Skip to content

fixed typos in the notebooks #36

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

fixed typos in the notebooks #36

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
17 changes: 15 additions & 2 deletions 18_sagemaker_training_recipes/nova/nova-lite-dpo-peft.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1825,7 +1825,7 @@
" if custom_model_arn is not None\n",
" else \"<CUSTOM_MODEL_DEPLOYMENT_ARN>\"\n",
" ),\n",
" \"us.amazon.nova-micro-v1:0\",\n",
" \"us.amazon.nova-lite-v1:0\",\n",
"]\n",
"\n",
"# Change model ID to run LLM as a judge evaluation on the fine-tuned model or base model\n",
Expand Down Expand Up @@ -1985,7 +1985,7 @@
"source": [
"recipe_content = f\"\"\"\n",
"run:\n",
" name: nova-micro-llm-judge-eval-job\n",
" name: nova-lite-llm-judge-eval-job\n",
" model_type: amazon.nova-micro-v1:0:128k\n",
" model_name_or_path: \"nova-micro/prod\"\n",
" replicas: 1 # unmodifiable\n",
Expand Down Expand Up @@ -2127,6 +2127,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d3fbf582",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "2e9af4f5",
Expand Down
17 changes: 15 additions & 2 deletions 18_sagemaker_training_recipes/nova/nova-lite-dpo.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1825,7 +1825,7 @@
" if custom_model_arn is not None\n",
" else \"<CUSTOM_MODEL_DEPLOYMENT_ARN>\"\n",
" ),\n",
" \"us.amazon.nova-micro-v1:0\",\n",
" \"us.amazon.nova-lite-v1:0\",\n",
"]\n",
"\n",
"# Change model ID to run LLM as a judge evaluation on the fine-tuned model or base model\n",
Expand Down Expand Up @@ -1985,7 +1985,7 @@
"source": [
"recipe_content = f\"\"\"\n",
"run:\n",
" name: nova-micro-llm-judge-eval-job\n",
" name: nova-lite-llm-judge-eval-job\n",
" model_type: amazon.nova-micro-v1:0:128k\n",
" model_name_or_path: \"nova-micro/prod\"\n",
" replicas: 1 # unmodifiable\n",
Expand Down Expand Up @@ -2127,6 +2127,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3d1d12be",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "3d41dcf4",
Expand Down
23 changes: 17 additions & 6 deletions 18_sagemaker_training_recipes/nova/nova-lite-sft-peft.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1856,7 +1856,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "0dedce87",
"id": "f04231c2",
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -1866,7 +1866,7 @@
" if custom_model_arn is not None\n",
" else \"<CUSTOM_MODEL_DEPLOYMENT_ARN>\"\n",
" ),\n",
" \"us.amazon.nova-micro-v1:0\",\n",
" \"us.amazon.nova-lite-v1:0\",\n",
"]\n",
"\n",
"# Change model ID to run LLM as a judge evaluation on the fine-tuned model or base model\n",
Expand All @@ -1890,9 +1890,7 @@
" )\n",
"\n",
" question = (\n",
" el[\"system\"] + \"\\n\\n\" + el[\"query\"]\n",
" if el[\"system\"] != \"\"\n",
" else el[\"query\"]\n",
" el[\"system\"] + \"\\n\\n\" + el[\"query\"] if el[\"system\"] != \"\" else el[\"query\"]\n",
" )\n",
"\n",
" llm_val_dataset.append(\n",
Expand Down Expand Up @@ -2026,7 +2024,7 @@
"source": [
"recipe_content = f\"\"\"\n",
"run:\n",
" name: nova-micro-llm-judge-eval-job\n",
" name: nova-lite-llm-judge-eval-job\n",
" model_type: amazon.nova-micro-v1:0:128k\n",
" model_name_or_path: \"nova-micro/prod\"\n",
" replicas: 1 # unmodifiable\n",
Expand Down Expand Up @@ -2168,6 +2166,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1144eb14",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "95d358b3",
Expand Down
17 changes: 15 additions & 2 deletions 18_sagemaker_training_recipes/nova/nova-lite-sft.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1866,7 +1866,7 @@
" if custom_model_arn is not None\n",
" else \"<CUSTOM_MODEL_DEPLOYMENT_ARN>\"\n",
