Comments (3)
Thanks for your interest!
I checked versions of related packages, which is as the below.
torch 1.2.0
transformers 2.8.0
allennlp 0.9.0
Could you give me the versions which you use? I'll try to upgrade package to the latest versions and debug codes.
from dual-encoder-entity-retrieval-with-bert.
Thank you for your assistance.
I installed exactly the same package versions you listed above, and now it works fine. I'm no longer getting weird nvidia driver errors.
(venv2) root@b049732753c9:/home/repositories/Dual-encoder-Entity-Retrieval-with-BERT# python3 train.py -num_epochs 1
Loading faiss with AVX2 support.
Loading faiss.
===PARAMETERS===
debug False
debug_for_entity_encoder False
dataset xxx
cached_instance False
lr 5e-06
weight_decay 1e-08
beta1 0.9
beta2 0.999
epsilon 1e-08
amsgrad False
word_embedding_dropout 0.1
scalingMSEfactor 1.0
save_model 1
cuda_devices 0
num_epochs 1
batch_size_for_train 32
batch_size_for_eval 32
allen_lazyload False
bert_name bert-base-uncased
max_context_len 80
max_mention_len 12
max_left_context_len 35
max_right_context_len 35
max_canonical_len 12
max_def_len 48
experiment_logdir ./experiment_logdir/
mention_dump_dir ./mention_dump_dir/
kbemb_dim 300
search_method_for_faiss_during_construct_smallKBfortrain cossim
negatives_for_knn 500
cand_num_for_knn 10000
model_for_training blink_implementation_inbatchencoder
biencoder_scoring cossim
negatives_during_train_fixednegatives_biencoder 15
cand_num_before_sort_candidates_forBLINKbiencoder 10000
search_method_before_re_sorting_for_faiss cossim
add_mse 0
===PARAMETERS END===
100%|##########| 231508/231508 [00:00<00:00, 451633.17B/s]
loading KB
set value and load original KB
original KB loaded
2it [00:00, 375.31it/s]
2it [00:00, 346.29it/s]
train statistics: 2
100%|##########| 433/433 [00:00<00:00, 203374.43B/s]
100%|##########| 440473133/440473133 [01:13<00:00, 5954118.82B/s]
100%|##########| 407873900/407873900 [01:18<00:00, 5224338.64B/s]
accuracy: 0.5000, loss: 6.1127 ||: 100%|##########| 1/1 [00:00<00:00, 1.53it/s]
======Start encoding all entities in KB=====
======1. Start Tokenizing All Entities=====
======2. Encoding All Entities=====
100%|##########| 3/3 [00:00<00:00, 346.02it/s]
3it [00:00, 320.89it/s]0:00<?, ?it/s]
0%| | 0/1 [00:00<?, ?it/s]======Encoding all entites from canonicals and definitions=====
100%|##########| 1/1 [00:00<00:00, 10.97it/s]
=====Encoding all entities in KB FINISHED!=====
+++++Indexnizing KB from encoded entites+++++
+++++Indexnizing KB from encoded entites FINISHED!+++++
Loading BLINKBiencoder
Loaded: BLINKBiencoder
Evaluation for BLINK start
============
<<<FINAL EVALUATION STARTS>>> dev Retrieve_Candidates: 100
============
2it [00:00, 229.91it/s]
2it [00:00, 214.83it/s]
100%|##########| 1/1 [00:00<00:00, 19.92it/s]
============
<<<FINAL EVALUATION STARTS>>> test Retrieve_Candidates: 100
============
2it [00:00, 184.35it/s]
2it [00:00, 175.05it/s]
100%|##########| 1/1 [00:00<00:00, 21.80it/s]
result_dir: ./experiment_logdir/200812_183001/
Experiment time 194 sec
from dual-encoder-entity-retrieval-with-bert.
Thanks for your report. I'll fix README.md.
from dual-encoder-entity-retrieval-with-bert.
Related Issues (3)
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 dual-encoder-entity-retrieval-with-bert.