-
Yes, the colour does change, but the icon's and title's color does NOT REFLECT THE LASTEST state but the lowest state in my case. Look at this weight curve and you can see that the orange belongs to t…
-
i try to pre-train supNMT,but this error occur:Not all gradients have been reduced from the backward of the previous iteration.
All params(src and tgt are mono lang,just like en and zh):
Namespace…
-
I trained lightconv model via fairseq .
When I used it in bert nmt, I got this error .
`(bertNMT) blue90211@AI02:~/Storage01/bert-nmt$ CUDA_VISIBLE_DEVICES=0 python train.py $DATAPATH -a $ARCH --op…
-
Hello,
I'm Eugenio Bertolini, a big fan of your works with Lightining Pose (LP) and EKS. Thank you so much for this incredible tool.
In the LP paper you were mentioning that the unsupervised losse…
-
### 🐛 Describe the bug
```python
batch_size = 10
channels = 3
length = 32
input_tensor = torch.randn([batch_size, channels, length])
adaptive_avg_pool = nn.AdaptiveAvgPool2d(output_size=16)
out…
-
The log is as follow:
0%| | 33792/407873900 [00:29
-
# Context
Documenting validation of a fast and differentiable cosmological model. This model defines a joint distribution over cosmology $\Omega$, initial conditions $\delta_L$, Lagrangian biases $b$…
-
Elegant work! In addition to training a transformer_base-scale model, I am still trying to train a large model, (e.g., 1024 model dim. & 4096 hidden dim), such that I can fine-tune Mask-predict with […
-
I'm trying to run udify on some data and have followed the instructions, e.g.
```bash
$ git clone https://github.com/Hyperparticle/udify
$ pip install -r ./requirements.txt
$ curl --remote-name…
-
`loek@DORAEMON:~/modernmt4$ ./mmt create zh en data/proceng -e proceng --gpus 0 --resume
=========== TRAINING STARTED ===========
ENGINE: proceng
LANGUAGE: zh > en
(1/4) Cleaning corpora
…