Info

Holy Snail
Author

Testing and Issues

You can test this entry and submit issues during the testing period of the ML Competition, Round 2 contest.

Entries with serious issues will not be able to win the contest, but even minor issues might be important for overall results.

Voting

by rating

Issues

Fair Leopard Nov 28, 2023 at 17:03
In our final tests, this submission received the following scores (out of 100):

Code Language Detection: 81.2
Overall Detection: 80
Average Time: 196.8ms per sample

Final Score: 0
10
Holy Snail Nov 30, 2023 at 23:22
Hi,
I hope you're doing well. I apologize for the late reply. I'm facing a perplexing issue: my submission takes 2ms on a laptop, PC, and Docker container. Additionally, I ran the winner's submission (the .so file shared in the group) for comparison, and it's twice as fast as mine, not 200 times faster as I expected.

I believe I've identified the problem. In my submission, there's a memory issue that can be resolved by adding the following line to the `initialize_tokens` function:
if(tokenizer != NULL) return;

I'm really curious to understand why my model is significantly slower and reaches the limit in the evaluation system and I want if it is possible let me know this fix the time issue
Nobody added any issues yet...