Skip to content

Commit a815429

Browse files
BethanyJepBethanyJep
committed
updating consistency with training and validation datasets
1 parent a867262 commit a815429

File tree

6 files changed

+273
-55
lines changed

6 files changed

+273
-55
lines changed

‎.gitignore‎

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -418,4 +418,10 @@ FodyWeavers.xsd
418418
*.msp
419419

420420
#mkdocs static site
421-
site/*
421+
site/*
422+
423+
# .github
424+
/chatmodes
425+
chatmodes/*
426+
.github/chatmodes
427+
.github/chatmodes/*

‎lab/5-Distillation/adding-distillation.ipynb‎

Lines changed: 99 additions & 40 deletions
Original file line numberDiff line numberDiff line change
@@ -41,7 +41,7 @@
4141
},
4242
{
4343
"cell_type": "code",
44-
"execution_count": 1,
44+
"execution_count": 15,
4545
"id": "56955b7f",
4646
"metadata": {},
4747
"outputs": [
@@ -72,7 +72,7 @@
7272
},
7373
{
7474
"cell_type": "code",
75-
"execution_count": 2,
75+
"execution_count": 16,
7676
"id": "465864fc",
7777
"metadata": {},
7878
"outputs": [],
@@ -162,7 +162,7 @@
162162
},
163163
{
164164
"cell_type": "code",
165-
"execution_count": null,
165+
"execution_count": 5,
166166
"id": "da251df8",
167167
"metadata": {},
168168
"outputs": [
@@ -263,6 +263,26 @@
263263
" \"purpose\": \"fine-tune\",\n",
264264
" \"status\": \"processed\"\n",
265265
"}\n",
266+
"🏋️‍♂️ Created training file:\n",
267+
"{\n",
268+
" \"id\": \"file-cbe473f7b8dd4c4e9448eff623184bb6\",\n",
269+
" \"bytes\": 14064,\n",
270+
" \"created_at\": 1758529781,\n",
271+
" \"filename\": \"zava-tone-training-6b44a2f5.jsonl\",\n",
272+
" \"object\": \"file\",\n",
273+
" \"purpose\": \"fine-tune\",\n",
274+
" \"status\": \"processed\"\n",
275+
"}\n",
276+
"📋 Created validation file:\n",
277+
"{\n",
278+
" \"id\": \"file-08146e3604f041ac80fc5a1b6993a5cf\",\n",
279+
" \"bytes\": 4289,\n",
280+
" \"created_at\": 1758529788,\n",
281+
" \"filename\": \"zava-tone-validation-6b44a2f5.jsonl\",\n",
282+
" \"object\": \"file\",\n",
283+
" \"purpose\": \"fine-tune\",\n",
284+
" \"status\": \"processed\"\n",
285+
"}\n",
266286
"📋 Created validation file:\n",
267287
"{\n",
268288
" \"id\": \"file-08146e3604f041ac80fc5a1b6993a5cf\",\n",
@@ -320,7 +340,7 @@
320340
},
321341
{
322342
"cell_type": "code",
323-
"execution_count": null,
343+
"execution_count": 7,
324344
"id": "79c79880",
325345
"metadata": {},
326346
"outputs": [
@@ -462,23 +482,15 @@
462482
},
463483
{
464484
"cell_type": "code",
465-
"execution_count": 10,
485+
"execution_count": null,
466486
"id": "ca89054c",
467487
"metadata": {},
468488
"outputs": [
469489
{
470-
"ename": "ClientAuthenticationError",
471-
"evalue": "(InvalidAuthenticationTokenTenant) The 'EvolvedSecurityTokenService' access token is from the wrong issuer 'https://sts.windows.net/9beeb100-cd32-43ab-a787-c6e1219f6859/'. It must match the tenant 'https://sts.windows.net/3724f11b-e7b2-41d9-92a6-05ff649e1c18/' associated with this subscription. Please use the authority (URL) 'https://login.windows.net/3724f11b-e7b2-41d9-92a6-05ff649e1c18' to get the token. Note, if the subscription is transferred to another tenant there is no impact to the services, but information about new tenant could take time to propagate (up to an hour). If you just transferred your subscription and see this error message, please try back later.\nCode: InvalidAuthenticationTokenTenant\nMessage: The 'EvolvedSecurityTokenService' access token is from the wrong issuer 'https://sts.windows.net/9beeb100-cd32-43ab-a787-c6e1219f6859/'. It must match the tenant 'https://sts.windows.net/3724f11b-e7b2-41d9-92a6-05ff649e1c18/' associated with this subscription. Please use the authority (URL) 'https://login.windows.net/3724f11b-e7b2-41d9-92a6-05ff649e1c18' to get the token. Note, if the subscription is transferred to another tenant there is no impact to the services, but information about new tenant could take time to propagate (up to an hour). If you just transferred your subscription and see this error message, please try back later.",
