metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - samsum
metrics:
  - rouge
model-index:
  - name: switch-base-16-finetuned-samsum
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: samsum
          type: samsum
          config: samsum
          split: validation
          args: samsum
        metrics:
          - name: Rouge1
            type: rouge
            value: 47.2139
widget:
  - text: |-
      Sid: Wanna catch a movie?
      Annie: sure what do you have in mind?
      Sid; the Aquaman? :D
      Annie: haha isn't it a bit childish
      Sid: noooooo I mean yes but it's the highest grossing movie this week
      Annie: seriously?
      Sid: yeah?
      Annie: okay let's see what the fuss is all about

Switch Transformer (base-16) fine-tuned om samsum for conversation summarization

This model is a fine-tuned version of google/switch-base-16 on the samsum dataset. It achieves the following results on the evaluation set:

Loss: 1.4434
Rouge1: 47.2139
Rouge2: 23.3399
Rougel: 39.8364
Rougelsum: 43.2592
Gen Len: 16.9194

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: 4
eval_batch_size: 4
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	Rouge2	Rougel	Rougelsum	Gen Len
1.846	1.0	3683	1.4857	45.9134	22.4258	38.9716	42.6169	17.0623
1.5734	2.0	7366	1.4346	47.574	24.2967	40.3749	44.2636	17.3790
1.38	3.0	11049	1.4277	47.9915	24.9077	40.658	44.5301	17.1406
1.2388	4.0	14732	1.4223	48.3444	25.4061	41.2776	45.0434	16.9254
1.1629	5.0	18415	1.4372	48.5991	25.5464	41.3726	45.0784	16.9890

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.1+cu116
Datasets 2.7.1
Tokenizers 0.13.2