TextSummizer

This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6837
  • Rouge1: 0.421
  • Rouge2: 0.1462
  • Rougel: 0.248
  • Rougelsum: 0.3488
  • Generated Length: 120.0345

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Generated Length
3.0367 1.0 609 2.7608 0.4091 0.1389 0.2423 0.3401 122.0861
2.6396 2.0 1218 2.6925 0.4206 0.1468 0.2485 0.3508 124.4791
2.4229 3.0 1827 2.6837 0.421 0.1462 0.248 0.3488 120.0345

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1
Downloads last month
35
Safetensors
Model size
306M 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 WasibMehmood/TextSummizer

Finetuned
(27)
this model

Dataset used to train WasibMehmood/TextSummizer