[ot][spam][crazy] adapters for semibalanced trees?

Undiscussed Horrific Abuse, One Victim of Many gmkarl at gmail.com
Fri Jul 22 02:56:11 PDT 2022


i actually did this. added adapters to longt5 in my repo branch, and
successfully trained on a csv file consisting of lines equal to "a,b"
. after 400 dataitems, loss dropped to around 0.6, eval loss was 0.0

i don't really know if it's _working_ or just looks like it is or
something, nor how it is interpreting the csv columns, yet

TRANSFORMERS_OFFLINE=1 python3 run_summarization.py
--model_name_or_path google/long-t5-tglobal-base     --do_train
--do_eval        --output_dir test     --per_device_train_batch_size=1
    --per_device_eval_batch_size=1     --overwrite_output_dir
--predict_with_generate --train_file test.csv --validation_file
test.csv --train_adapter True --num_train_epochs 100


More information about the cypherpunks mailing list