What are the parameters using as arguments in full fine-tuning the google flan model in lab 2?

windows · December 16, 2023, 2:56pm

Could you provide the detailed arguments used in the TrainingArguments for the fully fine-tuned model that was downloaded during Lab 2?

I’ve rented an A100 server for many hours and have spent much money, but I’ve still been unable to reproduce a model that had the same level of performance of the model that was available in the full fine-tuning section of Lab 2.

I tried to increase the max_steps, but still not as good as the downloaded model…

chris.favila · December 17, 2023, 2:58pm

Hi Tony. Unfortunately, this info was lost. Our partner remembers though that the training ran for 5-6 hours to get that performance.

Topic		Replies	Views
Week 2 Lab - what parameters to use to fully fine-tune the model? (part 2.2) Generative AI with Large Language Models ai-discussions	4	28	March 11, 2025
Week2: training args for offline models Generative AI with Large Language Models week-2	5	439	August 18, 2023
Lab 2 - What training parameters were used to full train the LoRA tuned model? Generative AI with Large Language Models week-2	2	72	June 25, 2024
Lab 2. Training params for fine-tuned models from AWS Generative AI with Large Language Models week-2	1	176	May 7, 2024
Re-creating the model from S3 Generative AI with Large Language Models week-2	2	437	December 18, 2023

What are the parameters using as arguments in full fine-tuning the google flan model in lab 2?

Related topics