mirror of
https://github.com/james-m-jordan/openai-cookbook.git
synced 2025-05-09 19:32:38 +00:00
small improvements to the fine-tuning cookbook (#651)
This commit is contained in:
Simón Fishman
GitHub
parent
64e9471909
commit
8ed84645e8
1
.gitignore
vendored
1
.gitignore
vendored
@ -132,3 +132,4 @@ dmypy.json
|
||||
*transactions*.jsonl
|
||||
/examples/data/transactions*
|
||||
*.DS_Store
|
||||
tmp_*
|
||||
@ -44,7 +44,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 76,
|
||||
"execution_count": 1,
|
||||
"id": "6e1f4403-37e1-4115-a215-12fd7daa1eb6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -53,7 +53,6 @@
|
||||
"import openai\n",
|
||||
"import os\n",
|
||||
"import pandas as pd\n",
|
||||
"import requests\n",
|
||||
"from pprint import pprint\n",
|
||||
"\n",
|
||||
"OPENAI_API_KEY = os.getenv(\"OPENAI_API_KEY\", \"\")"
|
||||
@ -216,7 +215,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": 3,
|
||||
"id": "9a8216b0-d1dc-472d-b07d-1be03acd70a5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -245,7 +244,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 4,
|
||||
"id": "5b853efa-dfea-4770-ab88-9b7e17794421",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -277,7 +276,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"execution_count": 5,
|
||||
"id": "8d2eb207-2c2b-43f6-a613-64a7e92d494d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -304,7 +303,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"execution_count": 6,
|
||||
"id": "8b53e7a2-1cac-4c5f-8ba4-3292ba2a0770",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -330,7 +329,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"execution_count": 7,
|
||||
"id": "69462d9e-e6bd-49b9-a064-9eae4ea5b7a8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -338,8 +337,8 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Training file id: file-XMhftmLXyyTvvmiLpMRMIAcL\n",
|
||||
"Validation file id: file-kZz433aerpPIMADZF7xC5NKd\n"
|
||||
"Training file ID: file-XEpJAyCL2qMbMEgXwYfS9ypT\n",
|
||||
"Validation file ID: file-MAGY5QyvCMdOWUDuXJB79uw9\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -354,8 +353,8 @@
|
||||
")\n",
|
||||
"validation_file_id = validation_response[\"id\"]\n",
|
||||
"\n",
|
||||
"print(\"Training file id:\", training_file_id)\n",
|
||||
"print(\"Validation file id:\", validation_file_id)"
|
||||
"print(\"Training file ID:\", training_file_id)\n",
|
||||
"print(\"Validation file ID:\", validation_file_id)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -367,12 +366,12 @@
|
||||
"\n",
|
||||
"Now we can create our fine-tuning job with the generated files and an optional suffix to identify the model. The response will contain an `id` which you can use to retrieve updates on the job.\n",
|
||||
"\n",
|
||||
"Note: The files have to first be processed by our system, so you might get a `File is not ready` error. In that case, simply retry a few minutes later.\n"
|
||||
"Note: The files have to first be processed by our system, so you might get a `File not ready` error. In that case, simply retry a few minutes later.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"execution_count": 10,
|
||||
"id": "05541ceb-5628-447e-962d-7e57c112439c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -380,40 +379,23 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{\n",
|
||||
" \"object\": \"fine_tuning.job\",\n",
|
||||
" \"id\": \"ftjob-ksOzx7zjpsrADZfhB5eyfB0Z\",\n",
|
||||
" \"model\": \"gpt-3.5-turbo-0613\",\n",
|
||||
" \"created_at\": 1692734343,\n",
|
||||
" \"finished_at\": null,\n",
|
||||
" \"fine_tuned_model\": null,\n",
|
||||
" \"organization_id\": \"org-l89177bnhkme4a44292n5r3j\",\n",
|
||||
" \"result_files\": [],\n",
|
||||
" \"status\": \"created\",\n",
|
||||
" \"validation_file\": \"file-kZz433aerpPIMADZF7xC5NKd\",\n",
|
||||
" \"training_file\": \"file-XMhftmLXyyTvvmiLpMRMIAcL\",\n",
|
||||
" \"hyperparameters\": {\n",
|
||||
" \"n_epochs\": 3\n",
|
||||
" },\n",
|
||||
" \"trained_tokens\": null\n",
|
||||
"}\n"
|
||||
"Job ID: ftjob-9xVzrp0Oem9rWj2UFWDcFLqT\n",
|
||||
