-
I am facing a very weird issue here.
### Issue
- The training speed slows down with time for batch sizes 64 and 128. For batch size 32 it seems to be staying fairly constant.
- The tensorboard g…
-
Hey guys.
I work at a relatively large scale company, and during my training loop I am eventually running OOM on my vms. This is unexpected and I was hoping someone could take a look at what I have…
-
As discussed in https://github.com/scikit-learn/scikit-learn/issues/12464#issuecomment-433815773 and https://github.com/scikit-learn/scikit-learn/issues/15358#issuecomment-549048650 in some specific u…
-
### The problem
The problem is that the convergence warning can be solved but that it effects the run time. The convergence warning can be solved by decreasing the max iteration or increasing the eps…
-
hello,
I am training a new `contentvec` model in order to replace the framework's `hubert` model with the newly trained `contentvec`.
However, when I tried to run the model created by learning wit…
-
### System Info
- `transformers` version: 4.45.2
- Platform: Linux-5.14.0-427.37.1.el9_4.x86_64-x86_64-with-glibc2.34
- Python version: 3.9.19
- Huggingface_hub version: 0.23.5
- Safetensors ve…
-
I was trying to use the solver to do DEA game cross-efficiency evaluation (based on the algorithm described in part 2 of this [paper](https://www.sciencedirect.com/science/article/pii/S095741741830387…
-
[Local collaborative autoencoders](https://sci-hub.ru/https://dl.acm.org/doi/abs/10.1145/3437963.3441808)
[Local latent space models for top-n recommendation](https://sci-hub.ru/https://dl.acm.org/do…
-
Building upon issues #4 and #5, we need a general module that explores several classification models.
Some libraries that can be explored for classification models are [scikit-learn](https://sciki…
-
## Context: the new `global_random_seed` fixture
#22749 introduces a new `global_random_seed` fixture to make it possible to run the same test with any seed between 0 and 99 included. By default, w…