Commit Graph

2613 Commits

Author SHA1 Message Date
Sang-Kil Park
64326dccfb
Fix it to run properly even if without --do_train param.
It was modified similar to `run_classifier.py`, and Fixed to run properly even if without `--do_train` param.
2019-01-10 21:51:39 +09:00
thomwolf
e5c78c6684 update readme and few typos 2019-01-10 01:40:00 +01:00
thomwolf
fa5222c296 update readme 2019-01-10 01:25:28 +01:00
Unknown
b3628f117e Added Squad 2.0 2019-01-08 15:13:13 -08:00
thomwolf
ab90d4cddd adding docs and example for OpenAI GPT 2019-01-09 00:12:43 +01:00
thomwolf
2e4db64cab add do_lower_case tokenizer loading optino in run_squad and ine_tuning examples 2019-01-07 13:06:42 +01:00
thomwolf
c9fd350567 remove default when action is store_true in arguments 2019-01-07 13:01:54 +01:00
Thomas Wolf
d3d56f9a0b
Merge pull request #166 from likejazz/patch-1
Fix error when `bert_model` param is path or url.
2019-01-07 12:40:55 +01:00
Thomas Wolf
766c6b2ce3
Merge pull request #159 from jaderabbit/master
Allow do_eval to be used without do_train and to use the pretrained model in the output folder
2019-01-07 12:31:06 +01:00
Thomas Wolf
77966a43a4
Merge pull request #156 from rodgzilla/cl_args_doc
Adding new pretrained model to the help of the `bert_model` argument.
2019-01-07 12:27:16 +01:00
Thomas Wolf
2e8c5c00ec
Merge pull request #141 from SinghJasdeep/patch-1
loading saved model when n_classes != 2
2019-01-07 12:21:13 +01:00
Sang-Kil Park
ca4e7aaa72
Fix error when bert_model param is path or url.
Error occurs when `bert_model` param is path or url. Therefore, if it is path, specify the last path to prevent error.
2019-01-05 11:42:54 +09:00
Jade Abbott
193e2df8ba Remove rogue comment 2019-01-03 13:13:06 +02:00
Jade Abbott
c64de50ea4 nb_tr_steps is not initialized 2019-01-03 12:34:57 +02:00
Jade Abbott
b96149a19b Training loss is not initialized if only do_eval is specified 2019-01-03 10:32:10 +02:00
Jade Abbott
be3b9bcf4d Allow one to use the pretrained model in evaluation when do_train is not selected 2019-01-03 09:02:33 +02:00
Grégory Châtel
186f75342e Adding new pretrained model to the help of the bert_model argument. 2019-01-02 14:00:59 +01:00
Jasdeep Singh
99709ee61d
loading saved model when n_classes != 2
Required to for: Assertion `t >= 0 && t < n_classes` failed,  if your default number of classes is not 2.
2018-12-20 13:55:47 -08:00
tholor
e5fc98c542 add exemplary training data. update to nvidia apex. refactor 'item -> line in doc' mapping. add warning for unknown word. 2018-12-20 18:30:52 +01:00
deepset
a58361f197
Add example for fine tuning BERT language model (#1)
Adds an example for loading a pre-trained BERT model and fine tune it as a language model (masked tokens & nextSentence) on your target corpus.
2018-12-18 10:32:25 +01:00
thomwolf
ae88eb88a4 set encoding to 'utf-8' in calls to open 2018-12-14 13:48:58 +01:00
thomwolf
e1eab59aac no fp16 on evaluation 2018-12-13 14:54:02 +01:00
thomwolf
087798b7fa fix reloading model for evaluation in examples 2018-12-13 14:48:12 +01:00
thomwolf
0f544625f4 fix swag example for work with apex 2018-12-13 13:35:59 +01:00
thomwolf
0cf88ff084 make examples work without apex 2018-12-13 13:28:00 +01:00
thomwolf
d3fcec1a3e add saving and loading model in examples 2018-12-13 12:50:44 +01:00
thomwolf
b3caec5a56 adding save checkpoint and loading in examples 2018-12-13 12:48:13 +01:00
Thomas Wolf
91aab2a6d3
Merge pull request #116 from FDecaYed/deyuf/fp16_with_apex
Change to use apex for better fp16 and multi-gpu support
2018-12-13 12:32:37 +01:00
Thomas Wolf
ffe9075f48
Merge pull request #96 from rodgzilla/multiple-choice-code
BertForMultipleChoice and Swag dataset example.
