results

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

• Loss: 0.6504
• Accuracy: 0.8201

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: 16
• eval_batch_size: 16
• 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
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2063	0.2015	250	0.7486	0.7993
0.4038	0.4029	500	0.3953	0.8140
0.4264	0.6044	750	0.3772	0.8156
0.3938	0.8058	1000	0.3900	0.8146
0.393	1.0073	1250	0.4148	0.8172
0.2627	1.2087	1500	0.4601	0.8247
0.2864	1.4102	1750	0.4548	0.8185
0.2559	1.6116	2000	0.4390	0.8138
0.2607	1.8131	2250	0.4408	0.8215
0.247	2.0145	2500	0.4906	0.8241
0.1356	2.2160	2750	0.6311	0.8177
0.1462	2.4174	3000	0.6750	0.8150
0.1252	2.6189	3250	0.6950	0.8207
0.1339	2.8203	3500	0.6504	0.8201

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0