Comments (2)
Hi MixalisV,
Sorry for the late reply. I was unable to reproduce this. Here's what I've got when training for the first time:
02/14/2018 01:40:01 epoch [ 8] updates[ 21639] train loss[3.57525] remaining[0:00:00]
02/14/2018 01:40:21 dev EM: 66.05487228003784 F1: 75.85399816131314
02/14/2018 01:40:23 [new best model saved.]
02/14/2018 01:40:23 Epoch 9
02/14/2018 01:40:24 epoch [ 9] updates[ 21641] train loss[3.57521] remaining[0:04:54]
02/14/2018 01:40:24 epoch [ 9] updates[ 21644] train loss[3.57518] remaining[0:05:47]
02/14/2018 01:40:24 epoch [ 9] updates[ 21647] train loss[3.57509] remaining[0:05:57]
After resumimg:
02/14/2018 02:14:23 [Data loaded.]
02/14/2018 02:14:23 [loading previous model...]
02/14/2018 02:14:45 [dev EM: 66.05487228003784 F1: 75.85399816131314]
02/14/2018 02:14:45 Epoch 9
02/14/2018 02:14:45 epoch [ 9] updates[ 21641] train loss[2.78311] remaining[0:04:47]
02/14/2018 02:14:46 epoch [ 9] updates[ 21644] train loss[3.14489] remaining[0:05:03]
02/14/2018 02:14:46 epoch [ 9] updates[ 21647] train loss[3.07743] remaining[0:05:27]
02/14/2018 02:14:46 epoch [ 9] updates[ 21650] train loss[2.89589] remaining[0:05:33]
The loss decreases significantly because the loss printed is the average of all losses and the average calculation is starting from an empty history after resumimg.
Please check whether you are using the latest version of this repository (by git log -1
) and provide more information about your pytorch version.
from drqa.
Now the random states are totally recovered and loss display is consistent as well. Check out the latest version! (51a7ce0)
from drqa.
Related Issues (20)
- no model file HOT 2
- Adding Evidence as Database (like wikipedia ) HOT 5
- Only decode on a test set HOT 3
- FileNotFoundError: [Errno 2] No such file or directory: 'SQuAD/meta.msgpack' HOT 6
- How long to run the model for the default params HOT 2
- Is there a way to know the score of the prediction to analyse whether it is right or wrong? HOT 1
- planning to implement Attend It Again paper. HOT 2
- Using DrQA on an Chinese dataset HOT 3
- using DrQA for Squad 2.0 and other datasets HOT 1
- train stop HOT 3
- Finetune against a custom dataset HOT 1
- AssertionError: Torch not compiled with CUDA enabled HOT 2
- Regarding train.py HOT 2
- msgpack.exceptions.UnpackValueError: Unpack failed: error = 0 HOT 1
- Trying to understand the index_answer funtion HOT 6
- Getting low F1 and EM scores HOT 1
- Different function of evaluating metrics
- Gradient flow of the failing model
- training stopped at epoch 1 HOT 9
- Cant do "bash" HOT 7
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 drqa.