2601 0.8743 0.8858 0.8858 0.8790
0.9937 2.0 610 0.7465 0.8988 0.9098 0.9098 0.9033
0.5354 3.0 915 0.4557 0.9044 0.9158 0.9158 0.9092
0.2862 4.0 1220 0.3772 0.9198 0.9198 0.9198 0.9193
0.1724 5.0 1525 0.3306 0.9274 0.9259 0.9259 0.9261
0.1235 6.0 1830 0.3763 0.9214 0.9158 0.9158 0.9171
0.0902 7.0 2135 0.3808 0.9229 0.9218 0.9218 0.9219
0.0644 8.0 2440 0.3974 0.9229 0.9218 0.9218 0.9220
0.0575 9.0 2745 0.3930 0.9224 0.9218 0.9218 0.9218
0.0483 10.0 3050 0.4081 0.9205 0.9198 0.9198 0.9199

Framework versions

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