Closed santhoshcameo closed 3 years ago
You're initializing CanineModel
, which doesn't accept a labels
argument.
You probably want to use CanineForSequenceClassification
, which is CANINE with a sequence classification head on top.
Also, please use the forum for training-related questions.
Environment info
transformers
version: 4.8.2Who can help
@NielsRogge @patrickvonplaten
Models:
Information
Model I am using is CANINE
I have a obfuscated documents consists around 30000 sentences and each has some labels too (in total 11 labels) - Multi Class Classification problem (The data has been obfuscated, however the patterns in them are preserved)
A single record look like this:
satwamuluhqgulamlrmvezuhqvkrpmletwulcitwskuhlemvtwamuluhiwiwenuhlrvimvqvkruhulenamuluhqgqvtwvimviwuhtwamuluhulqvkrenamcitwuhvipmpmqvuhskiwkrpmdfuhlrvimvskvikrpmqvuhskmvgzenleuhqvmvamuluhulenamuluhqvletwtwvipmpmgzleenamuhtwamuluhtwletwdfuhiwkrxeleentwxeuhpmqvuhtwiwmvamdfuhpkeztwamuluhvimvuhqvtwmkpmpmlelruhgztwtwskuhtwlrkrpmlruhpmuluhqvenuhtwyplepmxeuhenuhamypkrqvuhamulmvdfuhqvskentwamletwlrlrpmiwuhtwamul
So I am decided to try the CANINE since its works on the character encoding principle. But i am facing some issues, I have attached the code and exceptions.
Exception is
Expected behavior
Expected output is a multiclass classification model using CANINE Model where I should be able to get a prediction from test data set (obfuscated test data set).
Please advice.