Comments (5)
Thank you for providing your script and sorry for the issues with our model's sampling function.
I agree that the current behavior of the model is not optimal, and we should guide users better.
I will try make an update in the near future.
from be_great.
I suggest to train it longer 100+ epochs.
However, 11 rows and 25 columns is rather a very small dataset.
I would recommend here to do a prompt engineering with ChatGPT, Mixtral, or Claude.
from be_great.
Hi all,
I very much appreciate the clean and easy-to-use repo. In my limited experience with the repo, I've encountered OP's issue many times, however---that the generation loop is broken and no data is outputted. I've tried increasing the number of epochs (e.g. 200) and max_length
, but neither helps reliably. This remains true even when datasets are not tiny (e.g. 100 samples). To reproduce, e.g. use the UCI Spambase dataset (58 features):
from be_great import GReaT
from sklearn.datasets import fetch_openml
# load spam dataset, reduce to 100 samples
data = fetch_openml(data_id=44,as_frame=True).frame[:100]
# train model, takes about 12 minutes on a single GPU
model = GReaT(llm='distilgpt2', batch_size=32, epochs=200, fp16=True)
model.fit(data.to_numpy(), column_names=list(data.columns))
# generate---this will raise error "Breaking the generation Loop!"
synthetic_data = model.sample(n_samples=1000, max_length=2000)
print(len(synthetic_data))
assert len(synthetic_data)>0 # This will fail
Of course, in an example like the above you would expect the mode to overfit, but it's frustrating the model doesn't generate anything at all. Is there any guidance on when GReaT can be used reliably?
from be_great.
Thanks for the quick response! That'd be very helpful 😀
from be_great.
Hello, I am facing the same issue with NHANES 1999-2014 Dataset which consists of 6833 samples (rows) and 29 features (columns). I trained the model for 300 epochs, and tried generating with different max_length
parameter values. Any suggestions on how to fix this issue?
from be_great.
Related Issues (20)
- Breaking the generation loop HOT 3
- Long rows
- Suggestion: Improve sampling speed HOT 1
- Support for LoRA? HOT 1
- Unable to sample HOT 4
- Requirements don't allow numpy<1.24 HOT 3
- An error has occurred: Breaking the generation loop! HOT 4
- About how the GReaT model handles the generation of missing values (NaN) HOT 2
- How to randomly select a column for preconditioning for each epoch? HOT 7
- failing to use BART models - Breaking the generation loop! HOT 3
- Reg. Fine tuning for Time Series data generation
- How many samples are used for the classification and regression? HOT 2
- np.float is deprecated HOT 1
- Modifying the AutoModelForCausalLM HOT 4
- How many samples are used for the classification and regression? HOT 2
- Adding Native Distributed Data Parallels Support HOT 1
- No module named '_lzma' error on MacOS
- Can not be run on one 4090 GPU
- Error in sampling the data HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from be_great.