-
Hi there.
I’ve run the training code in this repository for 25k out of the 100k batches and achieved a validation loss of around 1.28, or perplexity of 3.59. After this, the training loss continues…
-
-
-
## 🐛 Bug
### To Reproduce
Steps to reproduce the behavior (**always include the command you ran**):
Run train.py with exact same arguments specified in examples/wav2vec/README.md
vq-wav2…
-
So I was training my model and it was going well, but I decided to stop training after a while and save the checkpoint to my google drive. Then I restarted training from the checkpoint with overwrite=…
r3ndd updated
5 years ago
-
Thanks for the excellent work :partying_face:
1. I'm looking for black-box optimization algorithms to perform prompt tuning on my neural network, which requires candidate solutions from each iterati…
-
我无法使用lstm实现td算法
例如：随机输入递减数列，数列元素取值区间为[0, 20]，数列长度区间为[2, 20]，输出该数列的相反数
要求：
- 使用LSTM
- 使用公式Q(s_t) = Q(s_{t+1}) - 1，规定Q(0) = 0
我期望得到一个类似[-3, -2, -1, 0]的递增数列，但是大部分情况下我只能得到[-4.5486226 -4.5486226 -…
-
### Version of the software
0.2.3
### Operating system
Windoes 10
### Browser / Native
Native
### What happened?
This has happened on two instances. The first time I had the Hits set to be sent…
-
Great work with the library! Is it still in use/active development?
I found a couple bugs in today's testing, I'll list them below rather than opening multiple issues:
1) Running commands in termi…
-
Kerbalism Version - 3.16
KSP Version - Latest from Steam
Mods - Admittedly, I'm running several mods beyond Kerbalism/RemoteTech.
Remotetech Version - 1.9.12
[Playerlog.zip](https://github.com/Ke…