472-
"output_type": "error",
473-
"traceback": [
474-
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
475-
"\u001b[31mClientAuthenticationError\u001b[39m Traceback (most recent call last)",
476-
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[10]\u001b[39m\u001b[32m, line 33\u001b[39m\n\u001b[32m 16\u001b[39m DEPLOYMENT = {\n\u001b[32m 17\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mproperties\u001b[39m\u001b[33m\"\u001b[39m: {\n\u001b[32m 18\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mmodel\u001b[39m\u001b[33m\"\u001b[39m: { \n\u001b[32m (...)\u001b[39m\u001b[32m 27\u001b[39m },\n\u001b[32m 28\u001b[39m }\n\u001b[32m 30\u001b[39m \u001b[38;5;66;03m# Submit the request for provisioning. This may take a few minutes, so we\u001b[39;00m\n\u001b[32m 31\u001b[39m \u001b[38;5;66;03m# poll for updates. If it already exists, this should return quickly. Since\u001b[39;00m\n\u001b[32m 32\u001b[39m \u001b[38;5;66;03m# we're deploying a 4.1-nano model, this should only take 3-5 minutes tops.\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m33\u001b[39m deployment = \u001b[43mcogsvc_client\u001b[49m\u001b[43m.\u001b[49m\u001b[43mdeployments\u001b[49m\u001b[43m.\u001b[49m\u001b[43mbegin_create_or_update\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 34\u001b[39m \u001b[43m \u001b[49m\u001b[43mresource_group_name\u001b[49m\u001b[43m=\u001b[49m\u001b[43mos\u001b[49m\u001b[43m.\u001b[49m\u001b[43menviron\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mAZURE_RESOURCE_GROUP\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 35\u001b[39m \u001b[43m \u001b[49m\u001b[43maccount_name\u001b[49m\u001b[43m=\u001b[49m\u001b[43mos\u001b[49m\u001b[43m.\u001b[49m\u001b[43menviron\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mAZURE_AI_FOUNDRY_NAME\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 36\u001b[39m \u001b[43m \u001b[49m\u001b[43mdeployment_name\u001b[49m\u001b[43m=\u001b[49m\u001b[43mDEPLOYMENT_NAME\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 37\u001b[39m \u001b[43m \u001b[49m\u001b[43mdeployment\u001b[49m\u001b[43m=\u001b[49m\u001b[43mDEPLOYMENT\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 38\u001b[39m \u001b[43m)\u001b[49m\n\u001b[32m 39\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33m🛳️ Submitted deployment \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdeployment\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m)\n",
477-
"\u001b[36mFile \u001b[39m\u001b[32m~/Downloads/ignite25-PDY123-learn-how-to-observe-manage-and-scale-agentic-ai-apps-using-azure/.venv/lib/python3.13/site-packages/azure/core/tracing/decorator.py:119\u001b[39m, in \u001b[36mdistributed_trace.<locals>.decorator.<locals>.wrapper_use_tracer\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m 117\u001b[39m \u001b[38;5;66;03m# If tracing is disabled globally and user didn't explicitly enable it, don't trace.\u001b[39;00m\n\u001b[32m 118\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m user_enabled \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mFalse\u001b[39;00m \u001b[38;5;129;01mor\u001b[39;00m (\u001b[38;5;129;01mnot\u001b[39;00m tracing_enabled \u001b[38;5;129;01mand\u001b[39;00m user_enabled \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[32m--> \u001b[39m\u001b[32m119\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 121\u001b[39m \u001b[38;5;66;03m# Merge span is parameter is set, but only if no explicit parent are passed\u001b[39;00m\n\u001b[32m 122\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m merge_span \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m passed_in_parent:\n",
