Skip to content

Remove max_prompt_length #345

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
stevhliu merged 2 commits into from
Feb 27, 2026
Merged

Remove max_prompt_length #345

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
09cf6b5
Remove max_prompt_length
miniMagic-beep Feb 27, 2026
d243ebe
Fix indentation for num_generations parameter
miniMagic-beep Feb 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 3 additions & 4 deletions notebooks/en/fine_tuning_llm_grpo_trl.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -470,9 +470,9 @@
"source": [
"### 3.4 Configuring GRPO Training Parameters\n",
"\n",
"Next, let's configure the training parameters for GRPO. We recommend experimenting with the `max_completion_length`, `num_generations`, and `max_prompt_length` parameters (refer to the image at the beginning for details about each of them).\n",
"Next, let's configure the training parameters for GRPO. We recommend experimenting with the `max_completion_length`and `num_generations` parameters (refer to the image at the beginning for details about each of them).\n",
"\n",
"To keep things simple, we’ll start by training for just one epoch and reducing the `max_completion_length`, `num_generations`, and `max_prompt_length` from their default values."
"To keep things simple, we’ll start by training for just one epoch and reducing the `max_completion_length`and `num_generations`from their default values."
],
"metadata": {
"id": "qW_3r8T1EtNg"
Expand Down Expand Up @@ -500,7 +500,6 @@
" # Parameters that control de data preprocessing\n",
" max_completion_length=64, # default: 256\n",
" num_generations=4, # default: 8\n",
" max_prompt_length=128, # default: 512\n",
"\n",
" # Parameters related to reporting and saving\n",
" report_to=[\"tensorboard\"],\n",
Expand Down Expand Up @@ -888,4 +887,4 @@
},
"nbformat": 4,
"nbformat_minor": 0
}
}