developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v3-lr2e6g16_v1
model_name: training123
model_group: ChaiML/kimid-v3_lr2e6g16
status: inactive
timestamp: 2025-12-05T18:36:33+00:00
num_battles: 20276
num_wins: 10589
celo_rating: 1308.86
family_friendly_score: 0.5087999999999999
family_friendly_standard_error: 0.007069972560059904
submission_type: basic
model_repo: ChaiML/kimid-v3_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': 0.41878598092705505, 'latency_mean': 2.3877899432182312, 'latency_p50': 2.3826117515563965, 'latency_p90': 2.600835847854614}, {'batch_size': 2, 'throughput': 0.6362012766972833, 'latency_mean': 3.1342375302314758, 'latency_p50': 3.1203783750534058, 'latency_p90': 3.3983864545822144}, {'batch_size': 3, 'throughput': 0.7857549284832888, 'latency_mean': 3.8081856787204744, 'latency_p50': 3.8306468725204468, 'latency_p90': 4.126994681358338}, {'batch_size': 4, 'throughput': 0.8798902144427794, 'latency_mean': 4.527362041473388, 'latency_p50': 4.502853751182556, 'latency_p90': 5.173549389839172}, {'batch_size': 5, 'throughput': 0.9559817568002986, 'latency_mean': 5.200836358070373, 'latency_p50': 5.176565766334534, 'latency_p90': 5.846566796302795}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v3_lr2e6g16
model_size: 24B
ranking_group: single
throughput_3p7s: 0.77
us_pacific_date: 2025-12-05
win_ratio: 0.5222430459656737
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>', 'User:', '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
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-kimid-v3-lr2e6g16-v1-mkmlizer
Waiting for job on chaiml-kimid-v3-lr2e6g16-v1-mkmlizer to finish
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3-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-v3-lr2e6g16-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: Downloaded to shared memory in 77.217s
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: Checking if ChaiML/kimid-v3_lr2e6g16 already exists in ChaiML
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_4ik2vuh, device:0
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   8%|▊         | 28.0/363 [00:01<00:13, 25.6it/s]
Loading 0:   8%|▊         | 28.0/363 [00:01<00:13, 25.6it/s]
Loading 0:  14%|█▍        | 50.0/363 [00:02<00:14, 21.9it/s]
Loading 0:  14%|█▍        | 50.0/363 [00:02<00:14, 21.9it/s]
Loading 0:  20%|██        | 73.0/363 [00:03<00:13, 21.9it/s]
Loading 0:  20%|██        | 73.0/363 [00:03<00:13, 21.9it/s]
Loading 0:  27%|██▋       | 99.0/363 [00:04<00:11, 23.1it/s]
Loading 0:  27%|██▋       | 99.0/363 [00:04<00:11, 23.1it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.3it/s] 
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.3it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 23.0it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 23.0it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:08, 23.2it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:08, 23.2it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.8it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.8it/s]
Loading 0:  53%|█████▎    | 194/363 [00:22<00:07, 21.8it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<00:45, 3.56it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<00:45, 3.56it/s]
Loading 0:  60%|██████    | 219/363 [00:23<00:30, 4.70it/s]
Loading 0:  60%|██████    | 219/363 [00:23<00:30, 4.70it/s]
Loading 0:  67%|██████▋   | 244/363 [00:24<00:17, 6.76it/s]
Loading 0:  67%|██████▋   | 244/363 [00:24<00:17, 6.76it/s]
Loading 0:  74%|███████▎  | 267/363 [00:25<00:11, 8.70it/s]
Loading 0:  74%|███████▎  | 267/363 [00:25<00:11, 8.70it/s]
Loading 0:  80%|███████▉  | 289/363 [00:26<00:06, 10.6it/s]
Loading 0:  80%|███████▉  | 289/363 [00:26<00:06, 10.6it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:04, 12.4it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:04, 12.4it/s]
Loading 0:  92%|█████████▏| 334/363 [00:28<00:01, 14.7it/s]
Loading 0:  92%|█████████▏| 334/363 [00:28<00:01, 14.7it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 15.0it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 15.0it/s]
Loading 0: 100%|██████████| 363/363 [00:30<00:00, 16.3it/s]
Loading 0: 100%|██████████| 363/363 [00:30<00:00, 16.3it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:30<00:00, 11.9it/s]
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp_4ik2vuh' 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-v3-lr2e6g16-v1-mkmlizer: quantized model in 48.938s
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: Processed model ChaiML/kimid-v3_lr2e6g16 in 126.156s
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g16-v1/nvidia
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g16-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g16-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3-lr2e6g16-v1-mkmlizer completed after 196.74s with status: succeeded
Stopping job with name chaiml-kimid-v3-lr2e6g16-v1-mkmlizer
Pipeline stage MKMLizer completed in 198.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.42s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v3-lr2e6g16-v1
Waiting for inference service chaiml-kimid-v3-lr2e6g16-v1 to be ready
Inference service chaiml-kimid-v3-lr2e6g16-v1 ready after 181.014967918396s
Pipeline stage MKMLDeployer completed in 181.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8825080394744873s
Received healthy response to inference request in 2.733743667602539s
Received healthy response to inference request in 2.6258440017700195s
Received healthy response to inference request in 2.3189778327941895s
Received healthy response to inference request in 3.0512866973876953s
5 requests
0 failed requests
5th percentile: 2.3803510665893555
10th percentile: 2.4417243003845215
20th percentile: 2.5644707679748535
30th percentile: 2.6474239349365236
40th percentile: 2.6905838012695313
50th percentile: 2.733743667602539
60th percentile: 2.793249416351318
70th percentile: 2.8527551651000977
80th percentile: 2.916263771057129
90th percentile: 2.983775234222412
95th percentile: 3.0175309658050535
99th percentile: 3.044535551071167
mean time: 2.722472047805786
Pipeline stage StressChecker completed in 15.13s
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 0.64s
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 1.00s
Shutdown handler de-registered
chaiml-kimid-v3-lr2e6g16_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-kimid-v3-lr2e6g16-v1-profiler
Waiting for inference service chaiml-kimid-v3-lr2e6g16-v1-profiler to be ready
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 2742.49s
Shutdown handler de-registered
chaiml-kimid-v3-lr2e6g16_v1 status is now inactive due to auto deactivation removed underperforming models