Comments (3)
Hi,
The small config is just an example showing what setting Joey has, it does not result in a good translation system.
Try out the reverse task instead (reverse.yaml). Check out scripts/generate_reverse_task.py
to generate the data for it.
from joeynmt.
I fact I try use my dataset: it 543k so I split it 540000 train and 35000 dev. BUT it's not translation it's BOT and language used Finnish :( .
But after about 7-8 hours on Nvida Tesla P100 GPU Hypothesis: still empty. It's a little bit strange for me? As config I use small.yaml . Probably I must switch on reverse.yaml ? But I don't see particular difference.
from joeynmt.
The model there is not configured well for your task I'm afraid.
Try using this one
Make sure to change the data set correctly in the config.
from joeynmt.
Related Issues (20)
- Better Transformer `TokenBatchSampler` HOT 4
- Multi-GPU training. HOT 5
- JoeyNMT v1 procedure is no more compatible with JoeyNMT v2 HOT 12
- better config validation
- "AutocastCPU only supports Bfloat16" error when following rnn_reverse tutorial HOT 5
- RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) HOT 1
- AttributeError: module 'packaging' has no attribute 'version' HOT 2
- Unit test FAIL: testSentencepieceTokenizer (test.unit.test_tokenizer.TestTokenizer) HOT 4
- trg_mask generate problem HOT 4
- Running build_vocab.py for wmt17_bpe with or without --joint? HOT 3
- RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) HOT 5
- run predict function in Colab, get ConfigurationError: Invalid `batch_type` option.
- (enhancement) Deploying trained models on HuggingFace Space HOT 2
- Basic iwslt config train failure due to directory errors HOT 1
- Early stopping criteria is only checked for the `ReduceLROnPlateau` scheduler HOT 5
- Link in Tutorial to Collab dead HOT 4
- Tutorial - Test Set Evaluation HOT 5
- Columns and DataType Not Explicitly Set on line 387 of datasets.py
- Unit Test Fails - Windows Installation HOT 4
- serving & ONNX compat ?
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 joeynmt.