developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v3-lr5e6g32_v1
model_name: training123
model_group: ChaiML/kimid-v3_lr5e6g32
status: inactive
timestamp: 2025-12-05T18:36:33+00:00
num_battles: 20130
num_wins: 10404
celo_rating: 1304.65
family_friendly_score: 0.5056
family_friendly_standard_error: 0.007070624300583366
submission_type: basic
model_repo: ChaiML/kimid-v3_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': 0.3490479104008958, 'latency_mean': 2.86485869884491, 'latency_p50': 2.8399637937545776, 'latency_p90': 3.124185800552368}, {'batch_size': 2, 'throughput': 0.5321291586194097, 'latency_mean': 3.7494847559928894, 'latency_p50': 3.7580552101135254, 'latency_p90': 4.017551326751709}, {'batch_size': 3, 'throughput': 0.6641786675427911, 'latency_mean': 4.507966092824936, 'latency_p50': 4.50410532951355, 'latency_p90': 5.040292143821716}, {'batch_size': 4, 'throughput': 0.7553085874687708, 'latency_mean': 5.277578641176223, 'latency_p50': 5.286102771759033, 'latency_p90': 5.809382009506225}, {'batch_size': 5, 'throughput': 0.8168463720479648, 'latency_mean': 6.084240350723267, 'latency_p50': 6.08914852142334, 'latency_p90': 6.921004271507263}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v3_lr5e6g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.53
us_pacific_date: 2025-12-05
win_ratio: 0.5168405365126677
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-v3-lr5e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v3-lr5e6g32-v1-mkmlizer to finish
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3-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-v3-lr5e6g32-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: Downloaded to shared memory in 57.818s
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: Checking if ChaiML/kimid-v3_lr5e6g32 already exists in ChaiML
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy1jke_gu, device:0
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.9it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.9it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:02<00:11, 27.8it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:02<00:11, 27.8it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 25.6it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 25.6it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 25.7it/s] 
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 25.7it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.3it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.3it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.1it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.1it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:06, 25.1it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:06, 25.1it/s]
Loading 0:  52%|█████▏    | 189/363 [00:20<00:06, 25.1it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.48it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.48it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 6.00it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 6.00it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.67it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.67it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 10.8it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 10.8it/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:  92%|█████████▏| 335/363 [00:25<00:01, 15.9it/s]
Loading 0:  92%|█████████▏| 335/363 [00:25<00:01, 15.9it/s]
Loading 0:  98%|█████████▊| 357/363 [00:26<00:00, 16.8it/s]
Loading 0:  98%|█████████▊| 357/363 [00:26<00:00, 16.8it/s]
Loading 0: 100%|██████████| 363/363 [00:26<00:00, 17.6it/s]
Loading 0: 100%|██████████| 363/363 [00:26<00:00, 17.6it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:26<00:00, 13.5it/s]
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpy1jke_gu' 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-lr5e6g32-v1-mkmlizer: quantized model in 43.892s
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: Processed model ChaiML/kimid-v3_lr5e6g32 in 101.711s
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3-lr5e6g32-v1/nvidia
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3-lr5e6g32-v1/nvidia/config.json
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3-lr5e6g32-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3-lr5e6g32-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3-lr5e6g32-v1/nvidia/tokenizer.json
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3-lr5e6g32-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3-lr5e6g32-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3-lr5e6g32-v1-mkmlizer completed after 181.67s with status: succeeded
Stopping job with name chaiml-kimid-v3-lr5e6g32-v1-mkmlizer
Pipeline stage MKMLizer completed in 182.14s
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-v3-lr5e6g32-v1
Waiting for inference service chaiml-kimid-v3-lr5e6g32-v1 to be ready
Inference service chaiml-kimid-v3-lr5e6g32-v1 ready after 181.14284586906433s
Pipeline stage MKMLDeployer completed in 181.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.910303831100464s
Received healthy response to inference request in 2.9882683753967285s
Received healthy response to inference request in 2.354773998260498s
Received healthy response to inference request in 2.9687485694885254s
Received healthy response to inference request in 2.551447868347168s
5 requests
0 failed requests
5th percentile: 2.394108772277832
10th percentile: 2.433443546295166
20th percentile: 2.512113094329834
30th percentile: 2.623219060897827
40th percentile: 2.7667614459991454
50th percentile: 2.910303831100464
60th percentile: 2.9336817264556885
70th percentile: 2.957059621810913
80th percentile: 2.972652530670166
90th percentile: 2.980460453033447
95th percentile: 2.984364414215088
99th percentile: 2.9874875831604
mean time: 2.7547085285186768
Pipeline stage StressChecker completed in 14.96s
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 0.68s
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 0.68s
Shutdown handler de-registered
chaiml-kimid-v3-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 2806.18s
Shutdown handler de-registered
chaiml-kimid-v3-lr5e6g32_v1 status is now inactive due to auto deactivation removed underperforming models