developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v4-lr2e6g16_v1
model_name: training123
model_group: ChaiML/kimid-v4_lr2e6g16
status: inactive
timestamp: 2025-12-06T16:26:29+00:00
num_battles: 6738
num_wins: 3502
celo_rating: 1310.87
family_friendly_score: 0.5142
family_friendly_standard_error: 0.0070682156164056
submission_type: basic
model_repo: ChaiML/kimid-v4_lr2e6g16
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': 0.345402476821788, 'latency_mean': 2.8950949144363403, 'latency_p50': 2.8845242261886597, 'latency_p90': 3.1519768238067627}, {'batch_size': 2, 'throughput': 0.5308253480562315, 'latency_mean': 3.763608638048172, 'latency_p50': 3.78441321849823, 'latency_p90': 4.073496031761169}, {'batch_size': 3, 'throughput': 0.6624068449608567, 'latency_mean': 4.508068703413009, 'latency_p50': 4.527737379074097, 'latency_p90': 4.864699339866638}, {'batch_size': 4, 'throughput': 0.7622949430512533, 'latency_mean': 5.237145589590073, 'latency_p50': 5.201558589935303, 'latency_p90': 5.969802904129028}, {'batch_size': 5, 'throughput': 0.8151449444559262, 'latency_mean': 6.102998338937759, 'latency_p50': 6.10864794254303, 'latency_p90': 6.861611032485962}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v4_lr2e6g16
model_size: 24B
ranking_group: single
throughput_3p7s: 0.52
us_pacific_date: 2025-12-06
win_ratio: 0.5197387948946275
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-lr2e6g16-v1-mkmlizer
Waiting for job on chaiml-kimid-v4-lr2e6g16-v1-mkmlizer to finish
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v4-lr2e6g16-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-lr2e6g16-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: Downloaded to shared memory in 95.086s
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: Checking if ChaiML/kimid-v4_lr2e6g16 already exists in ChaiML
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa7j7uaf3, device:0
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpa7j7uaf3' 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-lr2e6g16-v1-mkmlizer: quantized model in 44.377s
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: Processed model ChaiML/kimid-v4_lr2e6g16 in 139.463s
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v4-lr2e6g16-v1/nvidia
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v4-lr2e6g16-v1/nvidia/config.json
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v4-lr2e6g16-v1/nvidia/special_tokens_map.json
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v4-lr2e6g16-v1/nvidia/tokenizer_config.json
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v4-lr2e6g16-v1/nvidia/tokenizer.json
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4-lr2e6g16-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v4-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4-lr2e6g16-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v4-lr2e6g16-v1-mkmlizer completed after 215.64s with status: succeeded
Stopping job with name chaiml-kimid-v4-lr2e6g16-v1-mkmlizer
Pipeline stage MKMLizer completed in 216.18s
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-v4-lr2e6g16-v1
Waiting for inference service chaiml-kimid-v4-lr2e6g16-v1 to be ready
Inference service chaiml-kimid-v4-lr2e6g16-v1 ready after 201.00858521461487s
Pipeline stage MKMLDeployer completed in 201.42s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.0566163063049316s
Received healthy response to inference request in 2.5266377925872803s
Received healthy response to inference request in 2.921286106109619s
Received healthy response to inference request in 2.7435030937194824s
5 requests
1 failed requests
5th percentile: 2.570010852813721
10th percentile: 2.613383913040161
20th percentile: 2.700130033493042
30th percentile: 2.7790596961975096
40th percentile: 2.8501729011535644
50th percentile: 2.921286106109619
60th percentile: 2.9754181861877442
70th percentile: 3.0295502662658693
80th percentile: 6.4684113025665315
90th percentile: 13.292001295089722
95th percentile: 16.703796291351317
99th percentile: 19.433232288360596
mean time: 6.272726917266846
%s, retrying in %s seconds...
Received healthy response to inference request in 3.5080978870391846s
Received healthy response to inference request in 2.996446371078491s
Received healthy response to inference request in 2.441572904586792s
Received healthy response to inference request in 2.767059564590454s
Received healthy response to inference request in 2.5210986137390137s
5 requests
0 failed requests
5th percentile: 2.4574780464172363
10th percentile: 2.4733831882476807
20th percentile: 2.5051934719085693
30th percentile: 2.5702908039093018
40th percentile: 2.668675184249878
50th percentile: 2.767059564590454
60th percentile: 2.8588142871856688
70th percentile: 2.950569009780884
80th percentile: 3.09877667427063
90th percentile: 3.303437280654907
95th percentile: 3.405767583847046
99th percentile: 3.4876318264007566
mean time: 2.846855068206787
Pipeline stage StressChecker completed in 48.05s
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-lr2e6g16_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 2860.47s
Shutdown handler de-registered
chaiml-kimid-v4-lr2e6g16_v1 status is now inactive due to auto deactivation removed underperforming models