478-
"\u001b[36mFile \u001b[39m\u001b[32m~/Downloads/ignite25-PDY123-learn-how-to-observe-manage-and-scale-agentic-ai-apps-using-azure/.venv/lib/python3.13/site-packages/azure/mgmt/cognitiveservices/operations/_deployments_operations.py:596\u001b[39m, in \u001b[36mDeploymentsOperations.begin_create_or_update\u001b[39m\u001b[34m(self, resource_group_name, account_name, deployment_name, deployment, **kwargs)\u001b[39m\n\u001b[32m 594\u001b[39m cont_token: Optional[\u001b[38;5;28mstr\u001b[39m] = kwargs.pop(\u001b[33m\"\u001b[39m\u001b[33mcontinuation_token\u001b[39m\u001b[33m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[32m 595\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m cont_token \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m596\u001b[39m raw_result = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_create_or_update_initial\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 597\u001b[39m \u001b[43m \u001b[49m\u001b[43mresource_group_name\u001b[49m\u001b[43m=\u001b[49m\u001b[43mresource_group_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 598\u001b[39m \u001b[43m \u001b[49m\u001b[43maccount_name\u001b[49m\u001b[43m=\u001b[49m\u001b[43maccount_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 599\u001b[39m \u001b[43m \u001b[49m\u001b[43mdeployment_name\u001b[49m\u001b[43m=\u001b[49m\u001b[43mdeployment_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 600\u001b[39m \u001b[43m \u001b[49m\u001b[43mdeployment\u001b[49m\u001b[43m=\u001b[49m\u001b[43mdeployment\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 601\u001b[39m \u001b[43m \u001b[49m\u001b[43mapi_version\u001b[49m\u001b[43m=\u001b[49m\u001b[43mapi_version\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 602\u001b[39m \u001b[43m \u001b[49m\u001b[43mcontent_type\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcontent_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 603\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mz\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 604\u001b[39m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[43m=\u001b[49m\u001b[43m_headers\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 605\u001b[39m \u001b[43m \u001b[49m\u001b[43mparams\u001b[49m\u001b[43m=\u001b[49m\u001b[43m_params\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 606\u001b[39m \u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\n\u001b[32m 607\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 608\u001b[39m raw_result.http_response.read() \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[32m 609\u001b[39m kwargs.pop(\u001b[33m\"\u001b[39m\u001b[33merror_map\u001b[39m\u001b[33m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n",
479-
"\u001b[36mFile \u001b[39m\u001b[32m~/Downloads/ignite25-PDY123-learn-how-to-observe-manage-and-scale-agentic-ai-apps-using-azure/.venv/lib/python3.13/site-packages/azure/mgmt/cognitiveservices/operations/_deployments_operations.py:487\u001b[39m, in \u001b[36mDeploymentsOperations._create_or_update_initial\u001b[39m\u001b[34m(self, resource_group_name, account_name, deployment_name, deployment, **kwargs)\u001b[39m\n\u001b[32m 485\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m (StreamConsumedError, StreamClosedError):\n\u001b[32m 486\u001b[39m \u001b[38;5;28;01mpass\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m487\u001b[39m \u001b[43mmap_error\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstatus_code\u001b[49m\u001b[43m=\u001b[49m\u001b[43mresponse\u001b[49m\u001b[43m.\u001b[49m\u001b[43mstatus_code\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse\u001b[49m\u001b[43m=\u001b[49m\u001b[43mresponse\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merror_map\u001b[49m\u001b[43m=\u001b[49m\u001b[43merror_map\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 488\u001b[39m error = \u001b[38;5;28mself\u001b[39m._deserialize.failsafe_deserialize(_models.ErrorResponse, pipeline_response)\n\u001b[32m 489\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m HttpResponseError(response=response, model=error, error_format=ARMErrorFormat)\n",
