Search Results
| Search type | Search syntax |
|---|---|
| Tags | [tag] |
| Exact | "words here" |
| Author |
user:1234 user:me (yours) |
| Score |
score:3 (3+) score:0 (none) |
| Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
| Views | views:250 |
| Code | code:"if (foo != bar)" |
| Sections |
title:apples body:"apples oranges" |
| URL | url:"*.example.com" |
| Saves | in:saves |
| Status |
closed:yes duplicate:no migrated:no wiki:no |
| Types |
is:question is:answer |
| Exclude |
-[tag] -apples |
| For more details on advanced search visit our help page | |
Results tagged with bert
Search options not deleted
user 40765
For questions related to BERT (which stands for Bidirectional Encoder Representations from Transformers), a language representation model introduced in the paper "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding" (2019) by Google.
0
votes
1
answer
67
views
BERT: After pretraining 880000 step, why fine-tune not work? [closed]
training step 895429, loss 4.95, acc 0.082
dev loss 4.843, acc 0.092
Without restore the pretrained ckpt:
epoch 1:
training step 10429, loss 2.48, acc 0.606
dev loss 1.604, acc 0.8036
Restore the google's BERT-Base … Or restore from a pretrained ckpt pretrained from https://github.com/guotong1988/BERT-GPU
epoch 1:
training loss 1.89, acc 0.761
dev loss 1.351, acc 0.869 …
- 101
0
votes
Accepted
BERT: After pretraining 880000 step, why fine-tune not work?
change
bert_output = bert_model.get_pooled_output()
to
bert_output = tf.reduce_mean(bert_model.get_sequence_output()[:,1:,:],1)
- 101