Fine Tuning a Model in Gemini and Vertex AI | Steps to make a LLM

We walkthrough how how to fine tune a Gemini model in Vertex AI, that uses your input data to train the model. The video covers off where to tune, steps to follow on how to tune and create a JSONL file sample. We then show you where to find it and test it.

If you want a sample file let me know.

Contents:
00:00 Introduction
00:37 Vertex AI Language Models
01:01 Tune a Model steps
01:59 JSONL File overview
03:26 Create a JSONL file
05:21 Sample JSONL file - tips
06:21 Tuning Pipeline
08:30 Use the new Model
10:11 Model name in Google Cloud

#googleai #vertexai #geminiai

[uncle_slashes]

Based on the information in Google's doc - "The PaLM 2 for Text (text-bison, text-unicorn) foundation models are optimized for a variety of natural language tasks such as sentiment analysis, entity extraction, and content creation. The types of content that the PaLM 2 for Text models can create include document summaries, answers to questions, and labels that classify content." This video is not demonstrating Gemini.

[outcast]

great video! Thanks for this. Seems like its a lot simpler than having to understand how the tokenizer and architecture works and try to get your training dataset in that format. That being said, once tuned can the fine tuned model weights be downloaded to your local machine

[abdulrasool]

I finetuned gemini 1.0 pro for text classification. While finetuning i also provided a validation dataset. It showed some metrics called to be around 0.93 at the end of training. I am assuming it as the accuracy. But when i run the same model for my validation set locally and caluculate accuracy it is coming around 0.77 Then what is the metric that is shown in the vertex ai studio while training?

[HpVictus]

Can we fine tune again a fine tuned model with different dataset?

[noureddinhamouda]

thank you very much for this video, can you record another video for the chat-bison, I'm always getting an error when the training comes to the dataset-encoder.

[jonzh]

Thanks. Can make video for evaluating finetune results such as accuracy in vertex?

[pradachan]

can you turn off the browser when you just uploaded jsonl file to get trained, would it get trained or i have to keep the pc on>?

[John-jtdn]

Hello.. Thank you for the video.. I have a question.. for inputs i have examples questions and 5 other input parameters and or course and output. How can i integrated there parameters into the trainin data set? Which format should i use? Thanks.

[John-jtdn]

It took vertex AI to fine tune the data 2 hours 12 minutes on my side just for 10 examples while i was testing. Is there a way to speed this up? My original data has 14467 examples. It would take ages....

[Ristontestaus-onuq]

Hi there, thanks a lot for this. Trying to test somethign with it, but I get the "Failed to create pipeline job. Error: Permission denied on resource" error. I think it has to do with the service accounts and permissions. For me it only shows the compute engine default service account. I've gone to create service accounts but over there the instructions I've seen ask me to download a key, and that's no longer allowed. Could you please nudge me in the right direction on how to get the service account setup properly so that I could select it here? Thanks!

[KadirOrtac-xjww]

i've got an error like this Failed to process dataset for gemini-1.0-pro-002: Dataset validation failed: {"missing_messages_list": while tuning model. What am i supposed to do?

[MakeChangeNow]

what is the use case for making one? and how is it different than making an agent?

[ayushsinghal]

how can we fine tune the multimodal Gemini AI pro

[DeepakPoojary]

dude the code u copied at 3:20 and pasted at 3:50 are two different codes, can u please give this code

[KadirOrtac-xjww]

can i use my tuned model in my web application for free?