chaiml-kimid-v3b

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v3b_v1

model_name: training123

model_group: ChaiML/kimid-v3b

status: inactive

timestamp: 2025-12-05T21:50:54+00:00

num_battles: 9594

num_wins: 4979

celo_rating: 1306.62

family_friendly_score: 0.4972

family_friendly_standard_error: 0.0070709569366529165

submission_type: basic

model_repo: ChaiML/kimid-v3b

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': 0.3455307197725905, 'latency_mean': 2.894034252166748, 'latency_p50': 2.919669985771179, 'latency_p90': 3.1362767219543457}, {'batch_size': 2, 'throughput': 0.5334237780171001, 'latency_mean': 3.7436075353622438, 'latency_p50': 3.7327300310134888, 'latency_p90': 4.073670291900635}, {'batch_size': 3, 'throughput': 0.6657856841894867, 'latency_mean': 4.485414752960205, 'latency_p50': 4.48812460899353, 'latency_p90': 4.848562860488892}, {'batch_size': 4, 'throughput': 0.7580817571227781, 'latency_mean': 5.257635859251022, 'latency_p50': 5.26256537437439, 'latency_p90': 5.958857679367065}, {'batch_size': 5, 'throughput': 0.818496279439558, 'latency_mean': 6.065637130737304, 'latency_p50': 6.088285565376282, 'latency_p90': 6.877562618255615}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v3b

model_size: 24B

ranking_group: single

throughput_3p7s: 0.53

us_pacific_date: 2025-12-05

win_ratio: 0.518970189701897

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:', '</s>', '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-kimid-v3b-v1-mkmlizer
Waiting for job on chaiml-kimid-v3b-v1-mkmlizer to finish
chaiml-kimid-v3b-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3b-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3b-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-v3b-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3b-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3b-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3b-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3b-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3b-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3b-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3b-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3b-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3b-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3b-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3b-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3b-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3b-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3b-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3b-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3b-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3b-v1-mkmlizer: Downloaded to shared memory in 80.796s
chaiml-kimid-v3b-v1-mkmlizer: Checking if ChaiML/kimid-v3b already exists in ChaiML
chaiml-kimid-v3b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiryzd7rc, device:0
chaiml-kimid-v3b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3b-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   8%|▊         | 28.0/363 [00:00<00:11, 29.2it/s]
Loading 0:   8%|▊         | 28.0/363 [00:00<00:11, 29.2it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.8it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.8it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 25.1it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 25.1it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.4it/s] 
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.4it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.5it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.5it/s]
Loading 0:  45%|████▍     | 162/363 [00:06<00:07, 26.3it/s]
Loading 0:  45%|████▍     | 162/363 [00:06<00:07, 26.3it/s]
Loading 0:  52%|█████▏    | 188/363 [00:07<00:06, 26.1it/s]
Loading 0:  52%|█████▏    | 188/363 [00:07<00:06, 26.1it/s]
Loading 0:  52%|█████▏    | 188/363 [00:20<00:06, 26.1it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.49it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.49it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 5.98it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 5.98it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.63it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.63it/s]
Loading 0:  78%|███████▊  | 282/363 [00:23<00:07, 11.0it/s]
Loading 0:  78%|███████▊  | 282/363 [00:23<00:07, 11.0it/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, 17.8it/s]
Loading 0: 100%|█████████▉| 362/363 [00:26<00:00, 17.8it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.8it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.4it/s]
chaiml-kimid-v3b-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpiryzd7rc' 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-v3b-v1-mkmlizer: quantized model in 43.933s
chaiml-kimid-v3b-v1-mkmlizer: Processed model ChaiML/kimid-v3b in 124.730s
chaiml-kimid-v3b-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3b-v1/nvidia
chaiml-kimid-v3b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3b-v1/nvidia/config.json
chaiml-kimid-v3b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3b-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3b-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3b-v1/nvidia/tokenizer.json
chaiml-kimid-v3b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3b-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3b-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3b-v1-mkmlizer completed after 208.03s with status: succeeded
Stopping job with name chaiml-kimid-v3b-v1-mkmlizer
Pipeline stage MKMLizer completed in 210.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v3b-v1
Waiting for inference service chaiml-kimid-v3b-v1 to be ready
Inference service chaiml-kimid-v3b-v1 ready after 191.1705620288849s
Pipeline stage MKMLDeployer completed in 191.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.455514669418335s
Received healthy response to inference request in 2.9953646659851074s
Received healthy response to inference request in 2.639688730239868s
Received healthy response to inference request in 3.3271379470825195s
Received healthy response to inference request in 2.15881085395813s
5 requests
0 failed requests
5th percentile: 2.2181516170501707
10th percentile: 2.277492380142212
20th percentile: 2.396173906326294
30th percentile: 2.4923494815826417
40th percentile: 2.5660191059112547
50th percentile: 2.639688730239868
60th percentile: 2.7819591045379637
70th percentile: 2.9242294788360597
80th percentile: 3.0617193222045898
90th percentile: 3.194428634643555
95th percentile: 3.260783290863037
99th percentile: 3.313867015838623
mean time: 2.715303373336792
Pipeline stage StressChecker completed in 15.56s
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 1.01s
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 0.65s
Shutdown handler de-registered
chaiml-kimid-v3b_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 2767.83s
Shutdown handler de-registered