Comments (5)
Discussion began in #25.
from transformersum.
Interesting. So do you plan on implementing it in the future?
from transformersum.
Interesting. So do you plan on implementing it in the future?
@moyid Yes I will implement this. I'm just not sure when I'll have the time.
from transformersum.
Profiler reports of the new vs old dataloading methods:
Profiler Report - New Dataloading
Action | Mean duration (s) | Total time (s)
-----------------------------------------------------------------
on_fit_start | 3.182e-05 | 3.182e-05
on_validation_start | 0.00015438 | 0.00030876
on_validation_epoch_start | 1.2273e-05 | 2.4545e-05
on_validation_batch_start | 1.8387e-05 | 0.01653
validation_step_end | 1.8699e-05 | 0.01681
on_validation_batch_end | 2.6562e-05 | 0.02388
on_validation_epoch_end | 1.8851e-05 | 3.7701e-05
on_validation_end | 2.4432 | 4.8864
on_train_start | 0.0011054 | 0.0011054
on_epoch_start | 0.00034487 | 0.00034487
on_train_epoch_start | 4.2872e-05 | 4.2872e-05
get_train_batch | 0.0061234 | 5.4927
on_batch_start | 2.6541e-05 | 0.023807
on_train_batch_start | 2.0627e-05 | 0.018503
training_step_end | 1.9472e-05 | 0.017466
model_forward | 0.29406 | 263.77
model_backward | 0.52279 | 468.94
on_after_backward | 1.7245e-05 | 0.015468
on_batch_end | 2.3942e-05 | 0.021476
on_train_batch_end | 2.8652e-05 | 0.025701
optimizer_step | 0.82151 | 368.86
on_epoch_end | 1.8765e-05 | 1.8765e-05
on_train_epoch_end | 1.0901e-05 | 1.0901e-05
on_train_end | 0.00030913 | 0.00030913
Profiler Report - New Dataloading with 4 Workers
Action | Mean duration (s) | Total time (s)
-----------------------------------------------------------------
on_fit_start | 4.8096e-05 | 4.8096e-05
on_validation_start | 0.00016712 | 0.00033424
on_validation_epoch_start | 2.1737e-05 | 4.3473e-05
on_validation_batch_start | 1.8466e-05 | 0.016601
validation_step_end | 2.1195e-05 | 0.019055
on_validation_batch_end | 2.8794e-05 | 0.025886
on_validation_epoch_end | 2.676e-05 | 5.352e-05
on_validation_end | 2.5799 | 5.1598
on_train_start | 0.000615 | 0.000615
on_epoch_start | 0.00031976 | 0.00031976
on_train_epoch_start | 2.731e-05 | 2.731e-05
get_train_batch | 0.0030533 | 2.7388
on_batch_start | 2.4564e-05 | 0.022034
on_train_batch_start | 2.0619e-05 | 0.018496
training_step_end | 1.7099e-05 | 0.015337
model_forward | 0.294 | 263.71
model_backward | 0.52549 | 471.36
on_after_backward | 2.0427e-05 | 0.018323
on_batch_end | 2.2888e-05 | 0.02053
on_train_batch_end | 2.7878e-05 | 0.025006
optimizer_step | 0.82418 | 370.06
on_epoch_end | 1.8855e-05 | 1.8855e-05
on_train_epoch_end | 1.3511e-05 | 1.3511e-05
on_train_end | 0.00064615 | 0.00064615
Profiler Report - Old Dataloading
Action | Mean duration (s) | Total time (s)
-----------------------------------------------------------------
on_fit_start | 3.0753e-05 | 3.0753e-05
on_validation_start | 0.00019413 | 0.00038826
on_validation_epoch_start | 1.2077e-05 | 2.4155e-05
on_validation_batch_start | 1.6663e-05 | 0.01498
validation_step_end | 1.6222e-05 | 0.014584
on_validation_batch_end | 2.3677e-05 | 0.021285
on_validation_epoch_end | 2.2077e-05 | 4.4154e-05
on_validation_end | 2.4987 | 4.9973
on_train_start | 0.00050591 | 0.00050591
on_epoch_start | 0.00025153 | 0.00025153
on_train_epoch_start | 1.6057e-05 | 1.6057e-05
get_train_batch | 0.0053287 | 4.7799
on_batch_start | 2.6401e-05 | 0.023682
on_train_batch_start | 2.0031e-05 | 0.017968
training_step_end | 1.6952e-05 | 0.015206
model_forward | 0.29384 | 263.57
model_backward | 0.5215 | 467.79
on_after_backward | 2.1365e-05 | 0.019164
on_batch_end | 2.3954e-05 | 0.021487
on_train_batch_end | 2.6314e-05 | 0.023603
optimizer_step | 0.82007 | 368.21
on_epoch_end | 3.2557e-05 | 3.2557e-05
on_train_epoch_end | 1.1635e-05 | 1.1635e-05
on_train_end | 0.00037779 | 0.00037779
from transformersum.
Added in commit f383286. Closing.
from transformersum.
Related Issues (20)
- TypeError: __init__() got an unexpected keyword argument 'gradient_checkpointing' HOT 1
- predictions_website.py raises AttributeError: '_LazyAutoMapping' object has no attribute '_mapping' HOT 6
- ModuleNotFoundError: No module named 'extractive' HOT 1
- AttributeError: '_LazyAutoMapping' object has no attribute '_mapping' HOT 1
- Abstractive BART Model , RuntimeError: The size of tensor a (64000) must match the size of tensor b (64001) at non-singleton dimension 1
- ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on. HOT 3
- error when training an extractive summarization model HOT 2
- Found keys that are in the model state dict but not in the checkpoint HOT 3
- Suggest about the index order of extractive results
- A Chinese solution for TransformerSum-extractive, and I've implemented your work in my project HOT 1
- After extractive training, a process on one GPU won't terminate automatically.
- Fine-tuning/Inference commands for "roberta-base-ext-sum"
- '--data_type' is not accepted when running main.py (extractive mode)
- Why tokenize twice?
- TypeError: forward() got an unexpected keyword argument 'source'
- Instruction for fine tune
- Installation via Pip
- Some versioning problems when installing the environment HOT 2
- pytorch_lightning.callbacks update HOT 1
- RoBERTa & Longformer extractive model checkpoints availability
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 transformersum.