dipteshkanojia's picture
update model card README.md
353054e
metadata
license: cc-by-4.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: hing-mbert-finetuned-code-mixed-DS
    results: []

hing-mbert-finetuned-code-mixed-DS

This model is a fine-tuned version of l3cube-pune/hing-mbert on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7248
  • Accuracy: 0.7364
  • Precision: 0.6847
  • Recall: 0.7048
  • F1: 0.6901

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: 2.7277800745684633e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 43
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
0.6977 2.0 497 0.7248 0.7364 0.6847 0.7048 0.6901

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.10.1+cu111
  • Datasets 2.3.2
  • Tokenizers 0.12.1