-
Notifications
You must be signed in to change notification settings - Fork 297
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merge master into new_MT_branch. #977
Commits on Sep 19, 2019
-
Readme update for bert npi paper (#915)
* Update README.md * minor fix * Typo fix * typo fix
Configuration menu - View commit details
-
Copy full SHA for 10fb192 - Browse repository at this point
Copy the full SHA 10fb192View commit details
Commits on Sep 20, 2019
-
Fixing index problem & minor pytorch_transformers_interface cleanup (#…
…916) * update boundry func with offsets * update tasks that use indexes * remove outdated temporary fix
Configuration menu - View commit details
-
Copy full SHA for c36b74e - Browse repository at this point
Copy the full SHA c36b74eView commit details
Commits on Sep 23, 2019
-
Configuration menu - View commit details
-
Copy full SHA for 706b652 - Browse repository at this point
Copy the full SHA 706b652View commit details
Commits on Oct 1, 2019
-
* Initial QASRL * Updated pred writing for QASRL * Add validation shuffle to QASRL * Remove tqdm, modify class check in preds * qasrl rebase cleanup * Update QA-SRL to new repo changes * Removing src * QASRL Cleanup * updating to new model format * csv to tsv * QASRL update
Configuration menu - View commit details
-
Copy full SHA for b19ca78 - Browse repository at this point
Copy the full SHA b19ca78View commit details -
Implementing Data Parallel (#873)
* implemented data parallel * black style * Resolve last of merge marks * deleting irrelevant logs * adding new way to get attribute * updating to master * torch.Tensor -> torch.tensor for n_exs * black style * black style * Merge master * adapting other tasks to multiple GPU" * adding helper function for model attributes * adding get_model_attribute to main.py * deleting unecessary n_inbput for span_module * black style * revert comment change * fixing batch size keys * opt_params -> optimizer_params * Remove extraneous cahnges * changed n_exs to one-liner * adapting args.cuda to multi-GPU setting * adding use_cuda variable * Fixing parsing for case of args.cuda=subset * fixing tests * fixing nits, cleaning up parse_cuda function * additional nit * deleted extra space * Revert nit * refactoring into get_batch_size * removing use_cuda * adding options.py * removing use_cuda in tests, deleting extra changes * change cuda default * change parse_cuda_list_args import * jiant.options -> jiant.utils.options * change demo.conf cuda setting * fix bug -> make parse_cuda return int if only one gpu * fix bug * fixed tests * revert test_retokenize change * cleaning up code * adding addiitonal jiant.options * Separating cuda_device = int case with multiple cuda_device case * deleting remains of uses_cuda * remove time logging * remove use_cuda from evaluate * val_interval -> validation_interval * adding cuda comment to tutorial * fixed typo
Yada Pruksachatkun committedOct 1, 2019 Configuration menu - View commit details
-
Copy full SHA for 2553c2d - Browse repository at this point
Copy the full SHA 2553c2dView commit details
Commits on Oct 2, 2019
-
replace correct_sent_indexing with non inplace version (#921)
* replace correct_sent_indexing with non inplace version * Update modules.py * Update modules.py
Configuration menu - View commit details
-
Copy full SHA for 7508bea - Browse repository at this point
Copy the full SHA 7508beaView commit details
Commits on Oct 7, 2019
-
* anli * anli fix * Adding aNLI link, additional test/dev warning
Configuration menu - View commit details
-
Copy full SHA for 9d4baf3 - Browse repository at this point
Copy the full SHA 9d4baf3View commit details
Commits on Oct 10, 2019
-
* black style * adding SocialQA * black style * black style * fixed socialQA task * black style * Update citation * Nit * senteval * socialIQA naming * reverse unnecessary add
Yada Pruksachatkun committedOct 10, 2019 1Configuration menu - View commit details
-
Copy full SHA for 254dc37 - Browse repository at this point
Copy the full SHA 254dc37View commit details
Commits on Oct 16, 2019
-
Fixing bug with restoring checkpoint with two gpus + cleaning CUDA pa…