480-
"\u001b[36mFile \u001b[39m\u001b[32m~/Downloads/ignite25-PDY123-learn-how-to-observe-manage-and-scale-agentic-ai-apps-using-azure/.venv/lib/python3.13/site-packages/azure/core/exceptions.py:163\u001b[39m, in \u001b[36mmap_error\u001b[39m\u001b[34m(status_code, response, error_map)\u001b[39m\n\u001b[32m 161\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[32m 162\u001b[39m error = error_type(response=response)\n\u001b[32m--> \u001b[39m\u001b[32m163\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m error\n",
481-
"\u001b[31mClientAuthenticationError\u001b[39m: (InvalidAuthenticationTokenTenant) The 'EvolvedSecurityTokenService' access token is from the wrong issuer 'https://sts.windows.net/9beeb100-cd32-43ab-a787-c6e1219f6859/'. It must match the tenant 'https://sts.windows.net/3724f11b-e7b2-41d9-92a6-05ff649e1c18/' associated with this subscription. Please use the authority (URL) 'https://login.windows.net/3724f11b-e7b2-41d9-92a6-05ff649e1c18' to get the token. Note, if the subscription is transferred to another tenant there is no impact to the services, but information about new tenant could take time to propagate (up to an hour). If you just transferred your subscription and see this error message, please try back later.\nCode: InvalidAuthenticationTokenTenant\nMessage: The 'EvolvedSecurityTokenService' access token is from the wrong issuer 'https://sts.windows.net/9beeb100-cd32-43ab-a787-c6e1219f6859/'. It must match the tenant 'https://sts.windows.net/3724f11b-e7b2-41d9-92a6-05ff649e1c18/' associated with this subscription. Please use the authority (URL) 'https://login.windows.net/3724f11b-e7b2-41d9-92a6-05ff649e1c18' to get the token. Note, if the subscription is transferred to another tenant there is no impact to the services, but information about new tenant could take time to propagate (up to an hour). If you just transferred your subscription and see this error message, please try back later."
490+
"name": "stdout",
491+
"output_type": "stream",
492+
"text": [
493+
"🛳️ Submitted deployment <azure.core.polling._poller.LROPoller object at 0x12604d7f0>\n"
482494
]
483495
}
484496
],
@@ -534,16 +546,16 @@
534546
},
535547
{
536548
"cell_type": "code",
537-
"execution_count": null,
549+
"execution_count": 19,
538550
"id": "88230a2e",
539551
"metadata": {},
540552
"outputs": [
541553
{
542554
"name": "stdout",
543555
"output_type": "stream",
544556
"text": [
545-
"🛳️ Provisioning zava-tone-distilled-b836c26f: Succeeded\n",
546-
"⏱️Elapsed time: 5 minutes 11 seconds\n",
557+
"🛳️ Provisioning zava-tone-distilled-gpt-4o-zava-tone-6b44a2f5: Succeeded\n",
558+
"⏱️Elapsed time: 4 minutes 8 seconds\n",
547559
"🏁 Provisioning finished!\n"
548560
]
549561
}
@@ -576,7 +588,7 @@
576588
},
577589
{
578590
"cell_type": "code",
579-
"execution_count": null,
591+
"execution_count": 22,
580592
"id": "b687d4c6",
581593
"metadata": {},
582594
"outputs": [],
@@ -606,18 +618,74 @@
606618
},
607619
{
608620
"cell_type": "code",
609-
"execution_count": null,
621+
"execution_count": 23,
622+
"id": "752cad64",
623+
"metadata": {},
624+
"outputs": [],
625+
"source": [
626+
"# Now we define our Evaluation for validating our choice in grader prompt and model.\n",
627+
"\n",
628+
"# The entire user prompt is data driven from the file. No generation is done using\n",
629+
"# a model in this case, just simple string substitution using this pattern. This\n",