"Status: created\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"suffix_name = \"recipe-ner\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"response = openai.FineTuningJob.create(\n",
|
||||
" training_file=training_file_id,\n",
|
||||
" validation_file=validation_file_id,\n",
|
||||
" model=\"gpt-3.5-turbo\",\n",
|
||||
" suffix=suffix_name,\n",
|
||||
" suffix=\"recipe-ner\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"job_id = response[\"id\"]\n",
|
||||
"\n",
|
||||
"print(response)"
|
||||
"print(\"Job ID:\", response[\"id\"])\n",
|
||||
"print(\"Status:\", response[\"status\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -430,7 +412,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 59,
|
||||
"execution_count": 11,
|
||||
"id": "d7392f48",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -438,31 +420,18 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{\n",
|
||||
" \"object\": \"fine_tuning.job\",\n",
|
||||
" \"id\": \"ftjob-ksOzx7zjpsrADZfhB5eyfB0Z\",\n",
|
||||
" \"model\": \"gpt-3.5-turbo-0613\",\n",
|
||||
" \"created_at\": 1692734343,\n",
|
||||
" \"finished_at\": 1692735182,\n",
|
||||
" \"fine_tuned_model\": \"ft:gpt-3.5-turbo-0613:openai:recipe-ner:7qS2GFaX\",\n",
|
||||
" \"organization_id\": \"org-l89177bnhkme4a44292n5r3j\",\n",
|
||||
" \"result_files\": [\n",
|
||||
" \"file-Tjt0E6BvQ846m75gYxtWiRzb\"\n",
|
||||
" ],\n",
|
||||
" \"status\": \"succeeded\",\n",
|
||||
" \"validation_file\": \"file-kZz433aerpPIMADZF7xC5NKd\",\n",
|
||||
" \"training_file\": \"file-XMhftmLXyyTvvmiLpMRMIAcL\",\n",
|
||||
" \"hyperparameters\": {\n",
|
||||
" \"n_epochs\": 3\n",
|
||||
" },\n",
|
||||
" \"trained_tokens\": 39687\n",
|
||||
"}\n"
|
||||
"Job ID: ftjob-9xVzrp0Oem9rWj2UFWDcFLqT\n",
|
||||
"Status: running\n",
|
||||
"Trained Tokens: None\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"response = openai.FineTuningJob.retrieve(job_id)\n",
|
||||
"print(response)"
|
||||
"\n",
|
||||
"print(\"Job ID:\", response[\"id\"])\n",
|
||||
"print(\"Status:\", response[\"status\"])\n",
|
||||
"print(\"Trained Tokens:\", response[\"trained_tokens\"])\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -470,12 +439,12 @@
|
||||
"id": "30a57fbb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can track the progress of the fine-tune with the events endpoint. You can rerun the cell below a few times until the fine-tune is ready. \n"
|
||||
"We can track the progress of the fine-tune with the events endpoint. You can rerun the cell below a few times until the fine-tune is ready.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 69,
|
||||
"execution_count": 12,
|
||||
"id": "08cace28",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -483,39 +452,39 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Created fine-tune: ftjob-ksOzx7zjpsrADZfhB5eyfB0Z\n",
|
||||
"Created fine-tune: ftjob-9xVzrp0Oem9rWj2UFWDcFLqT\n",
|
||||
"Fine tuning job started\n",
|
||||
"Step 10: training loss=0.16\n",
|
||||
"Step 20: training loss=0.14\n",
|
||||
"Step 30: training loss=0.30\n",
|
||||
"Step 40: training loss=0.17\n",
|
||||
"Step 50: training loss=0.03\n",
|
||||
"Step 60: training loss=0.55\n",
|
||||
"Step 70: training loss=0.09\n",
|
||||
"Step 80: training loss=0.00\n",
|
||||
"Step 90: training loss=0.15\n",
|
||||
"Step 100: training loss=0.06\n",
|
||||
"Step 110: training loss=0.03\n",
|
||||
"Step 120: training loss=0.04\n",
|
||||
"Step 130: training loss=0.21\n",
|
||||
"Step 10: training loss=2.41\n",
|
||||
"Step 20: training loss=0.06\n",
|
||||
"Step 30: training loss=0.38\n",
|
||||
"Step 40: training loss=0.09\n",
|
||||
"Step 50: training loss=0.19\n",
|
||||
"Step 60: training loss=0.10\n",
|
||||
"Step 70: training loss=0.00\n",
|
||||
"Step 80: training loss=0.01\n",
|
||||
"Step 90: training loss=0.72\n",
|
||||
"Step 100: training loss=0.13\n",
|
||||
"Step 110: training loss=0.15\n",
|
||||
"Step 120: training loss=0.00\n",
|
||||
"Step 130: training loss=0.47\n",
|
||||
"Step 140: training loss=0.00\n",
|
||||
"Step 150: training loss=0.02\n",
|
||||
"Step 160: training loss=0.00\n",
