metadata

base_model: google/pegasus-cnn_dailymail
tags:
  - generated_from_trainer
  - dialog summarizer
model-index:
  - name: pegasus-finetuned-dialog-summarizer
    results: []
license: apache-2.0
datasets:
  - samsum
metrics:
  - rouge
library_name: transformers
widget:
  - text: >-
      Ernest: hey Mike, did you park your car on our street? Mike: no, took it
      into garage today Ernest: ok good Mike: why? Ernest: someone just crashed
      into a red honda looking just like yours Mike: lol lucky me.
  - text: >-
      Laura: Where are you? Paul: Almost there. Laura: Which is? Paul: Close to
      the Mac. Laura: That's so far away! Paul: 15 mins Laura: I am not waiting
      any more, see you some other time. Paul: Please, wait! Laura: I've waited
      30 minutes, 15 minutes ago you wrote you were almost here. This is too
      much. Paul: I am so sorry. Laura: I am not.
  - text: >-
      Lola: hey girlfriend, what's up? Adele: Oh, hi Lols, not much. Adele: got
      a new dog. Lola: another one? Adele: Yup. a pup biscuit lab. 4 months.
      Chewy. Lola: how did the others react? Adele: the cats keep their
      distance, Poppy and Lulu seem to mother him. Speedy wants to play. Lola:
      no fighting? that's new. Adele: they say puppies are accepted by other
      animals more easily than older dogs Lola: especially girl dogs, probably
      Adele: with the other ones I had to wean them because I took them in as
      adult dogs. And girls like to fight. like crazy. Lola: doggies, right/.
      Adele: that too :P Lola: haha. true though. Adele: I know, right. Anyway,
      called him Bones. He's so plump it kinda fit. Lola: cute. can't wait to
      see him.
  - text: >-
      Ali: I think I left my wallet at your place yesterday. Could you check?
      Garcia: Give me a sec, I'll have a look around my room. Ali: OK. Garcia:
      Found it! Ali: Phew, I don't know what I'd do if it wasn't there. Can you
      bring it to uni tomorrow? Garcia: Sure thing.

pegasus-finetuned-dialog-summarizer

This model is a fine-tuned version of google/pegasus-cnn_dailymail on the samsum dataset. It achieves the following results on the evaluation set:

Loss: 1.4894

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: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.6489	0.54	500	1.4894

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2