# Got keyerror train error while fine tuning stability ai model using LORA

**URL:** <https://discuss.huggingface.co/t/got-keyerror-train-error-while-fine-tuning-stability-ai-model-using-lora/103688>\
**Category:** Models\
**Created:** [August 23, 2024, 10:17am UTC](https://discuss.huggingface.co/t/got-keyerror-train-error-while-fine-tuning-stability-ai-model-using-lora/103688 "2024-08-23T10:17:03Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Mohitdiff](https://avatars.discourse-cdn.com/v4/letter/m/ed8c4c/32.png) [@Mohitdiff](https://discuss.huggingface.co/u/Mohitdiff)\
**Post date:** [August 23, 2024, 10:17am UTC](https://discuss.huggingface.co/t/got-keyerror-train-error-while-fine-tuning-stability-ai-model-using-lora/103688/1 "2024-08-23T10:17:03Z")

</div>

Traceback (most recent call last):  
File “/content/train\_text\_to\_image\_lora\_sdxl.py”, line 1327, in   
main(args)  
File “/content/train\_text\_to\_image\_lora\_sdxl.py”, line 877, in main  
column\_names = dataset[“train”].column\_names  
File “/usr/local/lib/python3.10/dist-packages/datasets/dataset\_dict.py”, line 75, in **getitem**  
return super(). **getitem** (k)  
KeyError: ‘train’  
Traceback (most recent call last):  
File “/usr/local/bin/accelerate”, line 8, in   
sys.exit(main())  
File “/usr/local/lib/python3.10/dist-packages/accelerate/commands/accelerate\_cli.py”, line 48, in main  
args.func(args)  
File “/usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py”, line 1097, in launch\_command  
simple\_launcher(args)  
File “/usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py”, line 703, in simple\_launcher  
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)  
subprocess.CalledProcessError: Command ‘[’/usr/bin/python3’, ‘train\_text\_to\_image\_lora\_sdxl.py’, ‘–pretrained\_model\_name\_or\_path=stabilityai/stable-diffusion-xl-base-1.0’, ‘–pretrained\_vae\_model\_name\_or\_path=madebyollin/sdxl-vae-fp16-fix’, ‘–dataset\_name=data’, ‘–output\_dir=output\_lora’, ‘–caption\_column=prompt’, ‘–mixed\_precision=fp16’, ‘–validation\_prompt=a man with a rose in his mouth’, ‘–resolution=1024’, ‘–train\_batch\_size=1’, ‘–gradient\_accumulation\_steps=1’, ‘–gradient\_checkpointing’, ‘–learning\_rate=1e-4’, ‘–snr\_gamma=5.0’, ‘–lr\_scheduler=constant’, ‘–lr\_warmup\_steps=0’, ‘–push\_to\_hub’, ‘–mixed\_precision=fp16’, ‘–use\_8bit\_adam’, ‘–max\_train\_steps=500’, ‘–checkpointing\_steps=717’, ‘–seed=0’]’ returned non-zero exit status 1.