|
||||
"Step 170: training loss=0.00\n",
|
||||
"Step 180: training loss=0.19\n",
|
||||
"Step 190: training loss=0.55\n",
|
||||
"Step 150: training loss=0.10\n",
|
||||
"Step 160: training loss=0.06\n",
|
||||
"Step 170: training loss=0.03\n",
|
||||
"Step 180: training loss=0.08\n",
|
||||
"Step 190: training loss=0.04\n",
|
||||
"Step 200: training loss=0.01\n",
|
||||
"Step 210: training loss=0.00\n",
|
||||
"Step 210: training loss=0.03\n",
|
||||
"Step 220: training loss=0.00\n",
|
||||
"Step 230: training loss=0.00\n",
|
||||
"Step 230: training loss=0.08\n",
|
||||
"Step 240: training loss=0.00\n",
|
||||
"Step 250: training loss=0.00\n",
|
||||
"Step 260: training loss=0.36\n",
|
||||
"Step 270: training loss=0.16\n",
|
||||
"Step 280: training loss=0.01\n",
|
||||
"Step 290: training loss=0.04\n",
|
||||
"Step 300: training loss=0.53\n",
|
||||
"New fine-tuned model created: ft:gpt-3.5-turbo-0613:openai:recipe-ner:7qS2GFaX\n",
|
||||
"Step 260: training loss=0.00\n",
|
||||
"Step 270: training loss=0.00\n",
|
||||
"Step 280: training loss=0.00\n",
|
||||
"Step 290: training loss=0.00\n",
|
||||
"Step 300: training loss=0.60\n",
|
||||
"New fine-tuned model created: ft:gpt-3.5-turbo-0613:openai:recipe-ner:7qTvyJ81\n",
|
||||
"Fine-tuning job successfully completed\n"
|
||||
]
|
||||
}
|
||||
@ -535,12 +504,12 @@
|
||||
"id": "d0da4e32",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now that it's done, we can get a fine-tuned model ID from the job\n"
|
||||
"Now that it's done, we can get a fine-tuned model ID from the job:\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 81,
|
||||
"execution_count": 14,
|
||||
"id": "40b28c26",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -548,27 +517,7 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{\n",
|
||||
" \"object\": \"fine_tuning.job\",\n",
|
||||
" \"id\": \"ftjob-ksOzx7zjpsrADZfhB5eyfB0Z\",\n",
|
||||
" \"model\": \"gpt-3.5-turbo-0613\",\n",
|
||||
" \"created_at\": 1692734343,\n",
|
||||
" \"finished_at\": 1692735182,\n",
|
||||
" \"fine_tuned_model\": \"ft:gpt-3.5-turbo-0613:openai:recipe-ner:7qS2GFaX\",\n",
|
||||
" \"organization_id\": \"org-l89177bnhkme4a44292n5r3j\",\n",
|
||||
" \"result_files\": [\n",
|
||||
" \"file-Tjt0E6BvQ846m75gYxtWiRzb\"\n",
|
||||
" ],\n",
|
||||
" \"status\": \"succeeded\",\n",
|
||||
" \"validation_file\": \"file-kZz433aerpPIMADZF7xC5NKd\",\n",
|
||||
" \"training_file\": \"file-XMhftmLXyyTvvmiLpMRMIAcL\",\n",
|
||||
" \"hyperparameters\": {\n",
|
||||
" \"n_epochs\": 3\n",
|
||||
" },\n",
|
||||
" \"trained_tokens\": 39687\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"Fine-tuned model id: ft:gpt-3.5-turbo-0613:openai:recipe-ner:7qS2GFaX\n"
|
||||
"Fine-tuned model ID: ft:gpt-3.5-turbo-0613:openai:recipe-ner:7qTvyJ81\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -576,8 +525,7 @@
|
||||
"response = openai.FineTuningJob.retrieve(job_id)\n",
|
||||
"fine_tuned_model_id = response[\"fine_tuned_model\"]\n",
|
||||
"\n",
|
||||
"print(response)\n",
|
||||
"print(\"\\nFine-tuned model id:\", fine_tuned_model_id)"
|
||||
"print(\"Fine-tuned model ID:\", fine_tuned_model_id)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -593,12 +541,12 @@
|
||||
"id": "0ab9ac11",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The last step is to use your fine-tuned model for inference. Similar to the classic `FineTuning`, you simply call `ChatCompletions` with your new fine-tuned model name filling the `model` parameter."
|
||||
"The last step is to use your fine-tuned model for inference. Similar to the classic `FineTuning`, you simply call `ChatCompletions` with your new fine-tuned model name filling the `model` parameter.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 87,
|
||||
"execution_count": 15,
|
||||
"id": "1c7de631-b68f-4eff-9ae7-051641579c2b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -632,7 +580,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 88,
|
||||
"execution_count": 16,
|
||||
"id": "1a1d2589",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user