-
# 🚀 Feature request
Since `Trainer` handles both batch_size and gradient_accumulation_steps it seems like it could detect some out-of-memory situations and handle those scenarios automatically.
…
-
### 🐛 Describe the bug
Hello everybody.
I’ve been experimenting with different models and different frameworks, and I’ve noticed that, when using CPU, training a LSTM model on the IMDB dataset is …
-
**1. Requester Information:**
Katie van Werkhoven
RTI International
[kvanwerkhoven@rti.org](mailto:kvanwerkhoven@rti.org)
Matthew Denno
RTI International
[mdenno@rti.org](mailto:mdenno@rti.org…
-
## Problem
Currently in Zig, the way to express a program which properly handles all potential errors, in this case integer overflows, is not the easiest, laziest thing to do. To use addition as th…
-
Hi @AlexeyAB , I'm training yolov3 on bdd100k, now I have trained for 27200 iterations, but the loss seems can't get any lower, which has been around 5 for almost 10000 iterations, the mAP also grow s…
-
Hi,
I am facing issue. If I train bertopic on a same dataset multiple times, I am getting different number of topics .
As per the discussion in this thread: https://github.com/MaartenGr/BERTop…
-
We can't use the MIT License because it technically requires the copyright notice even in the binary. Would it be possible to relicense or dual-license this under the BSL (Boost Software License) ? Th…
-
Feature to automate a variety of tasks associated with training a predictive machine learning model to generate market forecasts given a set of input signals. In general, this aims would be a sandbox …
-
**Bug Report Checklist**
- [ x ] I provided code that demonstrates a minimal reproducible example.
- [ ] I confirmed bug exists on the latest mainline of AutoGluon via source install.
- [ ] I…
-
I'm looking for hints about how to correctly replicate the exact normalization process that is applied during simulated streaming with `decode.py` in `streaming_decode.py` for the streaming zipformer.…