Skip to content

update grpo notebooks to have per_device_train_batch_size=num_generat… #130

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

Open
mmathew23 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

update grpo notebooks to have per_device_train_batch_size=num_generat… #130

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 5 additions & 5 deletions nb/Advanced_Llama3_2_(3B)_GRPO_LoRA.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,8 @@
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
"colab_type": "text",
"id": "view-in-github"
},
"source": [
"<a href=\"https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Advanced_Llama3_2_(3B)_GRPO_LoRA.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
Expand Down Expand Up @@ -1257,7 +1257,7 @@
" lr_scheduler_type = \"cosine\",\n",
" optim = \"adamw_8bit\",\n",
" logging_steps = 1,\n",
" per_device_train_batch_size = 1,\n",
" per_device_train_batch_size = 4,\n",
" gradient_accumulation_steps = 4, # Increase to 4 for smoother training\n",
" num_generations = 4, # Decrease if out of memory\n",
" max_prompt_length = max_prompt_length,\n",
Expand Down Expand Up @@ -12746,8 +12746,8 @@
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": [],
"include_colab_link": true
"include_colab_link": true,
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
Expand Down
2 changes: 1 addition & 1 deletion nb/DeepSeek_R1_0528_Qwen3_(8B)_GRPO.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1711,7 +1711,7 @@
" lr_scheduler_type = \"linear\",\n",
" optim = \"adamw_8bit\",\n",
" logging_steps = 1,\n",
" per_device_train_batch_size = 1,\n",
" per_device_train_batch_size = 4,\n",
" gradient_accumulation_steps = 1, # Increase to 4 for smoother training\n",
" num_generations = 4, # Decrease if out of memory\n",
" max_prompt_length = max_prompt_length,\n",
Expand Down
169 changes: 70 additions & 99 deletions nb/Gemma3_(1B)-GRPO.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions nb/Gemma3_(4B)-Vision-GRPO.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1114,7 +1114,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
Expand Down Expand Up @@ -1144,7 +1144,7 @@
" lr_scheduler_type = \"cosine\",\n",
" optim = \"adamw_8bit\",\n",
" logging_steps = 1,\n",
" per_device_train_batch_size = 1,\n",
" per_device_train_batch_size = 4,\n",
" gradient_accumulation_steps = 2, # Increase to 4 for smoother training\n",
" num_generations = 4, # Decrease if out of memory\n",
" max_prompt_length = 1024,\n",
Expand Down
2 changes: 1 addition & 1 deletion nb/HuggingFace Course-Advanced_Llama3_1_(3B)_GRPO_LoRA.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -819,7 +819,7 @@
" lr_scheduler_type = \"cosine\",\n",
" optim = \"adamw_torch_fused\",\n",
" logging_steps = 1,\n",
" per_device_train_batch_size = 1,\n",
" per_device_train_batch_size = 8,\n",
" gradient_accumulation_steps = 4, # Increase to 4 for smoother training\n",
" num_generations = 8, # Decrease if out of memory\n",
" max_prompt_length = max_prompt_length,\n",
Expand Down
10 changes: 5 additions & 5 deletions nb/HuggingFace Course-Advanced_Llama3_2_(3B)_GRPO_LoRA.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,8 @@
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
"colab_type": "text",
"id": "view-in-github"
},
"source": [
"<a href=\"https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Advanced_Llama3_2_(3B)_GRPO_LoRA.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
Expand Down Expand Up @@ -1257,7 +1257,7 @@
" lr_scheduler_type = \"cosine\",\n",
" optim = \"adamw_8bit\",\n",
" logging_steps = 1,\n",
" per_device_train_batch_size = 1,\n",
" per_device_train_batch_size = 4,\n",
" gradient_accumulation_steps = 4, # Increase to 4 for smoother training\n",
" num_generations = 4, # Decrease if out of memory\n",
" max_prompt_length = max_prompt_length,\n",
Expand Down Expand Up @@ -12746,8 +12746,8 @@
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": [],
"include_colab_link": true
"include_colab_link": true,
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
Expand Down
2 changes: 1 addition & 1 deletion nb/HuggingFace Course-DeepSeek_R1_0528_Qwen3_(8B)_GRPO.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1713,7 +1713,7 @@
" lr_scheduler_type = \"linear\",\n",
" optim = \"adamw_8bit\",\n",
" logging_steps = 1,\n",
" per_device_train_batch_size = 1,\n",
" per_device_train_batch_size = 4,\n",
" gradient_accumulation_steps = 1, # Increase to 4 for smoother training\n",
" num_generations = 4, # Decrease if out of memory\n",
" max_prompt_length = max_prompt_length,\n",
Expand Down
Loading