chaiml-kimid-v3a

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v3a_v1

model_name: training123

model_group: ChaiML/kimid-v3a

status: inactive

timestamp: 2025-12-05T18:36:33+00:00

num_battles: 17934

num_wins: 9233

celo_rating: 1303.52

family_friendly_score: 0.5032

family_friendly_standard_error: 0.007070922994913747

submission_type: basic

model_repo: ChaiML/kimid-v3a

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 72

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.34277679814722745, 'latency_mean': 2.9172826302051544, 'latency_p50': 2.9185463190078735, 'latency_p90': 3.1800944089889525}, {'batch_size': 2, 'throughput': 0.520546393533315, 'latency_mean': 3.838164196014404, 'latency_p50': 3.8512946367263794, 'latency_p90': 4.121680903434753}, {'batch_size': 3, 'throughput': 0.6504034818726309, 'latency_mean': 4.583281623125076, 'latency_p50': 4.594195246696472, 'latency_p90': 5.020257043838501}, {'batch_size': 4, 'throughput': 0.7451012395950762, 'latency_mean': 5.3441020154953005, 'latency_p50': 5.334784030914307, 'latency_p90': 6.06193745136261}, {'batch_size': 5, 'throughput': 0.8004213582862885, 'latency_mean': 6.221247475147248, 'latency_p50': 6.19932234287262, 'latency_p90': 7.038251280784607}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v3a

model_size: 24B

ranking_group: single

throughput_3p7s: 0.5

us_pacific_date: 2025-12-05

win_ratio: 0.514832162373146

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': ['You:', 'User:', '</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-v1-mkmlizer
Waiting for job on chaiml-kimid-v3a-v1-mkmlizer to finish
chaiml-kimid-v3a-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3a-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3a-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-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3a-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3a-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3a-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3a-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3a-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3a-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3a-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3a-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3a-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3a-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3a-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3a-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3a-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3a-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3a-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3a-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3a-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3a-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3a-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3a-v1-mkmlizer: Downloaded to shared memory in 46.242s
chaiml-kimid-v3a-v1-mkmlizer: Checking if ChaiML/kimid-v3a already exists in ChaiML
chaiml-kimid-v3a-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkox0a8rh, device:0
chaiml-kimid-v3a-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3a-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.6it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.6it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:02<00:11, 27.2it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:02<00:11, 27.2it/s]
Loading 0:  24%|██▍       | 87.0/363 [00:03<00:10, 26.3it/s]
Loading 0:  24%|██▍       | 87.0/363 [00:03<00:10, 26.3it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:09, 25.4it/s] 
Loading 0:  31%|███       | 113/363 [00:04<00:09, 25.4it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.3it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.3it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.2it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.2it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 25.2it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 25.2it/s]
Loading 0:  53%|█████▎    | 194/363 [00:20<00:06, 25.2it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:38, 4.22it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:38, 4.22it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:24, 5.78it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:24, 5.78it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.50it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.50it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 10.7it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 10.7it/s]
Loading 0:  84%|████████▍ | 306/363 [00:24<00:04, 13.0it/s]
Loading 0:  84%|████████▍ | 306/363 [00:24<00:04, 13.0it/s]
Loading 0:  93%|█████████▎| 336/363 [00:25<00:01, 15.8it/s]
Loading 0:  93%|█████████▎| 336/363 [00:25<00:01, 15.8it/s]
Loading 0: 100%|█████████▉| 362/363 [00:26<00:00, 17.7it/s]
Loading 0: 100%|█████████▉| 362/363 [00:26<00:00, 17.7it/s]
Loading 0: 100%|██████████| 363/363 [00:26<00:00, 17.7it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:26<00:00, 13.5it/s]
chaiml-kimid-v3a-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpkox0a8rh' 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-v1-mkmlizer: quantized model in 43.349s
chaiml-kimid-v3a-v1-mkmlizer: Processed model ChaiML/kimid-v3a in 89.591s
chaiml-kimid-v3a-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3a-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3a-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3a-v1/nvidia
chaiml-kimid-v3a-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3a-v1/nvidia/config.json
chaiml-kimid-v3a-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3a-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3a-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3a-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3a-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3a-v1/nvidia/tokenizer.json
chaiml-kimid-v3a-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3a-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3a-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3a-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3a-v1-mkmlizer completed after 165.76s with status: succeeded
Stopping job with name chaiml-kimid-v3a-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.59s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v3a-v1
Waiting for inference service chaiml-kimid-v3a-v1 to be ready
Inference service chaiml-kimid-v3a-v1 ready after 190.78756952285767s
Pipeline stage MKMLDeployer completed in 191.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.710097074508667s
Received healthy response to inference request in 2.3654282093048096s
Received healthy response to inference request in 2.91252064704895s
Received healthy response to inference request in 2.1732704639434814s
Received healthy response to inference request in 2.434404134750366s
5 requests
0 failed requests
5th percentile: 2.211702013015747
10th percentile: 2.2501335620880125
20th percentile: 2.326996660232544
30th percentile: 2.3792233943939207
40th percentile: 2.4068137645721435
50th percentile: 2.434404134750366
60th percentile: 2.5446813106536865
70th percentile: 2.654958486557007
80th percentile: 2.7505817890167235
90th percentile: 2.831551218032837
95th percentile: 2.8720359325408937
99th percentile: 2.904423704147339
mean time: 2.5191441059112547
Pipeline stage StressChecker completed in 14.11s
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 0.69s
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 0.60s
Shutdown handler de-registered
chaiml-kimid-v3a_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
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2716.03s
Shutdown handler de-registered
chaiml-kimid-v3a_v1 status is now inactive due to auto deactivation removed underperforming models