metadata

base_model: csebuetnlp/banglabert
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: banglabert-MLTC-BB1
    results: []

banglabert-MLTC-BB1

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

Loss: 0.3620
F1: 0.8590
F1 Weighted: 0.8576
Roc Auc: 0.8573
Accuracy: 0.5810
Hamming Loss: 0.1427
Jaccard Score: 0.7528
Zero One Loss: 0.4190

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	F1 Weighted	Roc Auc	Accuracy	Hamming Loss	Jaccard Score	Zero One Loss
0.5572	1.0	49	0.5051	0.8005	0.7870	0.7871	0.4216	0.2127	0.6673	0.5784
0.3995	2.0	98	0.4366	0.8273	0.8258	0.8160	0.5167	0.1838	0.7055	0.4833
0.3671	3.0	147	0.3832	0.8493	0.8493	0.8451	0.5630	0.1549	0.7380	0.4370
0.3239	4.0	196	0.3671	0.8600	0.8595	0.8573	0.5810	0.1427	0.7544	0.4190
0.2786	5.0	245	0.3593	0.8573	0.8557	0.8541	0.5784	0.1459	0.7503	0.4216
0.2783	6.0	294	0.3608	0.8530	0.8509	0.8502	0.5733	0.1497	0.7437	0.4267
0.2247	7.0	343	0.3576	0.8579	0.8564	0.8573	0.5758	0.1427	0.7511	0.4242
0.2354	8.0	392	0.3631	0.8591	0.8579	0.8560	0.5861	0.1440	0.7530	0.4139
0.2517	9.0	441	0.3630	0.8553	0.8541	0.8534	0.5758	0.1465	0.7472	0.4242
0.223	10.0	490	0.3620	0.8590	0.8576	0.8573	0.5810	0.1427	0.7528	0.4190

Framework versions

Transformers 4.41.1
Pytorch 2.1.2
Datasets 2.19.1
Tokenizers 0.19.1