bn_news_article_summarization

This model is a fine-tuned version of csebuetnlp/banglat5 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1868

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: 0.001
  • train_batch_size: 20
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 160
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine_with_restarts
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss
No log 0.99 83 0.5499
No log 2.0 167 0.6308
16.0025 2.99 250 0.4921
16.0025 3.99 334 0.4755
0.5191 5.0 418 0.4795
0.5191 5.99 501 0.4719
0.5191 7.0 585 0.4575
0.4756 8.0 669 0.4345
0.4756 8.99 752 0.3438
0.4157 10.0 836 0.2664
0.4157 10.99 919 0.2263
0.2776 11.99 1003 0.2013
0.2776 13.0 1087 0.1899
0.2776 13.99 1170 0.1872
0.2269 14.89 1245 0.1868

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
9
Safetensors
Model size
248M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for fahad1770/bengali_news_article_summarization_BanglaT5

Finetuned
(57)
this model