wsdbanglat5_2e4_15

This model is a fine-tuned version of csebuetnlp/banglat5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0009

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.0234	1.0	1481	0.0182
0.019	2.0	2962	0.0126
0.0893	3.0	4443	0.0043
0.0363	4.0	5924	0.0880
0.002	5.0	7405	0.0015
0.0017	6.0	8886	0.0011
0.0011	7.0	10367	0.0011
0.0007	8.0	11848	0.0009
0.0011	9.0	13329	0.0009
0.0006	10.0	14810	0.0008
0.0003	11.0	16291	0.0010
0.0003	12.0	17772	0.0009
0.0002	13.0	19253	0.0009

Framework versions

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