Comments (6)
He meant in your evaluation command, you should replace -bert_data_path ~/o3/PreSumm/bert_data/
into -bert_data_path ~/o3/PreSumm/bert_data/cnndm
from presumm.
Change -bert_data_path ~/o3/PreSumm/bert_data/
to -bert_data_path ~/o3/PreSumm/bert_data/cnndm
, it will append the .valid/test.pt to that.
from presumm.
Thanks. The pre- processing steps change the json file 'cnndm_sample.train.0.bert.json' to torch file, 'cnndm_sample.train.0.bert.pt' . The torch file remains with that name throughout the training steps (ex, ab, & ex-ab). It doesn't give me the 'cnndm', which you showed. But I tried appending my torch file like you showed, to no avail : ( (all steps are documented : https://github.com/antonysama/PreSumm/blob/master/README.md).
from presumm.
How do you get the 'cnndm' file? Because I get 'cnndm_sample.train.0.bert.pt' after preprocessing, and even after training. I'm missing something between the processing and training, and that's the cnndm file you mention.
from presumm.
@antonysama
There is no cnndm
file
Specifying -bert_data_path ~/o3/PreSumm/bert_data/cnndm
is just a way to indicate to the code the folder with the root name of your training files. So if you have data from another dataset, you can put it in the same folder with a different root name.
Just try to run the same command with this option, without changing anything else.
Note : If you data files start with cnndm_sample
, you might need to change the option to -bert_data_path ~/o3/PreSumm/bert_data/cnndm_sample
from presumm.
Thanks, I'll try this. Much appreciated.
from presumm.
Related Issues (20)
- Key error HOT 1
- Additional position embedding increase parameters of transformer?
- having [Errno 21] Is a directory: while running train for BertExtAbs
- step 4 converting to simpler json returning asci error
- TypeError: __init__() got an unexpected keyword argument 'temp_dir'
- example_add_guidance.py
- Error when testing BertAbs model HOT 2
- Acc is very low and does not converge during training
- Cannot load model via torch.load HOT 1
- xsum数据集 HOT 1
- data preprocessing: empty 'tgt' text HOT 1
- issue for converting to bert_data HOT 2
- Use pretrained model : train_from HOT 9
- Getting the same sequence for all input candidate in generation
- How to do inference using pretrained bertsum models?
- Training the BERT large extractive model
- How can i know if i download BERT successfully
- bert-base-uncased HOT 2
- error in step 3 HOT 1
- 在运行test模式,BertAbs模型时,遇到了RuntimeError: "index_select_out_cuda_impl" not implemented for 'Float' HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from presumm.