MediBool-banglabert-Context_Aware

This model is a fine-tuned version of csebuetnlp/banglabert on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1367
• Accuracy: 0.9882
• F1: 0.9882

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 128
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.2935	0.2769	250	0.2018	0.9763	0.9763
0.1594	0.5537	500	0.1717	0.9776	0.9776
0.1662	0.8306	750	0.1184	0.9844	0.9844
0.0709	1.1074	1000	0.1548	0.9844	0.9844
0.0810	1.3843	1250	0.1246	0.9857	0.9857
0.0799	1.6611	1500	0.1152	0.9863	0.9863
0.0720	1.9380	1750	0.1242	0.9869	0.9869
0.0279	2.2148	2000	0.1691	0.9844	0.9844
0.0228	2.4917	2250	0.1072	0.9913	0.9913
0.0184	2.7685	2500	0.1114	0.9906	0.9906
0.0173	3.0454	2750	0.1519	0.9894	0.9894

Framework versions

• Transformers 5.1.0
• Pytorch 2.8.0+cu126
• Datasets 4.5.0
• Tokenizers 0.22.1