-
Hi,
I upgraded from 1.5.0-rc1 to the current master branch and I started receiving the following error:
```
2018-01-27 02:48:38.928667: W tensorflow/core/framework/op_kernel.cc:1201] OP_REQUIRE…
-
The checkpoint files of a transformer model are quite large. The ones from the IWSLT_en_de architecture of fairseq are around 400MB, but these can grow bigger up to 2GB or more.
The problem is that G…
-
Hi, I have a few points in the research paper that I want to confirm and also a few questions to ask about fine-tuning procedure with JESC dataset.
From what I read:
- You use the big model to fin…
-
Hi, I ran your codes with different settings but got unexpected results that the model with PN performs worse than the model with LN.
The results are shown as following:
Transformer with LN:
```
N…
ghost updated
3 years ago
-
Hello, can you share the data set of the experiment, the displayed network link can no longer be downloaded.Thanks!
-
**Describe the bug**
Hello, when i use the deafult recipe for mustc v1, a bug raised(at stage 1):
**utils/validate_data_dir.sh: text contains 1 lines with non-printable characters**
I think this…
-
## 🚀 Feature
**Motivation**
https://github.com/pytorch/data#why-composable-data-loading
**_user-experience:_** TorchData datasets enable new functional API, auto-sharding, and snapshotting …
-
## 🐛 Bug
I was trying to train MMA-Hard model (a Simultaneous Translation model) on the WMT15 de-en data. After training started and 100-120 iterations done, I got "Only right padding is supporte…
-
## 🐛 Bug
When reproducing steps described in "Training a New Model" in documentation (https://fairseq.readthedocs.io/en/latest/getting_started.html#training-a-new-model) training end with an error
…
-
[INFO] elapsed=813.4, step=100, epoch=1, total word=713106, total batch=29584, loss=14.962, lr=1.87e-05
[ERROR] (XMem.cpp line 721): Cannot allocate the memory.
terminate called without an active ex…