nadika's picture
updated readme
f41b003 verified
|
raw
history blame
3.24 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
base_model: google/muril-base-cased
widget:
  - text: >-
      मेयरले उपभोक्ता समितिसँग ३० प्रतिशत कमिसन लिएपछि विकासको काम गुणस्तरहीन,
      दबाब झेल्न नसकेर प्रशासकीय अधिकृतको भागाभाग। बाह्रबिसेका मेयरको मनोमानी-
      दोहोरीमा रमाइलो गरेको बिलसमेत नगरपालिकाबाटै भुक्तानी गर्न दबाब मेयरले
      उपभोक्ता समितिसँग ३० प्रतिशत कमिसन लिएपछि विकासको काम गुणस्तरहीन, दबाब
      झेल्न नसकेर प्रशासकीय अधिकृतको भागाभाग। 
model-index:
  - name: nepali_complaints_classification_muril3
    results: []

nepali_complaints_classification_muril3

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: 0.2575

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
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
2.3973 0.25 500 2.0247
1.7073 0.5 1000 1.3814
1.1586 0.75 1500 0.9054
0.8099 1.0 2000 0.6431
0.5456 1.25 2500 0.4845
0.434 1.5 3000 0.4157
0.3643 1.75 3500 0.3814
0.3144 2.01 4000 0.3432
0.2616 2.26 4500 0.3156
0.2418 2.51 5000 0.2952
0.2256 2.76 5500 0.2805
0.2157 3.01 6000 0.2908
0.1749 3.26 6500 0.2847
0.1626 3.51 7000 0.2734
0.1522 3.76 7500 0.2658
0.1443 4.01 8000 0.2560
0.1196 4.26 8500 0.2580
0.1138 4.51 9000 0.2618
0.1119 4.76 9500 0.2575

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2