Edit model card

banglat5-finetuned-headlineBT5_1000_WithIp_1

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

  • Loss: 5.1889
  • Rouge1 Precision: 0.192
  • Rouge1 Recall: 0.1481
  • Rouge1 Fmeasure: 0.1493
  • Rouge2 Precision: 0.034
  • Rouge2 Recall: 0.0238
  • Rouge2 Fmeasure: 0.0257
  • Rougel Precision: 0.1832
  • Rougel Recall: 0.1382
  • Rougel Fmeasure: 0.1402
  • Rouge: {'rouge1_precision': 0.1920136634199134, 'rouge1_recall': 0.14811598124098124, 'rouge1_fmeasure': 0.14925985778926956, 'rouge2_precision': 0.03404265873015873, 'rouge2_recall': 0.023844246031746032, 'rouge2_fmeasure': 0.025712135087135088, 'rougeL_precision': 0.18318429834054833, 'rougeL_recall': 0.13817054473304474, 'rougeL_fmeasure': 0.14016822026013204}

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: 2e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • 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 Rouge1 Precision Rouge1 Recall Rouge1 Fmeasure Rouge2 Precision Rouge2 Recall Rouge2 Fmeasure Rougel Precision Rougel Recall Rougel Fmeasure Rouge
11.7469 1.0 160 8.0935 0.0715 0.1039 0.0761 0.0068 0.0122 0.0085 0.0715 0.1039 0.0761 {'rouge1_precision': 0.07145305878761761, 'rouge1_recall': 0.10394435425685425, 'rouge1_fmeasure': 0.07614152865370223, 'rouge2_precision': 0.006805555555555556, 'rouge2_recall': 0.012217261904761904, 'rouge2_fmeasure': 0.008484477124183007, 'rougeL_precision': 0.07145305878761761, 'rougeL_recall': 0.10394435425685425, 'rougeL_fmeasure': 0.07614152865370223}
8.8874 2.0 320 6.4819 0.1136 0.1427 0.1067 0.0217 0.0306 0.0217 0.1129 0.1406 0.1056 {'rouge1_precision': 0.11364718738219125, 'rouge1_recall': 0.14271974553224553, 'rouge1_fmeasure': 0.10674004897414845, 'rouge2_precision': 0.02169890873015873, 'rouge2_recall': 0.030600198412698412, 'rouge2_fmeasure': 0.021724970898143597, 'rougeL_precision': 0.11286593738219125, 'rougeL_recall': 0.1406364121989122, 'rougeL_fmeasure': 0.10560368533778482}
7.5001 3.0 480 5.6537 0.1619 0.1529 0.1379 0.0297 0.0278 0.0251 0.1595 0.148 0.1347 {'rouge1_precision': 0.16187199952824952, 'rouge1_recall': 0.15293786075036075, 'rouge1_fmeasure': 0.1378562003498065, 'rouge2_precision': 0.029678030303030303, 'rouge2_recall': 0.027787698412698413, 'rouge2_fmeasure': 0.02507508573298047, 'rougeL_precision': 0.15952157217782217, 'rougeL_recall': 0.14802714646464646, 'rougeL_fmeasure': 0.13468312342672956}
5.9849 4.0 640 5.2887 0.1799 0.1499 0.1427 0.0308 0.0238 0.0241 0.1714 0.14 0.1338 {'rouge1_precision': 0.17989579864579863, 'rouge1_recall': 0.14991657647907647, 'rouge1_fmeasure': 0.14274962921924997, 'rouge2_precision': 0.030773809523809523, 'rouge2_recall': 0.023844246031746032, 'rouge2_fmeasure': 0.024054670819376702, 'rougeL_precision': 0.1713640526140526, 'rougeL_recall': 0.13997113997113997, 'rougeL_fmeasure': 0.13379535432747508}
6.7428 5.0 800 5.1889 0.192 0.1481 0.1493 0.034 0.0238 0.0257 0.1832 0.1382 0.1402 {'rouge1_precision': 0.1920136634199134, 'rouge1_recall': 0.14811598124098124, 'rouge1_fmeasure': 0.14925985778926956, 'rouge2_precision': 0.03404265873015873, 'rouge2_recall': 0.023844246031746032, 'rouge2_fmeasure': 0.025712135087135088, 'rougeL_precision': 0.18318429834054833, 'rougeL_recall': 0.13817054473304474, 'rougeL_fmeasure': 0.14016822026013204}

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
12
Safetensors
Model size
248M params
Tensor type
F32
·
Inference API
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 mdosama39/banglat5-finetuned-headlineBT5_1000_WithIp_1

Finetuned
this model