Hugging Face's logo

NaeemCSECUET18
/
indic-bert-MLTC-BB1

Text Classification
Transformers
Safetensors
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
indic-bert-MLTC-BB1 / README.md
NaeemCSECUET18's picture
NaeemCSECUET18
End of training
edf55a1 verified
preview code
|
raw
history blame contribute delete
2.81 kB
metadata
license: mit
base_model: ai4bharat/indic-bert
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: indic-bert-MLTC-BB1
    results: []

indic-bert-MLTC-BB1

This model is a fine-tuned version of ai4bharat/indic-bert on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5041
  • F1: 0.7518
  • Roc Auc: 0.7539
  • Accuracy: 0.3728
  • Hamming Loss: 0.2461
  • Jaccard Score: 0.6023
  • Zero One Loss: 0.6272

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: 24
  • eval_batch_size: 24
  • 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 F1 Roc Auc Accuracy Hamming Loss Jaccard Score Zero One Loss
0.6264 1.0 49 0.6551 0.6188 0.6176 0.1028 0.3824 0.4481 0.8972
0.6024 2.0 98 0.6163 0.6967 0.6442 0.3316 0.3554 0.5345 0.6684
0.5574 3.0 147 0.5932 0.7081 0.6492 0.3548 0.3503 0.5481 0.6452
0.5267 4.0 196 0.6041 0.7105 0.6512 0.3573 0.3483 0.5510 0.6427
0.4988 5.0 245 0.5409 0.7215 0.6822 0.3573 0.3175 0.5644 0.6427
0.4609 6.0 294 0.5189 0.7188 0.6880 0.3419 0.3117 0.5611 0.6581
0.4214 7.0 343 0.5426 0.7423 0.7196 0.3676 0.2802 0.5902 0.6324
0.426 8.0 392 0.5119 0.7478 0.7416 0.3702 0.2584 0.5972 0.6298
0.4034 9.0 441 0.5065 0.7526 0.7506 0.3805 0.2494 0.6033 0.6195
0.3974 10.0 490 0.5041 0.7518 0.7539 0.3728 0.2461 0.6023 0.6272

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.1.2
  • Datasets 2.19.1
  • Tokenizers 0.19.1