developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v4-lr5e6g32_v1
model_name: training123
model_group: ChaiML/kimid-v4_lr5e6g32
status: inactive
timestamp: 2025-12-06T16:16:38+00:00
num_battles: 6105
num_wins: 3188
celo_rating: 1310.25
family_friendly_score: 0.508
family_friendly_standard_error: 0.007070162657251953
submission_type: basic
model_repo: ChaiML/kimid-v4_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': 0.3468561888243762, 'latency_mean': 2.8829715991020204, 'latency_p50': 2.887660264968872, 'latency_p90': 3.1464617013931275}, {'batch_size': 2, 'throughput': 0.5327828421442362, 'latency_mean': 3.7494940984249117, 'latency_p50': 3.761597990989685, 'latency_p90': 4.030856037139893}, {'batch_size': 3, 'throughput': 0.6655274231052585, 'latency_mean': 4.503731036186219, 'latency_p50': 4.513399839401245, 'latency_p90': 4.8162201881408695}, {'batch_size': 4, 'throughput': 0.7593278427222103, 'latency_mean': 5.243815962076187, 'latency_p50': 5.247447729110718, 'latency_p90': 6.01347017288208}, {'batch_size': 5, 'throughput': 0.8260394200551799, 'latency_mean': 6.027495791912079, 'latency_p50': 6.022415041923523, 'latency_p90': 6.827463984489441}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v4_lr5e6g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.53
us_pacific_date: 2025-12-06
win_ratio: 0.5221949221949221
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:', 'You:', '</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-v4-lr5e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v4-lr5e6g32-v1-mkmlizer to finish
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v4-lr5e6g32-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-v4-lr5e6g32-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: Downloaded to shared memory in 98.409s
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: Checking if ChaiML/kimid-v4_lr5e6g32 already exists in ChaiML
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0x735dnn, device:0
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   6%|▋         | 23.0/363 [00:01<00:17, 19.3it/s]
Loading 0:   6%|▋         | 23.0/363 [00:01<00:17, 19.3it/s]
Loading 0:  11%|█         | 40.0/363 [00:02<00:18, 17.9it/s]
Loading 0:  11%|█         | 40.0/363 [00:02<00:18, 17.9it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:03<00:13, 22.1it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:03<00:13, 22.1it/s]
Loading 0:  27%|██▋       | 97.0/363 [00:04<00:11, 23.5it/s]
Loading 0:  27%|██▋       | 97.0/363 [00:04<00:11, 23.5it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.7it/s] 
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.7it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 25.5it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 25.5it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.2it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.2it/s]
Loading 0:  50%|████▉     | 181/363 [00:21<00:06, 26.2it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:32, 4.96it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:32, 4.96it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21, 6.39it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21, 6.39it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:12, 8.93it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:12, 8.93it/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, 13.2it/s]
Loading 0:  84%|████████▍ | 306/363 [00:25<00:04, 13.2it/s]
Loading 0:  93%|█████████▎| 336/363 [00:26<00:01, 16.0it/s]
Loading 0:  93%|█████████▎| 336/363 [00:26<00:01, 16.0it/s]
Loading 0: 100%|█████████▉| 362/363 [00:27<00:00, 17.8it/s]
Loading 0: 100%|█████████▉| 362/363 [00:27<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, 13.2it/s]
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp0x735dnn' 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-v4-lr5e6g32-v1-mkmlizer: quantized model in 44.597s
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: Processed model ChaiML/kimid-v4_lr5e6g32 in 143.007s
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v4-lr5e6g32-v1/nvidia
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v4-lr5e6g32-v1/nvidia/config.json
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v4-lr5e6g32-v1/nvidia/special_tokens_map.json
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v4-lr5e6g32-v1/nvidia/tokenizer_config.json
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v4-lr5e6g32-v1/nvidia/tokenizer.json
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4-lr5e6g32-v1/nvidia/flywheel_model.0.safetensors
chaiml-kimid-v4-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4-lr5e6g32-v1/nvidia/flywheel_model.1.safetensors
Job chaiml-kimid-v4-lr5e6g32-v1-mkmlizer completed after 215.75s with status: succeeded
Stopping job with name chaiml-kimid-v4-lr5e6g32-v1-mkmlizer
Pipeline stage MKMLizer completed in 216.29s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v4-lr5e6g32-v1
Waiting for inference service chaiml-kimid-v4-lr5e6g32-v1 to be ready
Inference service chaiml-kimid-v4-lr5e6g32-v1 ready after 201.6882882118225s
Pipeline stage MKMLDeployer completed in 203.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8715806007385254s
Received healthy response to inference request in 3.3426692485809326s
Received healthy response to inference request in 3.173454523086548s
Received healthy response to inference request in 2.557591676712036s
Received healthy response to inference request in 2.1348533630371094s
5 requests
0 failed requests
5th percentile: 2.2194010257720946
10th percentile: 2.30394868850708
20th percentile: 2.473044013977051
30th percentile: 2.620389461517334
40th percentile: 2.7459850311279297
50th percentile: 2.8715806007385254
60th percentile: 2.9923301696777345
70th percentile: 3.113079738616943
80th percentile: 3.2072974681854247
90th percentile: 3.274983358383179
95th percentile: 3.3088263034820558
99th percentile: 3.3359006595611573
mean time: 2.8160298824310304
Pipeline stage StressChecker completed in 15.85s
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 0.62s
Shutdown handler de-registered
chaiml-kimid-v4-lr5e6g32_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 2791.37s
Shutdown handler de-registered
chaiml-kimid-v4-lr5e6g32_v1 status is now inactive due to auto deactivation removed underperforming models