chaiml-kimid-v2-cosine-_21546

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v2-cosine-_21546_v1

model_name: training123

model_group: ChaiML/kimid-v2_cosine-l

status: inactive

timestamp: 2025-12-04T12:57:18+00:00

num_battles: 5180

num_wins: 2743

celo_rating: 1311.6

family_friendly_score: 0.5032

family_friendly_standard_error: 0.007070922994913747

submission_type: basic

model_repo: ChaiML/kimid-v2_cosine-lr2e6g32

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': 0.34931307120795424, 'latency_mean': 2.862685364484787, 'latency_p50': 2.849312901496887, 'latency_p90': 3.130330514907837}, {'batch_size': 2, 'throughput': 0.536624693135998, 'latency_mean': 3.719531216621399, 'latency_p50': 3.6844284534454346, 'latency_p90': 4.052791595458984}, {'batch_size': 3, 'throughput': 0.6680307559359335, 'latency_mean': 4.479587603807449, 'latency_p50': 4.4852834939956665, 'latency_p90': 5.023633027076721}, {'batch_size': 4, 'throughput': 0.7653925397015956, 'latency_mean': 5.1975458467006685, 'latency_p50': 5.199223637580872, 'latency_p90': 6.003328394889832}, {'batch_size': 5, 'throughput': 0.82758961537208, 'latency_mean': 6.020689327716827, 'latency_p50': 6.048197507858276, 'latency_p90': 6.736537122726441}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v2_cosine-lr2e6g32

model_size: 24B

ranking_group: single

throughput_3p7s: 0.53

us_pacific_date: 2025-12-04

win_ratio: 0.5295366795366795

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:', '</s>', 'User:'], '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-v2-cosine-21546-v1-mkmlizer
Waiting for job on chaiml-kimid-v2-cosine-21546-v1-mkmlizer to finish
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v2-cosine-21546-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-v2-cosine-21546-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: Downloaded to shared memory in 100.881s
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: Checking if ChaiML/kimid-v2_cosine-lr2e6g32 already exists in ChaiML
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph9h2s55_, device:0
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.2it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.2it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.2it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.2it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.8it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.8it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.3it/s] 
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.3it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.9it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.9it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.9it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.9it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:06, 25.0it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:06, 25.0it/s]
Loading 0:  52%|█████▏    | 189/363 [00:20<00:06, 25.0it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.42it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.42it/s]
Loading 0:  60%|██████    | 219/363 [00:21<00:25, 5.55it/s]
Loading 0:  60%|██████    | 219/363 [00:21<00:25, 5.55it/s]
Loading 0:  68%|██████▊   | 247/363 [00:22<00:14, 7.93it/s]
Loading 0:  68%|██████▊   | 247/363 [00:22<00:14, 7.93it/s]
Loading 0:  75%|███████▌  | 273/363 [00:23<00:08, 10.3it/s]
Loading 0:  75%|███████▌  | 273/363 [00:23<00:08, 10.3it/s]
Loading 0:  83%|████████▎ | 303/363 [00:24<00:04, 13.2it/s]
Loading 0:  83%|████████▎ | 303/363 [00:24<00:04, 13.2it/s]
Loading 0:  90%|█████████ | 328/363 [00:25<00:02, 15.3it/s]
Loading 0:  90%|█████████ | 328/363 [00:25<00:02, 15.3it/s]
Loading 0:  96%|█████████▌| 348/363 [00:26<00:00, 16.1it/s]
Loading 0:  96%|█████████▌| 348/363 [00:26<00:00, 16.1it/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-v2-cosine-21546-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v2-cosine-21546-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v2-cosine-21546-v1-mkmlizer completed after 213.54s with status: succeeded
Stopping job with name chaiml-kimid-v2-cosine-21546-v1-mkmlizer
Pipeline stage MKMLizer completed in 214.00s
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-v2-cosine-21546-v1
Waiting for inference service chaiml-kimid-v2-cosine-21546-v1 to be ready
Inference service chaiml-kimid-v2-cosine-21546-v1 ready after 180.83365964889526s
Pipeline stage MKMLDeployer completed in 181.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6867141723632812s
Received healthy response to inference request in 2.9067978858947754s
Received healthy response to inference request in 2.4360172748565674s
Received healthy response to inference request in 2.6748862266540527s
Received healthy response to inference request in 2.608306884765625s
5 requests
0 failed requests
5th percentile: 2.470475196838379
10th percentile: 2.5049331188201904
20th percentile: 2.5738489627838135
30th percentile: 2.6216227531433107
40th percentile: 2.6482544898986817
50th percentile: 2.6748862266540527
60th percentile: 2.679617404937744
70th percentile: 2.6843485832214355
80th percentile: 2.73073091506958
90th percentile: 2.818764400482178
95th percentile: 2.8627811431884767
99th percentile: 2.8979945373535156
mean time: 2.6625444889068604
Pipeline stage StressChecker completed in 14.63s
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 0.60s
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-v2-cosine-_21546_v1 status is now deployed due to DeploymentManager action
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 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
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 2802.32s
Shutdown handler de-registered
chaiml-kimid-v2-cosine-_21546_v1 status is now inactive due to auto deactivation removed underperforming models