developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v3a-lr2e6g16_v1
model_name: training123
model_group: ChaiML/kimid-v3a_lr2e6g1
status: inactive
timestamp: 2025-12-05T23:13:33+00:00
num_battles: 7091
num_wins: 3709
celo_rating: 1308.04
family_friendly_score: 0.5058
family_friendly_standard_error: 0.007070592054418074
submission_type: basic
model_repo: ChaiML/kimid-v3a_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': 0.35391505605869955, 'latency_mean': 2.825458446741104, 'latency_p50': 2.802824854850769, 'latency_p90': 3.0909129858016966}, {'batch_size': 2, 'throughput': 0.5350288223175447, 'latency_mean': 3.7329487800598145, 'latency_p50': 3.739582061767578, 'latency_p90': 4.0132132291793825}, {'batch_size': 3, 'throughput': 0.6697294637014023, 'latency_mean': 4.456455470323562, 'latency_p50': 4.43087100982666, 'latency_p90': 4.9319659709930415}, {'batch_size': 4, 'throughput': 0.7618761186707087, 'latency_mean': 5.226957249641418, 'latency_p50': 5.23707127571106, 'latency_p90': 5.7744361639022825}, {'batch_size': 5, 'throughput': 0.8315435139383768, 'latency_mean': 5.9909291684627535, 'latency_p50': 5.969824194908142, 'latency_p90': 6.7573979139328}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v3a_lr2e6g16
model_size: 24B
ranking_group: single
throughput_3p7s: 0.53
us_pacific_date: 2025-12-05
win_ratio: 0.5230573967000423
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:', '</s>', 'User:'], '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-v3a-lr2e6g16-v1-mkmlizer
Waiting for job on chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer to finish
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3a-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-v3a-lr2e6g16-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: Downloaded to shared memory in 102.270s
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: Checking if ChaiML/kimid-v3a_lr2e6g16 already exists in ChaiML
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa1lqkzu8, device:0
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.2it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.2it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.3it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.3it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.8it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.8it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.4it/s] 
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.4it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.2it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.2it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.3it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.3it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:06, 25.5it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:06, 25.5it/s]
Loading 0:  52%|█████▏    | 189/363 [00:20<00:06, 25.5it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.43it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.43it/s]
Loading 0:  61%|██████    | 220/363 [00:21<00:25, 5.65it/s]
Loading 0:  61%|██████    | 220/363 [00:21<00:25, 5.65it/s]
Loading 0:  68%|██████▊   | 247/363 [00:22<00:14, 7.92it/s]
Loading 0:  68%|██████▊   | 247/363 [00:22<00:14, 7.92it/s]
Loading 0:  75%|███████▌  | 273/363 [00:23<00:08, 10.2it/s]
Loading 0:  75%|███████▌  | 273/363 [00:23<00:08, 10.2it/s]
Loading 0:  83%|████████▎ | 303/363 [00:24<00:04, 13.3it/s]
Loading 0:  83%|████████▎ | 303/363 [00:24<00:04, 13.3it/s]
Loading 0:  90%|█████████ | 328/363 [00:25<00:02, 15.3it/s]
Loading 0:  90%|█████████ | 328/363 [00:25<00:02, 15.3it/s]
Loading 0:  96%|█████████▌| 348/363 [00:26<00:00, 16.1it/s]
Loading 0:  96%|█████████▌| 348/363 [00:26<00:00, 16.1it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.9it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.9it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.3it/s]
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpa1lqkzu8' 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-v3a-lr2e6g16-v1-mkmlizer: quantized model in 44.319s
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: Processed model ChaiML/kimid-v3a_lr2e6g16 in 146.589s
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3a-lr2e6g16-v1/nvidia
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3a-lr2e6g16-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3a-lr2e6g16-v1/nvidia/config.json
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3a-lr2e6g16-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3a-lr2e6g16-v1/nvidia/tokenizer.json
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3a-lr2e6g16-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3a-lr2e6g16-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer completed after 225.92s with status: succeeded
Stopping job with name chaiml-kimid-v3a-lr2e6g16-v1-mkmlizer
Pipeline stage MKMLizer completed in 226.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v3a-lr2e6g16-v1
Waiting for inference service chaiml-kimid-v3a-lr2e6g16-v1 to be ready
Inference service chaiml-kimid-v3a-lr2e6g16-v1 ready after 190.93258571624756s
Pipeline stage MKMLDeployer completed in 191.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6470718383789062s
Received healthy response to inference request in 2.572176694869995s
Received healthy response to inference request in 3.127985954284668s
Received healthy response to inference request in 2.5895044803619385s
Received healthy response to inference request in 3.0980887413024902s
5 requests
0 failed requests
5th percentile: 2.5756422519683837
10th percentile: 2.5791078090667723
20th percentile: 2.58603892326355
30th percentile: 2.601017951965332
40th percentile: 2.624044895172119
50th percentile: 2.6470718383789062
60th percentile: 2.82747859954834
70th percentile: 3.0078853607177733
80th percentile: 3.1040681838989257
90th percentile: 3.116027069091797
95th percentile: 3.1220065116882325
99th percentile: 3.126790065765381
mean time: 2.8069655418396
Pipeline stage StressChecker completed in 17.42s
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 0.74s
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 0.64s
Shutdown handler de-registered
chaiml-kimid-v3a-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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-kimid-v3a-lr2e6g16-v1-profiler
Waiting for inference service chaiml-kimid-v3a-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 2735.95s
Shutdown handler de-registered