-
Reproduction is very inconsistent, but occasionally we see: ```
=================================== FAILURES ===================================
________________ test_sgd[dataframe-log-l1-float64-…
-
## 🐛 Bug
Pytorch documentation: https://pytorch.org/docs/stable/optim.html#torch.optim.SGD
"This is in contrast to Sutskever et. al. and other frameworks which employ an update of the form"
[original: nus-cs2113-AY2324S2/pe-in…
-
Hi!
I am running a linear evaluation right now on a simsiam network I've just trained. It's on a different repository.
In contrast to the evaluation protocol you've written, I use another one pref…
-
The text file for cell [9] is missing
`data = np.loadtxt('SGD_data.txt', delimiter=',')`
-
### Description of the bug
Hi, Dr Ou.
I am using your hicar pipeline. I download the test data, but I do not find the MAPSpeak dir in result file. I am wondering whether you can give me some advice.…
-
Currently weight updates are [calculated on `Native` backend](https://github.com/autumnai/leaf/blob/master/src/solvers/sgd/momentum.rs#L52). Profiling shows that about 40% of CPU time is spent doing c…
-
looks like the main thing left to do for this is to add the sample rule. for now, we will introduce a new kind of `let`. sample terms can only be used in assignment and all the code behind that assign…
ooovi updated
2 years ago
-
Step size of energy SGD: `0.8` / `0.6, 0.6` / `0.5, 0.5, 0.5` / `0.3, 0.3, 0.3, 0.3`
| setting | BLEU|
|-|-|
| delta steps = 2, sgd steps = 1 | 23.47 |
| delta steps = 2, sgd steps = 2 | 2…
zomux updated
4 years ago
-
I set the initial lr=0.0001, final_lr=0.1,
but I still don't know when the optimizer will become SGD.
Do I need to improve my learning rate to the final learning rate manually?
thanks！