Wikitext - [WIP] #150
Open
Wikitext - [WIP] #150
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- added dependencies, benchmark - added token generation and model training code from moasha in dependencies
- returning prediction time for evaluation time - changed perplexity --> log_perplexity for the objective (MO-ASHA uses log perplexity) changed error --> accuracy - added tqdm
-report train and eval time separately in objective func -code formatting -added test file
- added recipe and container file
…al encoding doesn't work for odd number, therefor log seems like perfect solution -removed logs
* Update Github Actions Workflow and drop support for singularity < 3.7
PhMueller
reviewed
May 24, 2022
PhMueller
reviewed
May 24, 2022
PhMueller
reviewed
May 24, 2022
PhMueller
reviewed
May 24, 2022
PhMueller
requested changes
May 24, 2022
hpobench/container/recipes/mo/Singularity.LanguageModelBenchmark
Outdated
Show resolved
Hide resolved
hpobench/container/recipes/mo/Singularity.LanguageModelBenchmark
Outdated
Show resolved
Hide resolved
hpobench/container/recipes/mo/Singularity.LanguageModelBenchmark
Outdated
Show resolved
Hide resolved
* Add yahpo_gym w help from phmueller Co-authored-by: PhMueller <[email protected]>
Update the Nasbench201 benchmark to support Multi-Objective queries. If you want to use the *single objective* Nasbench201 benchmark, you can query the SO version of this benchmark. Although, we have not changed the benchmark logic, you can also use the container v0.0.5 in your experiments to reproduce results from the old version of this benchmark.
We add the benchmark from the MO-ASHA paper by Schmucker et al. It is a MO benchmark, training an MLP on the Adult data set.
Added mo cnn benchmarks from bag of baseline paper We deviate from the original benchmark in two points: * we return as cost only the training time instead of the total elapsed time * we return as objective for minimization instead of `-100 * accuracy` now `1 - accuracy` to achieve better output scalings. Co-authored-by: ayushi-3536 <[email protected]> Co-authored-by: Philipp Müller <[email protected]>
PhMueller
requested changes
Jun 1, 2022
| class TransformerModel(nn.Module): | ||
| """Container module with an encoder, a transformer module, and a decoder.""" | ||
|
|
||
| def __init__(self, ntoken, ninp, nhead, nhid, nlayers, dropout=0.5, bptt=35, rng=None): |
-add dependency version
- added dependencies, benchmark - added token generation and model training code from moasha in dependencies
- returning prediction time for evaluation time - changed perplexity --> log_perplexity for the objective (MO-ASHA uses log perplexity) changed error --> accuracy - added tqdm
-report train and eval time separately in objective func -code formatting -added test file
- added recipe and container file
…al encoding doesn't work for odd number, therefor log seems like perfect solution -removed logs
-add dependency version
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.