" ),\n",
" \"us.amazon.nova-micro-v1:0\",\n",
" \"us.amazon.nova-lite-v1:0\",\n",
"]\n",
"\n",
"# Change model ID to run LLM as a judge evaluation on the fine-tuned model or base model\n",
Expand Down Expand Up @@ -2026,7 +2026,7 @@
"source": [
"recipe_content = f\"\"\"\n",
"run:\n",
" name: nova-micro-llm-judge-eval-job\n",
" name: nova-lite-llm-judge-eval-job\n",
" model_type: amazon.nova-micro-v1:0:128k\n",
" model_name_or_path: \"nova-micro/prod\"\n",
" replicas: 1 # unmodifiable\n",
Expand Down Expand Up @@ -2168,6 +2168,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1ac460dd",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "01c8e7ad",
Expand Down
13 changes: 13 additions & 0 deletions 18_sagemaker_training_recipes/nova/nova-micro-dpo.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2128,6 +2128,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e37c4a5d",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "c53f4555",
Expand Down
13 changes: 13 additions & 0 deletions 18_sagemaker_training_recipes/nova/nova-micro-sft-peft.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2173,6 +2173,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f5b7cc15",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "1951cdc2",
Expand Down
13 changes: 13 additions & 0 deletions 18_sagemaker_training_recipes/nova/nova-micro-sft.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2171,6 +2171,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e5b0e722",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "d7f6f0bb",
Expand Down
17 changes: 15 additions & 2 deletions 18_sagemaker_training_recipes/nova/nova-pro-dpo-peft.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1827,7 +1827,7 @@
" if custom_model_arn is not None\n",
" else \"<CUSTOM_MODEL_DEPLOYMENT_ARN>\"\n",
" ),\n",
" \"us.amazon.nova-micro-v1:0\",\n",
" \"us.amazon.nova-pro-v1:0\",\n",
"]\n",
"\n",
"# Change model ID to run LLM as a judge evaluation on the fine-tuned model or base model\n",
Expand Down Expand Up @@ -1987,7 +1987,7 @@
"source": [
"recipe_content = f\"\"\"\n",
"run:\n",
" name: nova-micro-llm-judge-eval-job\n",
" name: nova-pro-llm-judge-eval-job\n",
" model_type: amazon.nova-micro-v1:0:128k\n",
" model_name_or_path: \"nova-micro/prod\"\n",
" replicas: 1 # unmodifiable\n",
Expand Down Expand Up @@ -2129,6 +2129,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "836c0e19",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "2bb15296",
Expand Down
17 changes: 15 additions & 2 deletions 18_sagemaker_training_recipes/nova/nova-pro-sft-peft.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1847,7 +1847,7 @@
" if custom_model_arn is not None\n",
" else \"<CUSTOM_MODEL_DEPLOYMENT_ARN>\"\n",
" ),\n",
" \"us.amazon.nova-micro-v1:0\",\n",
" \"us.amazon.nova-pro-v1:0\",\n",
"]\n",
"\n",
"# Change model ID to run LLM as a judge evaluation on the fine-tuned model or base model\n",
Expand Down Expand Up @@ -2007,7 +2007,7 @@
"source": [
"recipe_content = f\"\"\"\n",
"run:\n",
" name: nova-micro-llm-judge-eval-job\n",
" name: nova-pro-llm-judge-eval-job\n",
" model_type: amazon.nova-micro-v1:0:128k\n",
" model_name_or_path: \"nova-micro/prod\"\n",
" replicas: 1 # unmodifiable\n",
Expand Down Expand Up @@ -2149,6 +2149,19 @@
"estimator.fit(inputs={\"train\": eval_input}, wait=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "833af432",
"metadata": {},
"outputs": [],
"source": [
"model_s3_uri = estimator.model_data\n",
"print(model_s3_uri)\n",
"\n",
"output_s3_uri = \"/\".join(model_s3_uri.split(\"/\")[:-1]) + \"/output.tar.gz\""
]
},
{
"cell_type": "markdown",
"id": "12501609",
Expand Down