developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v4a-lr2e6g32_v1
model_name: training123
model_group: ChaiML/kimid-v4a_lr2e6g3
status: inactive
timestamp: 2025-12-07T00:08:08+00:00
num_battles: 7200
num_wins: 3717
celo_rating: 1304.74
family_friendly_score: 0.5014000000000001
family_friendly_standard_error: 0.007071040093225324
submission_type: basic
model_repo: ChaiML/kimid-v4a_lr2e6g32
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': 0.34920295702047854, 'latency_mean': 2.8635874831676484, 'latency_p50': 2.864715099334717, 'latency_p90': 3.104726529121399}, {'batch_size': 2, 'throughput': 0.5374707066058094, 'latency_mean': 3.7175084173679354, 'latency_p50': 3.7009921073913574, 'latency_p90': 3.99516704082489}, {'batch_size': 3, 'throughput': 0.6749975415833426, 'latency_mean': 4.434561352729798, 'latency_p50': 4.42729115486145, 'latency_p90': 4.772485327720642}, {'batch_size': 4, 'throughput': 0.7680041151783003, 'latency_mean': 5.190225142240524, 'latency_p50': 5.216396689414978, 'latency_p90': 5.644520688056946}, {'batch_size': 5, 'throughput': 0.828318806430214, 'latency_mean': 5.993185856342316, 'latency_p50': 5.991366267204285, 'latency_p90': 6.82826976776123}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v4a_lr2e6g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.53
us_pacific_date: 2025-12-06
win_ratio: 0.51625
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:', '</s>', '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-v4a-lr2e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer to finish
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v4a-lr2e6g32-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-lr2e6g32-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: Downloaded to shared memory in 58.454s
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: Checking if ChaiML/kimid-v4a_lr2e6g32 already exists in ChaiML
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptd231i7s, device:0
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   6%|▋         | 23.0/363 [00:01<00:15, 22.3it/s]
Loading 0:   6%|▋         | 23.0/363 [00:01<00:15, 22.3it/s]
Loading 0:  13%|█▎        | 46.0/363 [00:02<00:14, 21.9it/s]
Loading 0:  13%|█▎        | 46.0/363 [00:02<00:14, 21.9it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:03<00:13, 21.5it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:03<00:13, 21.5it/s]
Loading 0:  25%|██▌       | 91.0/363 [00:04<00:12, 21.3it/s]
Loading 0:  25%|██▌       | 91.0/363 [00:04<00:12, 21.3it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:11, 21.1it/s] 
Loading 0:  31%|███       | 112/363 [00:05<00:11, 21.1it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:10, 21.5it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:10, 21.5it/s]
Loading 0:  41%|████▏     | 150/363 [00:07<00:11, 18.4it/s]
Loading 0:  41%|████▏     | 150/363 [00:07<00:11, 18.4it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:09, 19.3it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:09, 19.3it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:08, 19.2it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:08, 19.2it/s]
Loading 0:  53%|█████▎    | 192/363 [00:19<00:08, 19.2it/s]
Loading 0:  55%|█████▌    | 201/363 [00:24<00:50, 3.22it/s]
Loading 0:  55%|█████▌    | 201/363 [00:24<00:50, 3.22it/s]
Loading 0:  60%|██████    | 219/363 [00:25<00:33, 4.33it/s]
Loading 0:  60%|██████    | 219/363 [00:25<00:33, 4.33it/s]
Loading 0:  67%|██████▋   | 242/363 [00:26<00:19, 6.18it/s]
Loading 0:  67%|██████▋   | 242/363 [00:26<00:19, 6.18it/s]
Loading 0:  74%|███████▎  | 267/363 [00:27<00:11, 8.33it/s]
Loading 0:  74%|███████▎  | 267/363 [00:27<00:11, 8.33it/s]
Loading 0:  80%|███████▉  | 289/363 [00:28<00:07, 10.3it/s]
Loading 0:  80%|███████▉  | 289/363 [00:28<00:07, 10.3it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:04, 12.1it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:04, 12.1it/s]
Loading 0:  92%|█████████▏| 334/363 [00:30<00:02, 14.2it/s]
Loading 0:  92%|█████████▏| 334/363 [00:30<00:02, 14.2it/s]
Loading 0:  97%|█████████▋| 351/363 [00:31<00:00, 14.8it/s]
Loading 0:  97%|█████████▋| 351/363 [00:31<00:00, 14.8it/s]
Loading 0: 100%|██████████| 363/363 [00:32<00:00, 15.8it/s]
Loading 0: 100%|██████████| 363/363 [00:32<00:00, 15.8it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:32<00:00, 11.3it/s]
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmptd231i7s' 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-lr2e6g32-v1-mkmlizer: quantized model in 50.730s
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: Processed model ChaiML/kimid-v4a_lr2e6g32 in 109.185s
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g32-v1/nvidia
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g32-v1/nvidia/config.json
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g32-v1/nvidia/special_tokens_map.json
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g32-v1/nvidia/tokenizer_config.json
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g32-v1/nvidia/tokenizer.json
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g32-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g32-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer completed after 175.19s with status: succeeded
Stopping job with name chaiml-kimid-v4a-lr2e6g32-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.12s
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-v4a-lr2e6g32-v1
Waiting for inference service chaiml-kimid-v4a-lr2e6g32-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-kimid-v4a-lr2e6g32-v1 ready after 201.15736150741577s
Pipeline stage MKMLDeployer completed in 201.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.617607831954956s
Received healthy response to inference request in 2.58160662651062s
Received healthy response to inference request in 2.532278299331665s
Received healthy response to inference request in 2.6574230194091797s
Received healthy response to inference request in 2.5169317722320557s
5 requests
0 failed requests
5th percentile: 2.5200010776519775
10th percentile: 2.5230703830718992
20th percentile: 2.5292089939117433
30th percentile: 2.542143964767456
40th percentile: 2.5618752956390383
50th percentile: 2.58160662651062
60th percentile: 2.5960071086883545
70th percentile: 2.610407590866089
80th percentile: 2.625570869445801
90th percentile: 2.64149694442749
95th percentile: 2.649459981918335
99th percentile: 2.6558304119110105
mean time: 2.5811695098876952
Pipeline stage StressChecker completed in 14.09s
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 0.61s
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 0.63s
Shutdown handler de-registered
chaiml-kimid-v4a-lr2e6g32_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 0.09s
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-v4a-lr2e6g32-v1-profiler
Waiting for inference service chaiml-kimid-v4a-lr2e6g32-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 2705.06s
Shutdown handler de-registered