# Error merge\_adapter on autotrain?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-merge-adapter-on-autotrain%2F72847%3E%5C
**Category:** 🤗AutoTrain\
**Created:** [February 12, 2024, 3:57pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-merge-adapter-on-autotrain%2F72847 "2024-02-12T15:57:55Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![wange56](https://avatars.discourse-cdn.com/v4/letter/w/e95f7d/32.png) [@wange56](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fwange56)%5C
**Post date:** [February 12, 2024, 3:57pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-merge-adapter-on-autotrain%2F72847%2F1 "2024-02-12T15:57:55Z")

</div>

Hi everyone!

After few tests, i’m keeping an error during merging adapter to models.  
I’m succefully train with a simple dataset (csv) based on Mistral models. After trying to merge it with the models, i got a failure with message: Connection errored out on the GUI.

Then i was tried to directly adjust the parameters and pass merge\_adapter to “true”.

The training is ok, but i have an error about merging (seems to be).

Below, the parameters and the output log with error.

Did i miss something? Any ideas would be welcome 🙂

Thx a lot

----Parameters----  
{  
“block\_size”: 1024,  
“model\_max\_length”: 2048,  
“padding”: “right”,  
“use\_flash\_attention\_2”: false,  
“disable\_gradient\_checkpointing”: false,  
“logging\_steps”: -1,  
“evaluation\_strategy”: “epoch”,  
“save\_total\_limit”: 1,  
“save\_strategy”: “epoch”,  
“auto\_find\_batch\_size”: false,  
“mixed\_precision”: “fp16”,  
“lr”: 0.00003,  
“epochs”: 3,  
“batch\_size”: 2,  
“warmup\_ratio”: 0.1,  
“gradient\_accumulation”: 1,  
“optimizer”: “adamw\_torch”,  
“scheduler”: “linear”,  
“weight\_decay”: 0,  
“max\_grad\_norm”: 1,  
“seed”: 42,  
“apply\_chat\_template”: false,  
“quantization”: “int4”,  
“target\_modules”: “”,  
“merge\_adapter”: true,  
“peft”: true,  
“lora\_r”: 16,  
“lora\_alpha”: 32,  
“lora\_dropout”: 0.05  
}

----Output logs with error-----

File “/app/env/lib/python3.10/site-packages/accelerate/commands/launch.py”, line 643, in simple\_launcher  
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)  
subprocess.CalledProcessError: Command ‘[’/app/env/bin/python’, ‘-m’, ‘autotrain.trainers.clm’, ‘–training\_config’, ‘autotrain-test/training\_params.json’]’ died with \<Signals.SIGKILL: 9\>.