-
Hi @dsindex
I'm getting the following error, while running `evaluate.py` with these parameters:
`evaluate.py --config=configs/config-bert.json --data_dir=data/conll2003 --model_path=pytorch-mod…
geo47 updated
3 years ago
-
Hi @dsindex
The new [BERT-Finetune](https://drive.google.com/file/d/1Vpt95HB-rOlI01OPZo00G0zizRkll67c/view?usp=sharing) model produces better results than the Luke benchmark. F1 score : 94.60 on C…
geo47 updated
3 years ago
-
insert learnable layer scaling parameters to be learned once LSTM weights are frozen (for eval tasks) when training on LM
-
**Issue by [W4ngatang](https://github.com/W4ngatang)**
_Monday Jun 25, 2018 at 05:14 GMT_
_Originally opened as https://github.com/nyu-mll/jiant/issues/15_
----
insert learnable layer scaling param…
-
**System (please complete the following information):**
- OS: Ubuntu 18.04
- Python version: 3.6.1
- AllenNLP version: v0.8.0
- PyTorch version: 1.0
**Question**
There are two questions a…
-
作者,你好,感谢您的分享。
今天在引入char_embeddings和word_embeddings,模型是charCNN + wordLSTM + CRF,发现一个疑似bug。训练过程中,“ERROR: LOSS EXPLOSION (>1e8) ! PLEASE SET PROPER PARAMETERS AND STRUCTURE! EXIT....”导致退出,回看日志发现是sample_…
-
Hey! I tried to run training of the varmisuse model in order to explore how it works on data from unseen projects. I have a few questions regarding it:
1. Seems like the dataset format has changed co…
-
Not top priority, but the largest model gets about 150 steps per minute, so a large training run (500k steps) could take two or three days. If anyone has spare bandwidth, do some CPU profiling and mak…
-
https://arxiv.org/pdf/1509.01626.pdf
from: charCNN
-
Hey,
I'm trying to use [SeqVecEmbedder](https://github.com/sacdallago/bio_embeddings/blob/develop/bio_embeddings/embed/seqvec_embedder.py#L15) with the newest [SeqVec v2](http://maintenance.dallago…