Fix Log in Finetune Script

[szhengac]

Description

The finetune_squad.py has been wrong since 0.6.0. We cannot reproduce the log using all the past versions.

Checklist

Essentials

• PR's title starts with a category (e.g. [BUGFIX], [MODEL], [TUTORIAL], [FEATURE], [DOC], etc)
• Changes are complete (i.e. I finished coding on this PR)
• All changes have test coverage
• Code is well-documented

Changes

• Feature1, tests, (and when applicable, API doc)
• Feature2, tests, (and when applicable, API doc)

Comments

• If this change is a backward incompatible change, why must this change be made.
• Interesting edge cases to note here

cc @dmlc/gluon-nlp-team

[codecov]

Codecov Report

Merging #1001 into master will increase coverage by 0.56%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master    #1001      +/-   ##
==========================================
+ Coverage   89.29%   89.85%   +0.56%     
==========================================
  Files          67       67              
  Lines        6351     6351              
==========================================
+ Hits         5671     5707      +36     
+ Misses        680      644      -36

Impacted Files	Coverage Δ
src/gluonnlp/model/attention_cell.py	95.06% <0%> (+1.23%)	⬆️
src/gluonnlp/model/block.py	53.19% <0%> (+2.12%)	⬆️
src/gluonnlp/model/transformer.py	91.31% <0%> (+4.5%)	⬆️
src/gluonnlp/model/seq2seq_encoder_decoder.py	75.38% <0%> (+29.23%)	⬆️

[mli]

Job PR-1001/1 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-1001/1/index.html

[mli]

Job PR-1001/2 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-1001/2/index.html