pszemraj's picture
Adding Evaluation Results (#3)
155a823
---
license: apache-2.0
tags:
- generated_from_trainer
- distilgpt2
- 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: 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
---
# distilgpt2-emailgen: V2
[![colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/pszemraj/d1c2d88b6120cca4ca7df078ea1d1e50/scratchpad.ipynb)
Why write the rest of your email when you can generate it?
```python
from transformers import pipeline
model_tag = "postbot/distilgpt2-emailgen-V2"
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'])
```
## Model description
This model is a fine-tuned version of `distilgpt2` on the postbot/multi-emails-100k dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9126
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters (run 1/2)
TODO
### Training hyperparameters (run 2/2)
The following hyperparameters were used during training:
- learning_rate: 0.0006
- 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: 0.01
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.9045 | 1.0 | 789 | 2.0006 |
| 1.8115 | 2.0 | 1578 | 1.9557 |
| 1.8501 | 3.0 | 2367 | 1.9110 |
| 1.7376 | 4.0 | 3156 | 1.9126 |
### 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__distilgpt2-emailgen-V2)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 24.59 |
| ARC (25-shot) | 20.99 |
| HellaSwag (10-shot) | 26.78 |
| MMLU (5-shot) | 25.53 |
| TruthfulQA (0-shot) | 46.51 |
| Winogrande (5-shot) | 52.01 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 0.31 |