chaiml-kimid-v3a-lr5e6g32

developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v3a-lr5e6g32_v1
model_name: training123
model_group: ChaiML/kimid-v3a_lr5e6g3
status: inactive
timestamp: 2025-12-06T00:11:59+00:00
num_battles: 8614
num_wins: 4585
celo_rating: 1315.47
family_friendly_score: 0.501
family_friendly_standard_error: 0.00707105366971571
submission_type: basic
model_repo: ChaiML/kimid-v3a_lr5e6g32
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 72
reward_model: default
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v3a_lr5e6g32
model_size: 24B
ranking_group: single
us_pacific_date: 2025-12-05
win_ratio: 0.5322730438820524
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', 'You:', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 72}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer to finish
Stopping job with name chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer to finish
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: Downloaded to shared memory in 107.075s
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: Checking if ChaiML/kimid-v3a_lr5e6g32 already exists in ChaiML
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsr46b9l7, device:0
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.9it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.9it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:02<00:11, 27.6it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:02<00:11, 27.6it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:03<00:13, 21.2it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:03<00:13, 21.2it/s]
Loading 0:  25%|██▌       | 92.0/363 [00:04<00:13, 20.5it/s]
Loading 0:  25%|██▌       | 92.0/363 [00:04<00:13, 20.5it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.9it/s] 
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.9it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 25.1it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 25.1it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 25.9it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 25.9it/s]
Loading 0:  50%|████▉     | 181/363 [00:21<00:07, 25.9it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:33, 4.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:33, 4.88it/s]
Loading 0:  61%|██████▏   | 223/363 [00:22<00:22, 6.27it/s]
Loading 0:  61%|██████▏   | 223/363 [00:22<00:22, 6.27it/s]
Loading 0:  68%|██████▊   | 248/363 [00:23<00:13, 8.22it/s]
Loading 0:  68%|██████▊   | 248/363 [00:23<00:13, 8.22it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:08, 10.5it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:08, 10.5it/s]
Loading 0:  84%|████████▍ | 305/363 [00:25<00:04, 13.5it/s]
Loading 0:  84%|████████▍ | 305/363 [00:25<00:04, 13.5it/s]
Loading 0:  92%|█████████▏| 334/363 [00:26<00:01, 16.2it/s]
Loading 0:  92%|█████████▏| 334/363 [00:26<00:01, 16.2it/s]
Loading 0:  98%|█████████▊| 357/363 [00:27<00:00, 17.2it/s]
Loading 0:  98%|█████████▊| 357/363 [00:27<00:00, 17.2it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 18.0it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 18.0it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.2it/s]
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpsr46b9l7' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: quantized model in 44.506s
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: Processed model ChaiML/kimid-v3a_lr5e6g32 in 151.582s
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3a-lr5e6g32-v1/nvidia
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3a-lr5e6g32-v1/nvidia/config.json
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3a-lr5e6g32-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3a-lr5e6g32-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3a-lr5e6g32-v1/nvidia/tokenizer.json
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3a-lr5e6g32-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3a-lr5e6g32-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer completed after 207.31s with status: succeeded
Stopping job with name chaiml-kimid-v3a-lr5e6g32-v1-mkmlizer
Pipeline stage MKMLizer completed in 229.95s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.53s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v3a-lr5e6g32-v1
Waiting for inference service chaiml-kimid-v3a-lr5e6g32-v1 to be ready
Inference service chaiml-kimid-v3a-lr5e6g32-v1 ready after 191.54960441589355s
Pipeline stage MKMLDeployer completed in 192.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.604696750640869s
Received healthy response to inference request in 2.578354835510254s
Received healthy response to inference request in 3.2885191440582275s
Received healthy response to inference request in 2.686762809753418s
Received healthy response to inference request in 2.4065332412719727s
5 requests
0 failed requests
5th percentile: 2.440897560119629
10th percentile: 2.4752618789672853
20th percentile: 2.5439905166625976
30th percentile: 2.5836232185363768
40th percentile: 2.594159984588623
50th percentile: 2.604696750640869
60th percentile: 2.6375231742858887
70th percentile: 2.670349597930908
80th percentile: 2.80711407661438
90th percentile: 3.047816610336304
95th percentile: 3.1681678771972654
99th percentile: 3.264448890686035
mean time: 2.7129733562469482
Pipeline stage StressChecker completed in 15.23s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.94s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 3.08s
Shutdown handler de-registered
chaiml-kimid-v3a-lr5e6g32_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-kimid-v3a-lr5e6g32-v1-profiler
Waiting for inference service chaiml-kimid-v3a-lr5e6g32-v1-profiler to be ready
Inference service chaiml-kimid-v3a-lr5e6g32-v1-profiler ready after 191.92509818077087s
Pipeline stage MKMLProfilerDeployer completed in 192.58s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts creator-studio/chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplobj22l:/code/chaiverse_profiler_1764976439 --namespace creator-studio
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplobj22l --namespace creator-studio -- sh -c 'cd /code/chaiverse_profiler_1764976439 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 72 --summary /code/chaiverse_profiler_1764976439/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts creator-studio/chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplobj22l:/code/chaiverse_profiler_1764977319 --namespace creator-studio
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplobj22l --namespace creator-studio -- sh -c 'cd /code/chaiverse_profiler_1764977319 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 72 --summary /code/chaiverse_profiler_1764977319/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts creator-studio/chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplobj22l:/code/chaiverse_profiler_1764978576 --namespace creator-studio
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplobj22l --namespace creator-studio -- sh -c 'cd /code/chaiverse_profiler_1764978576 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 72 --summary /code/chaiverse_profiler_1764978576/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-kimid-v3a-lr5e6g32-v1-profiler is running
Tearing down inference service chaiml-kimid-v3a-lr5e6g32-v1-profiler
Service chaiml-kimid-v3a-lr5e6g32-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.89s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-kimid-v3a-lr5e6g32-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 0.95s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-kimid-v3a-lr5e6g32-v1-profiler
Waiting for inference service chaiml-kimid-v3a-lr5e6g32-v1-profiler to be ready
Inference service chaiml-kimid-v3a-lr5e6g32-v1-profiler ready after 191.78347969055176s
Pipeline stage MKMLProfilerDeployer completed in 192.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts creator-studio/chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplo492wk:/code/chaiverse_profiler_1764980114 --namespace creator-studio
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplo492wk --namespace creator-studio -- sh -c 'cd /code/chaiverse_profiler_1764980114 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 72 --summary /code/chaiverse_profiler_1764980114/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-kimid-v3a-lr56bc6f911cd4adcdbe3ea0df7f580343f-deplo492wk --namespace creator-studio -- bash -c 'cat /code/chaiverse_profiler_1764980114/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1763.38s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-kimid-v3a-lr5e6g32-v1-profiler is running
Tearing down inference service chaiml-kimid-v3a-lr5e6g32-v1-profiler
Service chaiml-kimid-v3a-lr5e6g32-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.93s
Shutdown handler de-registered