…rsing related code (#928) * black style * remove * cleaning up code around cuda-parsing * adding defaulting to -1 if there is no cuda devices detected * fixing nits, throw error instead of log warning for cuda not found
Yada Pruksachatkun committedOct 16, 2019 Configuration menu - View commit details
-
Copy full SHA for f0ef3f7 - Browse repository at this point
Copy the full SHA f0ef3f7View commit details
Commits on Oct 17, 2019
-
Configuration menu - View commit details
-
Copy full SHA for 8f46d4f - Browse repository at this point
Copy the full SHA 8f46d4fView commit details
Commits on Oct 21, 2019
-
* black style * adding initial senteval, senteval preprocessing script * black * adding senteval to registry * fixing bigram-shift * adding label_namespace arg, fixing the ksenteval tasks * revert extra changes * black style * change name -> senteval-probing * fixing senteval-probing tasks * renamed senteval -> sentevalprobing * delete extra imports * black style * renaming files and cleaning up preprocessing code * nit * black * deleting pdb * Senteval -> SE shorthand * fixing code style
Yada Pruksachatkun committedOct 21, 2019 Configuration menu - View commit details
-
Copy full SHA for 303a733 - Browse repository at this point
Copy the full SHA 303a733View commit details
Commits on Oct 22, 2019
-
Speed up retokenization (#935)
* black style * pre-loading tokenizer before retokenization function
Yada Pruksachatkun committedOct 22, 2019 Configuration menu - View commit details
-
Copy full SHA for 787e78b - Browse repository at this point
Copy the full SHA 787e78bView commit details
Commits on Oct 26, 2019
-
* scitail * Scitail * Scitail * update Scitail, removed config * update Scitail, removed config
Configuration menu - View commit details
-
Copy full SHA for 2ed6802 - Browse repository at this point
Copy the full SHA 2ed6802View commit details -
Add corrected data stastistics (#941)
Thanks to #936, we've discovered errors in our data statistics reporting in the edge probing paper. This table contains the corrected values. As there is more space here, the full (unrounded) values are reported instead. This was generated by a script that read the stats.tsv file and the diff vs. the paper should match my comment on the issue yesterday.
Configuration menu - View commit details
-
Copy full SHA for fb1eec1 - Browse repository at this point
Copy the full SHA fb1eec1View commit details -
CommonsenseQA+hellaswag (#942)
* add commonsenseqa task * add hellaswag task * dabug * from #928 * add special tokens to CommensenseQA input * format * revert irrelevant change * Typo fix * delete * rename stuff * Update qa.py * black
Configuration menu - View commit details
-
Copy full SHA for 1d40f23 - Browse repository at this point
Copy the full SHA 1d40f23View commit details
Commits on Oct 27, 2019
-
Configuration menu - View commit details
-
Copy full SHA for 3b07a5e - Browse repository at this point
Copy the full SHA 3b07a5eView commit details
Commits on Nov 3, 2019
-
* generalize ccg to other transformer models * debug * I don't know who broke this at what time, but let's just fix it here now
Configuration menu - View commit details
-
Copy full SHA for 347f743 - Browse repository at this point
Copy the full SHA 347f743View commit details
Commits on Nov 5, 2019
-
Fixing senteval-probing preprocessing (#951)
* Copying configs from superglue * adding senteval probing config commands * adding meta-script for transfer and probing exps * Adding meta bash script fixed * give_permissions script * small fix transfer_analysis.sh (#946) model_*.th might indicate several models; fixed to model_*.best.th * lr_patience fix * target_task training -> pretrain training * adding edgeprobing configs and command * adding edge probing conf * fix load_target_train bug * add hyperparameter sweeping * val_interval change * adding sweep function * Task specific val_intervals * add reload_vocab to hyperparameter sweep * adding batch_size specification * fixing senteval-word-content * fixing senteval preprocess script * revert extra delete * remove extra files * black format * black formatting trainer.py * remove load_data() * removing extra changes
Yada Pruksachatkun committedNov 5, 2019 Configuration menu - View commit details
-
