developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v3b-lr2e6g16_v1
model_name: training123
model_group: ChaiML/kimid-v3b_lr2e6g1
status: inactive
timestamp: 2025-12-06T04:57:50+00:00
num_battles: 6067
num_wins: 3216
celo_rating: 1312.71
family_friendly_score: 0.5116
family_friendly_standard_error: 0.007069164589963937
submission_type: basic
model_repo: ChaiML/kimid-v3b_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': 0.34931951893037316, 'latency_mean': 2.8626305294036865, 'latency_p50': 2.8402591943740845, 'latency_p90': 3.1119144678115847}, {'batch_size': 2, 'throughput': 0.5328365315904248, 'latency_mean': 3.7492607021331787, 'latency_p50': 3.758665680885315, 'latency_p90': 4.066878056526184}, {'batch_size': 3, 'throughput': 0.6618054677028687, 'latency_mean': 4.527849742174149, 'latency_p50': 4.523326754570007, 'latency_p90': 4.865251755714416}, {'batch_size': 4, 'throughput': 0.7590576696477976, 'latency_mean': 5.249499274492264, 'latency_p50': 5.238550782203674, 'latency_p90': 5.6869797706604}, {'batch_size': 5, 'throughput': 0.8178596007951792, 'latency_mean': 6.093293150663376, 'latency_p50': 6.071551203727722, 'latency_p90': 6.943043303489685}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v3b_lr2e6g16
model_size: 24B
ranking_group: single
throughput_3p7s: 0.53
us_pacific_date: 2025-12-05
win_ratio: 0.5300807647931433
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>', 'You:', '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-v3b-lr2e6g16-v1-mkmlizer
Waiting for job on chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer to finish
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3b-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-v3b-lr2e6g16-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: Downloaded to shared memory in 71.796s
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: Checking if ChaiML/kimid-v3b_lr2e6g16 already exists in ChaiML
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7jn9jpfu, device:0
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.2it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.2it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:02<00:11, 26.2it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:02<00:11, 26.2it/s]
Loading 0:  22%|██▏       | 79.0/363 [00:03<00:11, 24.0it/s]
Loading 0:  22%|██▏       | 79.0/363 [00:03<00:11, 24.0it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 24.8it/s] 
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 24.8it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.4it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.4it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 24.8it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 24.8it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 25.9it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 25.9it/s]
Loading 0:  51%|█████     | 186/363 [00:21<00:06, 25.9it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:35, 4.53it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:35, 4.53it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:23, 6.00it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:23, 6.00it/s]
Loading 0:  70%|██████▉   | 253/363 [00:23<00:13, 8.39it/s]
Loading 0:  70%|██████▉   | 253/363 [00:23<00:13, 8.39it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:08, 10.1it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:08, 10.1it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:04, 13.0it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:04, 13.0it/s]
Loading 0:  91%|█████████ | 329/363 [00:26<00:02, 14.9it/s]
Loading 0:  91%|█████████ | 329/363 [00:26<00:02, 14.9it/s]
Loading 0:  97%|█████████▋| 353/363 [00:27<00:00, 16.6it/s]
Loading 0:  97%|█████████▋| 353/363 [00:27<00:00, 16.6it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.5it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.5it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.1it/s]
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp7jn9jpfu' 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-v3b-lr2e6g16-v1-mkmlizer: quantized model in 44.610s
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: Processed model ChaiML/kimid-v3b_lr2e6g16 in 116.407s
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g16-v1/nvidia
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g16-v1/nvidia/config.json
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g16-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g16-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g16-v1/nvidia/tokenizer.json
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g16-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g16-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer completed after 197.24s with status: succeeded
Stopping job with name chaiml-kimid-v3b-lr2e6g16-v1-mkmlizer
Pipeline stage MKMLizer completed in 197.73s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.25s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v3b-lr2e6g16-v1
Waiting for inference service chaiml-kimid-v3b-lr2e6g16-v1 to be ready
Inference service chaiml-kimid-v3b-lr2e6g16-v1 ready after 190.68809533119202s
Pipeline stage MKMLDeployer completed in 191.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.773192882537842s
Received healthy response to inference request in 2.7886228561401367s
Received healthy response to inference request in 2.982300281524658s
Received healthy response to inference request in 1.9835715293884277s
Received healthy response to inference request in 2.0632026195526123s
5 requests
0 failed requests
5th percentile: 1.9994977474212647
10th percentile: 2.0154239654541017
20th percentile: 2.0472764015197753
30th percentile: 2.205200672149658
40th percentile: 2.48919677734375
50th percentile: 2.773192882537842
60th percentile: 2.7793648719787596
70th percentile: 2.785536861419678
80th percentile: 2.827358341217041
90th percentile: 2.9048293113708494
95th percentile: 2.943564796447754
99th percentile: 2.9745531845092774
mean time: 2.518178033828735
Pipeline stage StressChecker completed in 14.04s
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 0.66s
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 0.62s
Shutdown handler de-registered
chaiml-kimid-v3b-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-v3b-lr2e6g16-v1-profiler
Waiting for inference service chaiml-kimid-v3b-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 2827.55s
Shutdown handler de-registered