chaiml-kimid-v3

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v3_v1

model_name: training123

model_group: ChaiML/kimid-v3

status: inactive

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

num_battles: 19465

num_wins: 10221

celo_rating: 1310.77

family_friendly_score: 0.5048

family_friendly_standard_error: 0.007070741969553125

submission_type: basic

model_repo: ChaiML/kimid-v3

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': 0.41312982153994643, 'latency_mean': 2.4204686164855955, 'latency_p50': 2.422467589378357, 'latency_p90': 2.6391643285751343}, {'batch_size': 2, 'throughput': 0.6239297703309089, 'latency_mean': 3.2036492216587065, 'latency_p50': 3.212799310684204, 'latency_p90': 3.4570544719696046}, {'batch_size': 3, 'throughput': 0.7796352261023506, 'latency_mean': 3.8397105646133425, 'latency_p50': 3.825786828994751, 'latency_p90': 4.137644839286804}, {'batch_size': 4, 'throughput': 0.8754420047270087, 'latency_mean': 4.5482335066795345, 'latency_p50': 4.545282363891602, 'latency_p90': 4.970132446289062}, {'batch_size': 5, 'throughput': 0.9395505968889718, 'latency_mean': 5.282976261377335, 'latency_p50': 5.281850457191467, 'latency_p90': 5.891475701332092}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v3

model_size: 24B

ranking_group: single

throughput_3p7s: 0.75

us_pacific_date: 2025-12-05

win_ratio: 0.5250963267403032

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': ['</s>', 'User:', 'You:'], '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-v3-v1-mkmlizer
Waiting for job on chaiml-kimid-v3-v1-mkmlizer to finish
chaiml-kimid-v3-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3-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-v3-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3-v1-mkmlizer: Downloaded to shared memory in 52.980s
chaiml-kimid-v3-v1-mkmlizer: Checking if ChaiML/kimid-v3 already exists in ChaiML
chaiml-kimid-v3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwmys8x0g, device:0
chaiml-kimid-v3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 27.0/363 [00:01<00:12, 26.9it/s]
Loading 0:   7%|▋         | 27.0/363 [00:01<00:12, 26.9it/s]
Loading 0:  13%|█▎        | 46.0/363 [00:02<00:14, 21.6it/s]
Loading 0:  13%|█▎        | 46.0/363 [00:02<00:14, 21.6it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:03<00:13, 21.9it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:03<00:13, 21.9it/s]
Loading 0:  25%|██▌       | 92.0/363 [00:04<00:13, 20.8it/s]
Loading 0:  25%|██▌       | 92.0/363 [00:04<00:13, 20.8it/s]
Loading 0:  31%|███       | 113/363 [00:05<00:12, 20.6it/s] 
Loading 0:  31%|███       | 113/363 [00:05<00:12, 20.6it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:10, 22.3it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:10, 22.3it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:09, 20.7it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:09, 20.7it/s]
Loading 0:  50%|█████     | 182/363 [00:08<00:08, 21.4it/s]
Loading 0:  50%|█████     | 182/363 [00:08<00:08, 21.4it/s]
Loading 0:  50%|█████     | 182/363 [00:23<00:08, 21.4it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<00:40, 3.98it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<00:40, 3.98it/s]
Loading 0:  60%|██████    | 219/363 [00:24<00:28, 5.00it/s]
Loading 0:  60%|██████    | 219/363 [00:24<00:28, 5.00it/s]
Loading 0:  66%|██████▌   | 239/363 [00:25<00:19, 6.45it/s]
Loading 0:  66%|██████▌   | 239/363 [00:25<00:19, 6.45it/s]
Loading 0:  73%|███████▎  | 266/363 [00:26<00:10, 8.93it/s]
Loading 0:  73%|███████▎  | 266/363 [00:26<00:10, 8.93it/s]
Loading 0:  78%|███████▊  | 284/363 [00:27<00:07, 10.2it/s]
Loading 0:  78%|███████▊  | 284/363 [00:27<00:07, 10.2it/s]
Loading 0:  84%|████████▍ | 306/363 [00:28<00:04, 12.0it/s]
Loading 0:  84%|████████▍ | 306/363 [00:28<00:04, 12.0it/s]
Loading 0:  91%|█████████ | 329/363 [00:29<00:02, 14.0it/s]
Loading 0:  91%|█████████ | 329/363 [00:29<00:02, 14.0it/s]
Loading 0:  96%|█████████▌| 348/363 [00:30<00:01, 14.6it/s]
Loading 0:  96%|█████████▌| 348/363 [00:30<00:01, 14.6it/s]
Loading 0: 100%|██████████| 363/363 [00:31<00:00, 16.2it/s]
Loading 0: 100%|██████████| 363/363 [00:31<00:00, 16.2it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:31<00:00, 11.5it/s]
chaiml-kimid-v3-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpwmys8x0g' 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-v3-v1-mkmlizer: quantized model in 51.284s
chaiml-kimid-v3-v1-mkmlizer: Processed model ChaiML/kimid-v3 in 104.264s
chaiml-kimid-v3-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3-v1/nvidia/tokenizer.json
chaiml-kimid-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3-v1-mkmlizer completed after 185.69s with status: succeeded
Stopping job with name chaiml-kimid-v3-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.15s
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-v3-v1
Waiting for inference service chaiml-kimid-v3-v1 to be ready
Inference service chaiml-kimid-v3-v1 ready after 191.7158625125885s
Pipeline stage MKMLDeployer completed in 192.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5781092643737793s
Received healthy response to inference request in 3.4290771484375s
Received healthy response to inference request in 3.3776676654815674s
Received healthy response to inference request in 3.386273145675659s
Received healthy response to inference request in 3.512260913848877s
5 requests
0 failed requests
5th percentile: 2.7380209445953367
10th percentile: 2.8979326248168946
20th percentile: 3.21775598526001
30th percentile: 3.379388761520386
40th percentile: 3.3828309535980225
50th percentile: 3.386273145675659
60th percentile: 3.4033947467803953
70th percentile: 3.420516347885132
80th percentile: 3.4457139015197753
90th percentile: 3.4789874076843263
95th percentile: 3.4956241607666017
99th percentile: 3.508933563232422
mean time: 3.2566776275634766
Pipeline stage StressChecker completed in 17.48s
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 0.63s
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 0.57s
Shutdown handler de-registered
chaiml-kimid-v3_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 2698.88s
Shutdown handler de-registered
chaiml-kimid-v3_v1 status is now inactive due to auto deactivation removed underperforming models