[Community notebooks] Add notebook on fine-tuning Electra and interpreting with IG

[elsanns]

Adding a link to a community notebook containing an example of:

• fine-tuning Electra on GLUE SST-2 with Trainer,
• running Captum Integrated Gradients token importance attribution on the results ,
• visualizing attribution with captum.attr.visualization.

[codecov]

Codecov Report

Merging #6321 into master will decrease coverage by 0.25%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master    #6321      +/-   ##
==========================================
- Coverage   79.52%   79.27%   -0.26%     
==========================================
  Files         148      148              
  Lines       27194    27194              
==========================================
- Hits        21627    21559      -68     
- Misses       5567     5635      +68     

Impacted Files	Coverage Δ
src/transformers/tokenization_roberta.py	76.71% <0.00%> (-21.92%)	⬇️
src/transformers/tokenization_utils_base.py	86.43% <0.00%> (-7.42%)	⬇️
src/transformers/tokenization_transfo_xl.py	38.73% <0.00%> (-3.76%)	⬇️
src/transformers/tokenization_utils_fast.py	92.14% <0.00%> (-2.15%)	⬇️
src/transformers/tokenization_openai.py	82.57% <0.00%> (-1.52%)	⬇️
src/transformers/tokenization_bert.py	91.07% <0.00%> (-0.45%)	⬇️
src/transformers/tokenization_utils.py	90.00% <0.00%> (-0.41%)	⬇️
src/transformers/file_utils.py	82.18% <0.00%> (-0.26%)	⬇️
src/transformers/tokenization_bart.py	95.77% <0.00%> (+35.21%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update c72f9c9...6505a38. Read the comment docs.

[patrickvonplaten]

Hey @elsanns - thanks a lot for your notebook! It looks great :-)

Also cc @LysandreJik, you might be interested in this!

[elsanns]

Thank you;)