filtered_annotated94k_banglat5

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

• Loss: 0.1241
• Val accuracy: 0.9387
• Gen Len: 2.6493

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: 0.0005
• train_batch_size: 300
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Val accuracy	Gen Len
No log	1.0	253	0.1969	0.8979	2.6679
1.0947	2.0	506	0.1400	0.924	2.6558
1.0947	3.0	759	0.1280	0.9324	2.653
0.1281	4.0	1012	0.1250	0.9359	2.6522
0.1281	5.0	1265	0.1241	0.9387	2.6493

Framework versions

• Transformers 4.35.2
• Pytorch 1.13.1+cu117
• Datasets 2.17.0
• Tokenizers 0.15.1