2018-12-13 12:05:11 +01:00
Deyu Fu
c8ea286048 change to apex for better fp16 and multi-gpu support 2018-12-11 17:13:58 -08:00
Thomas Wolf
e622790a93
Merge pull request #91 from rodgzilla/convert-examples-code-improvement
run_classifier.py improvements
2018-12-11 05:12:04 -05:00
Grégory Châtel
df34f22854 Removing the dependency to pandas and using the csv module to load data. 2018-12-10 17:45:23 +01:00
Grégory Châtel
d429c15f25 Removing old code from copy-paste. 2018-12-06 19:19:21 +01:00
Grégory Châtel
63c45056aa Finishing the code for the Swag task. 2018-12-06 18:53:05 +01:00
Grégory Châtel
c45d8ac554 Storing the feature of each choice as a dict for readability. 2018-12-06 16:01:28 +01:00
Grégory Châtel
0812aee2c3 Fixing problems in convert_examples_to_features. 2018-12-06 15:53:07 +01:00
Grégory Châtel
f2b873e995 convert_examples_to_features code and small improvements. 2018-12-06 15:40:47 +01:00
Grégory Châtel
83fdbd6043 Adding read_swag_examples to load the dataset. 2018-12-06 14:02:46 +01:00
Grégory Châtel
7183cded4e SwagExample class. 2018-12-06 13:39:44 +01:00
Grégory Châtel
fa7daa247d Fixing the commentary of the SquadExample class. 2018-12-06 13:14:33 +01:00
Grégory Châtel
a994bf4076 Fixing related to issue #83. 2018-12-05 18:16:30 +01:00
Grégory Châtel
c6d9d5394e Simplifying code for easier understanding. 2018-12-05 17:53:09 +01:00
Grégory Châtel
793262e8ec Removing trailing whitespaces. 2018-12-05 17:52:39 +01:00
Davide Fiocco
e60e8a6068
Correct assignement for logits in classifier example
I tried to address https://github.com/huggingface/pytorch-pretrained-BERT/issues/76
should be correct, but there's likely a more efficient way.
2018-12-02 12:38:26 +01:00
Davide Fiocco
dc13e276ee
Point typo fix 2018-12-01 01:02:16 +01:00
thomwolf
89d47230d7 clean up classification model output 2018-11-30 22:54:53 +01:00
thomwolf
c588453a0f fix run_squad 2018-11-30 14:22:40 +01:00
thomwolf
0541442558 add do_lower_case in examples 2018-11-30 13:47:33 +01:00
Li Li
0aaedcc02f Bug fix in examples;correct t_total for distributed training;run prediction for full dataset 2018-11-27 01:08:37 -08:00
thomwolf
32167cdf4b remove convert_to_unicode and printable_text from examples 2018-11-26 23:33:22 +01:00
thomwolf
05053d163c update cache_dir in readme and examples 2018-11-26 10:45:13 +01:00
thomwolf
6b2136a8a9 fixing weights decay in run_squad example 2018-11-20 10:12:44 +01:00
Thomas Wolf
061eeca84a
Merge pull request #32 from xiaoda99/master
Fix ineffective no_decay bug when using BERTAdam
2018-11-20 10:11:46 +01:00
thomwolf
2f21497d3e fixing param.grad is None in fp16 examples 2018-11-20 10:01:21 +01:00
xiaoda99
6c4789e4e8
Fix ineffective no_decay bug 2018-11-18 16:16:21 +08:00
thomwolf
27ee0fff3c add no_cuda args in extract_features 2018-11-17 23:04:44 +01:00
thomwolf
aa50fd196f remove unused arguments in example scripts 2018-11-17 23:01:05 +01:00
thomwolf
47a7d4ec14 update examples from master 2018-11-17 12:21:35 +01:00
thomwolf
c8cba67742 clean up readme and examples 2018-11-17 12:19:16 +01:00
thomwolf
757750d6f6 fix tests 2018-11-17 11:58:14 +01:00
thomwolf
4e46affc34 updating examples 2018-11-17 10:30:54 +01:00
thomwolf
cba85a67b9 fix nan in optimizer_on_cpu 2018-11-15 21:47:41 +01:00
thomwolf
1de35b624b preparing for first release 2018-11-15 20:56:10 +01:00