630+
"# means we directly reference the two fields in our baseline.jsonl file.\n",
631+
"\n",
632+
"USER_PROMPT = \"\"\"\n",
633+
"Q: {{item.question}}\n",
634+
"A: {{item.answer}}\n",
635+
"\"\"\"\n",
636+
"\n",
637+
"INPUT = [\n",
638+
" {\n",
639+
" \"type\": \"message\",\n",
640+
" \"role\": \"system\",\n",
641+
" \"content\": { \"type\": \"input_text\", \"text\": GRADER_PROMPT }\n",
642+
" },\n",
643+
" {\n",
644+
" \"type\": \"message\",\n",
645+
" \"role\": \"user\",\n",
646+
" \"content\": { \"type\": \"input_text\", \"text\": USER_PROMPT }\n",
647+
" }\n",
648+
"]\n",
649+
"\n",
650+
"# We need to describe what our evaluation dataset looks like.\n",
651+
"SCHEMA = {\n",
652+
" \"type\": \"object\",\n",
653+
" \"properties\": {\n",
654+
" \"question\": { \"type\": \"string\" },\n",
655+
" \"answer\": { \"type\": \"string\" },\n",
656+
" }\n",
657+
"}\n",
658+
"DATA_SOURCE = {\n",
659+
" \"item_schema\": SCHEMA,\n",
660+
" \"include_sample_schema\": False,\n",
661+
" \"type\": \"custom\",\n",
662+
"}\n",
663+
"\n",
664+
"# Lastly, we define test criteria that combines all the above.\n",
665+
"TESTING_CRITERIA = {\n",
666+
" \"name\": \"Zava Tone Grader\",\n",
667+
" \"type\": \"score_model\",\n",
668+
" \"model\": GRADER_MODEL,\n",
669+
" \"input\": INPUT,\n",
670+
" \"range\": [1.0, 10.0], # Our grader scores in a range from 1 to 10\n",
671+
" \"pass_threshold\": 4.0, # Let's say a 4 is \"passing\" for now.\n",
672+
"}"
673+
]
674+
},
675+
{
676+
"cell_type": "code",
677+
"execution_count": 24,
610678
"id": "7c4ac102",
611679
"metadata": {},
612680
"outputs": [
613681
{
614682
"name": "stdout",
615683
"output_type": "stream",
616684
"text": [
617-
"Created eval eval_68b6d9c91a4881918384d517abb81f0e\n",
618-
"🏃‍➡️ Created run evalrun_68b6d9c9c9548191aa7972b9b40cb29c for eval_68b6d9c91a4881918384d517abb81f0e\n",
619-
"🏃‍➡️ Created run evalrun_68b6d9cad2a88191b37225350496cfc3 for eval_68b6d9c91a4881918384d517abb81f0e\n",
620-
"🏃‍➡️ Created run evalrun_68b6d9cb6f948191a557c5cc60d18bfc for eval_68b6d9c91a4881918384d517abb81f0e\n"
685+
"Created eval eval_68d1191f6e1c81919d212598b5fdec4a\n",
686+
"🏃‍➡️ Created run evalrun_68d11920eaf88191ad58e883892ac386 for eval_68d1191f6e1c81919d212598b5fdec4a\n",
687+
"🏃‍➡️ Created run evalrun_68d11922214c8191b1fe3ade32579626 for eval_68d1191f6e1c81919d212598b5fdec4a\n",
688+
"🏃‍➡️ Created run evalrun_68d1192376b08191b221ecaececf061f for eval_68d1191f6e1c81919d212598b5fdec4a\n"
621689
]
622690
}
623691
],
@@ -628,7 +696,7 @@
628696
"# models as a control.\n",
629697
"POST_EVAL_MODELS = [\n",
630698
" DEPLOYMENT_NAME,# distilled\n",
631-
" \"gpt-4o-mini\", # student\n",
699+
" \"gpt-4.1-nano\", # student\n",
632700
" \"gpt-4.1\", # control\n",
633701
"]\n",
634702
"\n",
@@ -716,11 +784,10 @@
716784
"name": "stdout",
717785
"output_type": "stream",
718786
"text": [
719-
"🏃‍➡️ Run zava-tone-distilled-b836c26f-b836c26f: completed\n",
720-
"🏃‍➡️ Run gpt-4.1-mini-b836c26f: completed\n",
721-
"🏃‍➡️ Run gpt-4.1-b836c26f: completed\n",
722-
"⏱️ Elapsed time: 5 minutes 5 seconds\n",
723-
"🏁 All 3 runs completed!\n"
787+
"🏃‍➡️ Run zava-tone-distilled-gpt-4o-zava-tone-6b44a2f5-6b44a2f5: in_progress\n",
788+
"🏃‍➡️ Run gpt-4.1-nano-6b44a2f5: in_progress\n",
789+
"🏃‍➡️ Run gpt-4.1-6b44a2f5: in_progress\n",
790+
"⏱️ Elapsed time: 1 minutes 20 seconds\n"
724791
]
725792
}
726793
],
@@ -818,14 +885,6 @@
818885
"display_evaluation_summary(client, [posttraining_eval.id], x_range=(1, 10))"
819886
]
820887
},
821-
{
822-
"cell_type": "code",
823-
"execution_count": null,
824-
"id": "fa190861",
825-
"metadata": {},
826-
"outputs": [],
827-
"source": []
828-
},
829888
{
830889
"cell_type": "code",
831890
"execution_count": null,

0 commit comments

Comments
 (0)