Edit model card

Model description

Parameter-efficient fine-tuning (PEFT) with QLoRA was employed to fine-tune the base google/flan-t5-large model on the samsum dataset containing dialoges. After the fine-tuning, the PEFT model adapter was merged with the base model. The model is intended for generative summarization tasks and achieved the following scores on the test dataset:

  • Rogue1: 49.249596%
  • Rouge2: 23.513032%
  • RougeL: 39.960812%
  • RougeLsum: 39.968438%

How to use

Load the model:

from transformers import pipeline
pipeline_model = pipeline("summarization", model="MuntasirHossain/flan-t5-large-samsum-qlora-merged")
summary = pipeline_model(text, max_new_tokens = 50)
print(summary[0]['summary_text'])

Example Inference:

# random sample text from the samsum test dataset
text = """
Emma: Hi, we're going with Peter to Amiens tomorrow.
Daniel: oh! Cool.
Emma: Wanna join?
Daniel: Sure, I'm fed up with Paris.
Emma: We're too. The noise, traffic etc. Would be nice to see some countrysides.
Daniel: I don't think Amiens is exactly countrysides though :P
Emma: Nope. Hahahah. But not a megalopolis either!
Daniel: Right! Let's do it!
Emma: But we should leave early. The days are shorter now.
Daniel: Yes, the stupid winter time.
Emma: Exactly!
Daniel: Where should we meet then?
Emma: Come to my place by 9am.
Daniel: oohhh. It means I have to get up before 7!
Emma: Yup. The early bird gets the worm (in Amiens).
Daniel: You sound like my grandmother.
Emma: HAHAHA. I'll even add: no parties tonight, no drinking dear Daniel
Daniel: I really hope Amiens is worth it!
"""

summary = pipeline_model(text, max_new_tokens = 50)
print(summary[0]['summary_text'])
Emma and Peter are going to Amiens tomorrow. Daniel will join them. They will meet at Emma's place by 9 am. They will not have any parties tonight.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Framework versions

  • PEFT 0.8.2
  • Transformers 4.38.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2
Downloads last month
0
Safetensors
Model size
784M params
Tensor type
F32
·
FP16
·
I8
·
Inference Examples
Inference API (serverless) does not yet support peft models for this pipeline type.

Model tree for MuntasirHossain/flan-t5-large-samsum-qlora-merged

Adapter
(143)
this model

Dataset used to train MuntasirHossain/flan-t5-large-samsum-qlora-merged