chaiml-kimid-v4a-eos-lr5e6g32

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v4a-eos-lr5e6g32_v1

model_name: training123

model_group: ChaiML/kimid-v4a_eos-lr5

status: inactive

timestamp: 2025-12-06T16:36:44+00:00

num_battles: 7461

num_wins: 3952

celo_rating: 1317.23

family_friendly_score: 0.501

family_friendly_standard_error: 0.00707105366971571

submission_type: basic

model_repo: ChaiML/kimid-v4a_eos-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': 0.3457439955052516, 'latency_mean': 2.892232929468155, 'latency_p50': 2.9009828567504883, 'latency_p90': 3.152509307861328}, {'batch_size': 2, 'throughput': 0.5276353426873712, 'latency_mean': 3.779380742311478, 'latency_p50': 3.7952858209609985, 'latency_p90': 4.096471929550171}, {'batch_size': 3, 'throughput': 0.6590919987659845, 'latency_mean': 4.540783932209015, 'latency_p50': 4.50215470790863, 'latency_p90': 4.896363568305969}, {'batch_size': 4, 'throughput': 0.7555900005642915, 'latency_mean': 5.2833145964145665, 'latency_p50': 5.239853620529175, 'latency_p90': 6.0140375137329105}, {'batch_size': 5, 'throughput': 0.8148596002065362, 'latency_mean': 6.12413676738739, 'latency_p50': 6.147526144981384, 'latency_p90': 6.981601500511169}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v4a_eos-lr5e6g32

model_size: 24B

ranking_group: single

throughput_3p7s: 0.52

us_pacific_date: 2025-12-06

win_ratio: 0.5296877094223295

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': ['You:', 'User:', '</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-v4a-eos-lr5e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer to finish
Received healthy response to inference request in 2.6690361499786377s
Received healthy response to inference request in 3.086104154586792s
5 requests
0 failed requests
5th percentile: 2.5839523792266847
10th percentile: 2.6052233219146728
20th percentile: 2.6477652072906492
30th percentile: 2.671204996109009
40th percentile: 2.675542688369751
50th percentile: 2.679880380630493
60th percentile: 2.8188059329986572
70th percentile: 2.9577314853668213
80th percentile: 3.038976240158081
90th percentile: 3.0625401973724364
95th percentile: 3.0743221759796144
99th percentile: 3.0837477588653566
mean time: 2.8049792766571047
Pipeline stage StressChecker completed in 16.17s
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 0.77s
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 0.78s
Shutdown handler de-registered
chaiml-kimid-v4-eos-lr5e6g32_v1 status is now deployed due to DeploymentManager action
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v4a-eos-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-v4a-eos-lr5e6g32-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: Downloaded to shared memory in 102.403s
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: Checking if ChaiML/kimid-v4a_eos-lr5e6g32 already exists in ChaiML
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpip4ukocj, device:0
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.3it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.3it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:02<00:11, 26.7it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:02<00:11, 26.7it/s]
Loading 0:  24%|██▍       | 87.0/363 [00:03<00:10, 26.0it/s]
Loading 0:  24%|██▍       | 87.0/363 [00:03<00:10, 26.0it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:09, 25.8it/s] 
Loading 0:  31%|███       | 113/363 [00:04<00:09, 25.8it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.8it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.8it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 27.2it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 27.2it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 24.6it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 24.6it/s]
Loading 0:  53%|█████▎    | 194/363 [00:20<00:06, 24.6it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:38, 4.16it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:38, 4.16it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:24, 5.72it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:24, 5.72it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.44it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.44it/s]
Loading 0:  76%|███████▌  | 275/363 [00:23<00:08, 9.96it/s]
Loading 0:  76%|███████▌  | 275/363 [00:23<00:08, 9.96it/s]
Loading 0:  83%|████████▎ | 303/363 [00:24<00:04, 12.8it/s]
Loading 0:  83%|████████▎ | 303/363 [00:24<00:04, 12.8it/s]
Loading 0:  90%|████████▉ | 325/363 [00:25<00:02, 14.5it/s]
Loading 0:  90%|████████▉ | 325/363 [00:25<00:02, 14.5it/s]
Loading 0:  96%|█████████▌| 348/363 [00:26<00:00, 16.0it/s]
Loading 0:  96%|█████████▌| 348/363 [00:26<00:00, 16.0it/s]
Loading 0: 100%|██████████| 363/363 [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, 13.4it/s]
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpip4ukocj' 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-v4a-eos-lr5e6g32-v1-mkmlizer: quantized model in 43.975s
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: Processed model ChaiML/kimid-v4a_eos-lr5e6g32 in 146.379s
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v4a-eos-lr5e6g32-v1/nvidia
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v4a-eos-lr5e6g32-v1/nvidia/config.json
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v4a-eos-lr5e6g32-v1/nvidia/special_tokens_map.json
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v4a-eos-lr5e6g32-v1/nvidia/tokenizer_config.json
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v4a-eos-lr5e6g32-v1/nvidia/tokenizer.json
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4a-eos-lr5e6g32-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4a-eos-lr5e6g32-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer completed after 206.49s with status: succeeded
Stopping job with name chaiml-kimid-v4a-eos-lr5e6g32-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.12s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.61s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v4a-eos-lr5e6g32-v1
Waiting for inference service chaiml-kimid-v4a-eos-lr5e6g32-v1 to be ready
Inference service chaiml-kimid-v4a-eos-lr5e6g32-v1 ready after 200.849755525589s
Pipeline stage MKMLDeployer completed in 201.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.584946393966675s
Received healthy response to inference request in 2.9065699577331543s
Received healthy response to inference request in 3.2367196083068848s
Received healthy response to inference request in 3.06693696975708s
Received healthy response to inference request in 2.4050676822662354s
5 requests
0 failed requests
5th percentile: 2.441043424606323
10th percentile: 2.477019166946411
20th percentile: 2.548970651626587
30th percentile: 2.649271106719971
40th percentile: 2.7779205322265623
50th percentile: 2.9065699577331543
60th percentile: 2.9707167625427244
70th percentile: 3.034863567352295
80th percentile: 3.100893497467041
90th percentile: 3.168806552886963
95th percentile: 3.202763080596924
99th percentile: 3.2299283027648924
mean time: 2.8400481224060057
Pipeline stage StressChecker completed in 15.77s
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 0.78s
Shutdown handler de-registered
chaiml-kimid-v4a-eos-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 2864.99s
Shutdown handler de-registered
chaiml-kimid-v4a-eos-lr5e6g32_v1 status is now inactive due to auto deactivation removed underperforming models