localminimum / localminimum/R-net

Training restarted again after it hit 100%

Open
#42 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
319
Forks
121
PR merge metrics
No merged PRs in 30d

Description

Initially I had issue while running model.py. Cannot reshape array of size 27481400 into shape(91604,300).

But I have fixed it by changing the config value vocab_size by 2196018 .

My training has started successfully after the above config change. It was running around 5 days and completed 100 %. I left my machine open for training and I thought it will end up after 100%. But yesterday again it started to run from the scratch. Any issue here? or do I need to stop manually when it comes to 100%?

I set num_epochs to 10 in params.py file. Will it run for 10 cycles?

I have attached screen shot. Any help would be really appreciated
R-Net rerun issue
.

I have VM with 64 GB RAM and I am using Ubuntu 14.04.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading model.py and params.py, especially how num_epochs is interpreted and how training completion is handled. Reproduce the run if possible and trace what happens after reaching 100%. Done means the cause of the restart is identified and the training process has a clear, verified completion behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, tensorflow
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.