-
Notifications
You must be signed in to change notification settings - Fork 163
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Reproducing numbers from the paper on java-small dataset #6
Comments
Hi Alexander, Just |
Thank you for the prompt reply! Indeed, on colab instance some preprocessing has failed, but as state is not persistent there I did not get that stats (will take some hours to re-run, will post back) And from the same notebook (where some data failed to be preprocessed) results of running evaluation on test set with the best model is:
But I did preprocessing twice and training several times on the local machine, just in case (keep some intermediate .csv data), and in both cases results were the same
Numbers on the test set from the training logs on the local machine with all the data preprocessed, with increased patience to 20:
|
I see, you preprocessed much fewer examples than there are in the dataset. I designed the scripts to work on a 64-core machine, not on colab, so they timed out and less than 5% of the examples were extracted.
Regarding training - the default hyperparameters should be OK. In the paper I used (for Java-small specifically): config.SUBTOKENS_VOCAB_MAX_SIZE = 7300 and: config.TARGET_VOCAB_MAX_SIZE = 8700 But I think the default vocab sizes will work very similarly. |
I added a link to Java-med-preprocessed as well, in the README: |
Thank you! I'll try these out over the weekend and report back. From a quick glance - the numbers I posted are from training on ~1/10th of the data |
Hi Uri, May I ask what parameters you used for the java-med set? Also 190000 and 27000 respectively? Thank you! |
Hi @claudiosv, |
@urialon |
First of all - thank you for sharing the code of the model and a detailed reproduction instructions!
I tried to reproduce the results from the paper on the
java-small
dataset using default hyper-parameters fromconfig.py
, only changing the batch size to 256 to fit it into the GPU memory, and was able to fetch, preprocess data and train the model.On validation set, using the best model it got - Precision: 36.24, Recall: 26.89, F1: 30.88
In paper's Table 1 results on
java-small
are - Precision: 50.64, Recall: 73.40, F1: 43.02Here is a notebook with all the steps and the output.
Most probably I just have missed something obvious here and would be very grateful if you could help me by pointing out to the right direction in order to reproduce the paper's results.
Thanks in advance!
The text was updated successfully, but these errors were encountered: