nlpyang / BertSum

Code for paper Fine-tune BERT for Extractive Summarization

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Running the code for the first time

nimahassanpour opened this issue · comments

When I execute this line of command:

To train the BERT+Classifier model, run:
python train.py -mode train -encoder classifier -dropout 0.1 -bert_data_path ../bert_data/cnndm -model_path ../models/bert_classifier -lr 2e-3 -visible_gpus 0,1,2 -gpu_ranks 0,1,2 -world_size 3 -report_every 50 -save_checkpoint_steps 1000 -batch_size 3000 -decay_method noam -train_steps 50000 -accum_count 2 -log_file ../logs/bert_classifier -use_interval true -warmup_steps 10000

I get an error that -dropout, -decay_method, - world_size do not exist between args of the code. After deleting them and setting visible_gpus and -gpu_ranks to 0, which is for the first run, I get the following error
Untitled

Can you please help me to find out how to run the code?