-
In the CLI we set `args.v_kl` to 0 for evidential. This flag is also used for the `v_kl` in dirichlet, but in the dirichlet paper, they suggest using a `v_kl` that changes with epoch:
.
My script is as follows:
OUTPUT_DIR=${1:-"./saves/llama-2-7b-oscar-ft"}
# random port between 30000 and 5…
-
## ❓ Questions and Help
Hi, I recieved loss None when training model. Anyone can help?
Simple reproduct kaggle notebook [link](https://www.kaggle.com/code/liondude/notebook548442067d)
```
im…
-
Hi @danielhanchen
I am trying to fine-tune gemma2-2b for my task following the guidelines of the continued finetuning in unsloth. Howver, I am facing OOM while doing so. My intent is to train gemm…
-
Evaluations are being run, _but no validation loss is logged or sent to WandB_
The console shows that eval is running, but displays a table along the lines of:
| eval loss | validation loss |
|…
-
When I run the workflow after updating ComfyUI-Advanced-ControlNet, the following error occurs. How can I solve it?
Error occurred when executing KSampler (Efficient):
'NoneType' object has no a…
-
Hello,
I just runned Get started code as below using pretrained model 'osnet_x1_0' and even 'resnet50' too.
However, the result was weird. mAP was just 3.9%.... and when I used resnet50, it was 2.x…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### System Info
Have installed all the requirements for Qwen2-vl
### Reproduction
train_mm_proj_only:True
Hello, I wan…