145 lines
4.5 KiB
Markdown
145 lines
4.5 KiB
Markdown
---
|
|
license:
|
|
- apache-2.0
|
|
tags:
|
|
- text generation
|
|
- emailgen
|
|
- email generation
|
|
- email
|
|
datasets:
|
|
- aeslc
|
|
- postbot/multi-emails-100k
|
|
|
|
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>,\n\nThank 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>,\n\nI hope this email finds you well. I wanted to reach out and ask about office hours"
|
|
example_title: "office hours"
|
|
- text: "Greetings <NAME>,\n\nI hope you had a splendid evening at the Company sausage eating festival. I am reaching out because"
|
|
example_title: "festival"
|
|
- text: "Good Morning Harold,\n\nI was wondering when the next"
|
|
example_title: "event"
|
|
- text: "URGENT - I need the TPS reports"
|
|
example_title: "URGENT"
|
|
- text: "Hi Archibald,\n\nI hope this email finds you extremely well."
|
|
example_title: "emails that find you"
|
|
- text: "Hello there.\n\nI just wanted to reach out and check in to"
|
|
example_title: "checking in"
|
|
- text: "Hello <NAME>,\n\nI 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>,\n\nI 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: 32
|
|
max_length: 128
|
|
no_repeat_ngram_size: 2
|
|
do_sample: True
|
|
temperature: 0.3
|
|
top_k: 20
|
|
top_p: 0.95
|
|
repetition_penalty: 3.5
|
|
length_penalty: 0.9
|
|
---
|
|
|
|
|
|
# gpt2-medium-emailgen
|
|
|
|
[](https://colab.research.google.com/gist/pszemraj/70058788c6d4b430398c12ee8ba10602/minimal-demo-for-postbot-gpt2-medium-emailgen.ipynb
|
|
)
|
|
|
|
Why write the entire email when you can generate (most of) it?
|
|
|
|
```python
|
|
from transformers import pipeline
|
|
|
|
model_tag = "postbot/gpt2-medium-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'])
|
|
```
|
|
|
|
## about
|
|
|
|
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the postbot/multi-emails-100k dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 1.5840
|
|
|
|
## Model description
|
|
|
|
More information needed
|
|
|
|
## Intended uses & limitations
|
|
|
|
- this is intended as a tool to save time writing predictable emails and not to write emails without a human-in-the-loop. validate that your email is factually correct before sending it to others.
|
|
|
|
## Training and evaluation data
|
|
|
|
- the dataset is essentially a hand-curated/augmented expansion to the classic `aeslc` dataset
|
|
|
|
## Training procedure
|
|
|
|
### Training hyperparameters
|
|
|
|
The following hyperparameters were used during training:
|
|
- learning_rate: 0.001
|
|
- train_batch_size: 16
|
|
- eval_batch_size: 16
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- gradient_accumulation_steps: 8
|
|
- total_train_batch_size: 128
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: cosine
|
|
- lr_scheduler_warmup_ratio: 0.02
|
|
- num_epochs: 3
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:-----:|:----:|:---------------:|
|
|
| 1.8701 | 1.0 | 789 | 1.8378 |
|
|
| 1.5065 | 2.0 | 1578 | 1.6176 |
|
|
| 1.1873 | 3.0 | 2367 | 1.5840 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.22.2
|
|
- Pytorch 1.10.0+cu113
|
|
- Datasets 2.5.1
|
|
- Tokenizers 0.12.1
|
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_postbot__gpt2-medium-emailgen)
|
|
|
|
| Metric | Value |
|
|
|-----------------------|---------------------------|
|
|
| Avg. | 25.97 |
|
|
| ARC (25-shot) | 26.45 |
|
|
| HellaSwag (10-shot) | 34.31 |
|
|
| MMLU (5-shot) | 24.1 |
|
|
| TruthfulQA (0-shot) | 43.96 |
|
|
| Winogrande (5-shot) | 50.43 |
|
|
| GSM8K (5-shot) | 0.0 |
|
|
| DROP (3-shot) | 2.53 |
|