#🔒 Fine tuning google mt5 small model for sinhalese to english translation

12 messages · Page 1 of 1 (latest)

weary yacht
#

I just wanted to ask that i have fine tuned a google mt5 model using my custom tokenizer trained on all sentence pairs of en-si on the opus 100 dataset
i am getting currently a validation loss of 3.3221 so now any tool or guide on how to calculate sacre bleu score of my fine tuned model

glass robinBOT
#

@weary yacht

Python help channel opened

Remember to:

  • Ask your Python question, not if you can ask or if there's an expert who can help.
  • Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
  • Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

Closes after a period of inactivity, or when you send !close.
weary yacht
#

Actually limit came on kaggle so two epoch steps did not execute but we are fine with 4

weary yacht
#

oh no shi we are cooked

stray cypress
weary yacht
#

Actually no problem

#

my tokenizer got fucked

#

working on that first'

stray cypress
#

OH, so this is done i guess?!

#

If so, do !close to let others know this needs no more help, otherwise ask your questions here.

glass robinBOT
#
Python help channel closed for inactivity

This help channel has been closed. Feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.