Copy full SHA for 41abe5f - Browse repository at this point
Copy the full SHA 41abe5fView commit details
Commits on Nov 6, 2019
-
Adding tokenizer alignment function (#953)
* Copying configs from superglue * adding senteval probing config commands * adding meta-script for transfer and probing exps * Adding meta bash script fixed * give_permissions script * small fix transfer_analysis.sh (#946) model_*.th might indicate several models; fixed to model_*.best.th * lr_patience fix * target_task training -> pretrain training * adding edgeprobing configs and command * adding edge probing conf * fix load_target_train bug * add hyperparameter sweeping * val_interval change * adding sweep function * Task specific val_intervals * add reload_vocab to hyperparameter sweep * adding batch_size specification * fixing senteval-word-content * fixing senteval preprocess script * revert extra delete * remove extra files * black format * black formatting trainer.py * remove load_data() * removing extra changes * adding alignment mapping function * fix comment nits * comment nit * adding example of token_alignment
Yada Pruksachatkun committedNov 6, 2019 Configuration menu - View commit details
-
Copy full SHA for 98b1dc8 - Browse repository at this point
Copy the full SHA 98b1dc8View commit details
Commits on Nov 8, 2019
-
* add nli prob task template * Create acceptablity_probing.py * specify nli probing tasks * port acceptablity probing tasks * add directory name * debug * debug * format * black * revert unintended change
Configuration menu - View commit details
-
Copy full SHA for d769338 - Browse repository at this point
Copy the full SHA d769338View commit details
Commits on Nov 9, 2019
-
* misc run scripts * cosmosqa * cosmosqa * cosmosqa * cosmosqa run * cleaned up repo * cleaned up repo * reformatted
Configuration menu - View commit details
-
Copy full SHA for 8af068d - Browse repository at this point
Copy the full SHA 8af068dView commit details
Commits on Nov 10, 2019
-
Configuration menu - View commit details
-
Copy full SHA for 1ee0d95 - Browse repository at this point
Copy the full SHA 1ee0d95View commit details
Commits on Nov 12, 2019
-
* qamr * tokenization * temp qamr * qamr * QASRL * Undo slicing * quick hack to bypass bad qasrl examples * f1 em fix * tokenization fixes * average * New tokenization aligner * update example counts * Cleanup * Typography
Configuration menu - View commit details
-
Copy full SHA for 2a9230b - Browse repository at this point
Copy the full SHA 2a9230bView commit details
Commits on Nov 14, 2019
-
Set _unk_id in Roberta module (#959)
Currently the `_unk_id` for Roberta is not set correctly, which triggers the assertion error on line 118.
Configuration menu - View commit details
-
Copy full SHA for 39b234e - Browse repository at this point
Copy the full SHA 39b234eView commit details
Commits on Nov 15, 2019
-
Fixing load_target_train_checkpoint with mixing setting (#960)
* adding loading for mix * black style
Yada Pruksachatkun committedNov 15, 2019 Configuration menu - View commit details
-
Copy full SHA for 7dc9965 - Browse repository at this point
Copy the full SHA 7dc9965View commit details
Commits on Nov 20, 2019
-
Configuration menu - View commit details
-
Copy full SHA for daec5cf - Browse repository at this point
Copy the full SHA daec5cfView commit details
Commits on Nov 22, 2019
-
* generalize ccg to other transformer models * debug * I don't know who broke this at what time, but let's just fix it here now * ccg lazy iterator * debug * clean up * debug * debug ccg, minor cleanup
Configuration menu - View commit details
-
Copy full SHA for 8a059b8 - Browse repository at this point
Copy the full SHA 8a059b8View commit details
Commits on Nov 23, 2019
-
Configuration menu - View commit details
-
Copy full SHA for c181273 - Browse repository at this point
Copy the full SHA c181273View commit details
Commits on Nov 27, 2019
-
Configuration menu - View commit details
-
Copy full SHA for 42b389f - Browse repository at this point
Copy the full SHA 42b389fView commit details
Commits on Dec 9, 2019
-
Configuration menu - View commit details
-
Copy full SHA for 18ca100 - Browse repository at this point
Copy the full SHA 18ca100View commit details