metadata

license: apache-2.0
tags:
  - generated_from_trainer
  - distilgpt2
  - email generation
  - email
datasets:
  - aeslc
  - postbot/multi_emails
widget:
  - text: >-
      Good Morning Professor Beans,

      Hope you are doing well. I just wanted to reach out and ask if
      differential calculus will be on the exam
    example_title: email to prof
  - text: >-
      Hey <NAME>,


      Thank you for signing up for my weekly newsletter. Before we get started,
      you'll have to confirm your email address.
    example_title: newsletter
  - text: >-
      Hi <NAME>,


      I hope this email finds you well. I wanted to reach out and ask about
      office hours
    example_title: office hours
  - text: >-
      Greetings <NAME>,


      I hope you had a splendid evening at the Company sausage eating festival.
      I am reaching out because
    example_title: festival
  - text: |-
      Good Morning Harold,

      I was wondering when the next
    example_title: event
  - text: URGENT - I need the TPS reports
    example_title: URGENT
  - text: |-
      Hi Archibald,

      I hope this email finds you extremely well.
    example_title: emails that find you
  - text: |-
      Hello there.

      I just wanted to reach out and check in to
    example_title: checking in
  - text: >-
      Hello <NAME>,


      I hope this email finds you well. I wanted to reach out and see if you've
      enjoyed your time with us
    example_title: work well
  - text: >-
      Hi <NAME>,


      I hope this email finds you well. I wanted to reach out and see if we
      could catch up
    example_title: catch up
  - text: >-
      I'm <NAME> and I just moved into the area and wanted to reach out and get
      some details on where I could get groceries and
    example_title: grocery
parameters:
  min_length: 4
  max_length: 128
  length_penalty: 0.8
  no_repeat_ngram_size: 2
  do_sample: false
  num_beams: 8
  early_stopping: true
  repetition_penalty: 5.5
base_model: distilgpt2

distilgpt2-emailgen

Why write the rest of your email when you can generate it?

from transformers import pipeline

model_tag = "postbot/distilgpt2-emailgen"
generator = pipeline(
              'text-generation', 
              model=model_tag, 
            )
            
prompt = """
Hello, 

Following up on the bubblegum shipment."""

result = generator(
    prompt,
    max_length=64,
    do_sample=False,
    early_stopping=True,
) # generate
print(result[0]['generated_text'])

try it in a Google Colab notebook
Use it in bash/cmd with this gist :)

For this model, formatting matters. The results may be (significantly) different between the structure outlined above and prompt = "Hey, just wanted to ..." etc.

Model description

This model is a fine-tuned version of distilgpt2 on a dataset of 50k emails, including the classic aeslc dataset.

It achieves the following results on the evaluation set:

Loss: 2.6247

Intended uses & limitations

The intended use of this model is to provide suggestions to "autocomplete" the rest of your email. Said another way, it should serve as a tool to write predictable emails faster. It is not intended to write entire emails; at least some input is required to guide the direction of the model.

Please verify any suggestions by the model for A) False claims and B) negation statements before accepting/sending something.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 6e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 32
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.02
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
2.8299	1.0	248	2.7971
2.6984	2.0	496	2.6826
2.7022	3.0	744	2.6361
2.6436	4.0	992	2.6245
2.6195	5.0	1240	2.6247

Framework versions

Transformers 4.21.1
Pytorch 1.12.0+cu113
Datasets 2.4.0
Tokenizers 0.12.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	24.89
ARC (25-shot)	21.76
HellaSwag (10-shot)	27.52
MMLU (5-shot)	25.97
TruthfulQA (0-shot)	46.17
Winogrande (5-shot)	51.62
GSM8K (5-shot)	0.0
DROP (3-shot)	1.16