chaiml-kimid-v2-cosine-l_4565

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v2-cosine-l_4565_v1

model_name: training123

model_group: ChaiML/kimid-v2_cosine-l

status: inactive

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

num_battles: 5108

num_wins: 2583

celo_rating: 1293.96

family_friendly_score: 0.504

family_friendly_standard_error: 0.007070841534074993

submission_type: basic

model_repo: ChaiML/kimid-v2_cosine-lr5e6g32

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': 0.3448769749837365, 'latency_mean': 2.899522442817688, 'latency_p50': 2.900148868560791, 'latency_p90': 3.1439358234405517}, {'batch_size': 2, 'throughput': 0.528026946598239, 'latency_mean': 3.7774642169475556, 'latency_p50': 3.7725247144699097, 'latency_p90': 4.062393379211426}, {'batch_size': 3, 'throughput': 0.6572749170672886, 'latency_mean': 4.562821562290192, 'latency_p50': 4.570030331611633, 'latency_p90': 4.906794786453247}, {'batch_size': 4, 'throughput': 0.7540964342141919, 'latency_mean': 5.282777733802796, 'latency_p50': 5.242201566696167, 'latency_p90': 5.946845126152039}, {'batch_size': 5, 'throughput': 0.8018440748208417, 'latency_mean': 6.206670124530792, 'latency_p50': 6.195640206336975, 'latency_p90': 6.9270987749099735}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v2_cosine-lr5e6g32

model_size: 24B

ranking_group: single

throughput_3p7s: 0.52

us_pacific_date: 2025-12-04

win_ratio: 0.5056773688332028

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>', 'You:', '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-l-4565-v1-mkmlizer
Waiting for job on chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer to finish
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v2-cosine-l-4565-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-l-4565-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: Downloaded to shared memory in 81.555s
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: Checking if ChaiML/kimid-v2_cosine-lr5e6g32 already exists in ChaiML
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxqz6xuwd, device:0
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.6it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.6it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:12, 25.3it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:12, 25.3it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:03<00:15, 19.2it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:03<00:15, 19.2it/s]
Loading 0:  25%|██▌       | 92.0/363 [00:04<00:13, 20.1it/s]
Loading 0:  25%|██▌       | 92.0/363 [00:04<00:13, 20.1it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.6it/s] 
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.6it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 24.9it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 24.9it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 25.2it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 25.2it/s]
Loading 0:  49%|████▉     | 178/363 [00:21<00:07, 25.2it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:32, 4.98it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:32, 4.98it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21, 6.40it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21, 6.40it/s]
Loading 0:  70%|██████▉   | 253/363 [00:23<00:12, 8.71it/s]
Loading 0:  70%|██████▉   | 253/363 [00:23<00:12, 8.71it/s]
Loading 0:  77%|███████▋  | 280/363 [00:24<00:07, 11.0it/s]
Loading 0:  77%|███████▋  | 280/363 [00:24<00:07, 11.0it/s]
Loading 0:  84%|████████▍ | 306/363 [00:25<00:04, 13.1it/s]
Loading 0:  84%|████████▍ | 306/363 [00:25<00:04, 13.1it/s]
Loading 0:  93%|█████████▎| 336/363 [00:26<00:01, 15.8it/s]
Loading 0:  93%|█████████▎| 336/363 [00:26<00:01, 15.8it/s]
Loading 0: 100%|█████████▉| 362/363 [00:27<00:00, 17.7it/s]
Loading 0: 100%|█████████▉| 362/363 [00:27<00:00, 17.7it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.7it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.1it/s]
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpxqz6xuwd' 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-v2-cosine-l-4565-v1-mkmlizer: quantized model in 44.548s
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: Processed model ChaiML/kimid-v2_cosine-lr5e6g32 in 126.103s
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-l-4565-v1/nvidia
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-l-4565-v1/nvidia/config.json
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-l-4565-v1/nvidia/special_tokens_map.json
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-l-4565-v1/nvidia/tokenizer_config.json
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-l-4565-v1/nvidia/flywheel_model.0.safetensors
chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-l-4565-v1/nvidia/flywheel_model.1.safetensors
Job chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer completed after 216.62s with status: succeeded
Stopping job with name chaiml-kimid-v2-cosine-l-4565-v1-mkmlizer
Pipeline stage MKMLizer completed in 217.12s
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-l-4565-v1
Waiting for inference service chaiml-kimid-v2-cosine-l-4565-v1 to be ready
Inference service chaiml-kimid-v2-cosine-l-4565-v1 ready after 180.86165380477905s
Pipeline stage MKMLDeployer completed in 181.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5962321758270264s
Received healthy response to inference request in 2.658825635910034s
Received healthy response to inference request in 2.569103240966797s
Received healthy response to inference request in 2.7340173721313477s
Received healthy response to inference request in 2.8979125022888184s
5 requests
0 failed requests
5th percentile: 2.574529027938843
10th percentile: 2.579954814910889
20th percentile: 2.5908063888549804
30th percentile: 2.6087508678436278
40th percentile: 2.633788251876831
50th percentile: 2.658825635910034
60th percentile: 2.6889023303985597
70th percentile: 2.718979024887085
80th percentile: 2.7667963981628416
90th percentile: 2.83235445022583
95th percentile: 2.8651334762573244
99th percentile: 2.8913566970825197
mean time: 2.6912181854248045
Pipeline stage StressChecker completed in 14.74s
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 0.85s
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 0.70s
Shutdown handler de-registered
chaiml-kimid-v2-cosine-l_4565_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 2812.76s
Shutdown handler de-registered
chaiml-kimid-v2-cosine-l_4565_v1 status is now inactive due to auto deactivation removed underperforming models