developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v3b-lr2e6g32_v1
model_name: training123
model_group: ChaiML/kimid-v3b_lr2e6g3
status: inactive
timestamp: 2025-12-06T04:55:57+00:00
num_battles: 6191
num_wins: 3230
celo_rating: 1311.52
family_friendly_score: 0.49760000000000004
family_friendly_standard_error: 0.007070986352695075
submission_type: basic
model_repo: ChaiML/kimid-v3b_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': 0.35154509407182016, 'latency_mean': 2.8445065665245055, 'latency_p50': 2.8261419534683228, 'latency_p90': 3.1217992305755615}, {'batch_size': 2, 'throughput': 0.5377160967418961, 'latency_mean': 3.717074967622757, 'latency_p50': 3.7293895483016968, 'latency_p90': 4.049119710922241}, {'batch_size': 3, 'throughput': 0.6686175285698003, 'latency_mean': 4.4785069453716275, 'latency_p50': 4.4845210313797, 'latency_p90': 5.050899791717529}, {'batch_size': 4, 'throughput': 0.7675514466636405, 'latency_mean': 5.184939377307892, 'latency_p50': 5.154089331626892, 'latency_p90': 5.71378321647644}, {'batch_size': 5, 'throughput': 0.8270926576883885, 'latency_mean': 6.0200716292858125, 'latency_p50': 5.99924373626709, 'latency_p90': 6.777766609191895}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v3b_lr2e6g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.54
us_pacific_date: 2025-12-05
win_ratio: 0.5217250848005168
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-v3b-lr2e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer to finish
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3b-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-v3b-lr2e6g32-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: Downloaded to shared memory in 66.505s
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: Checking if ChaiML/kimid-v3b_lr2e6g32 already exists in ChaiML
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkr4proos, device:0
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.6it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.6it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 25.9it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 25.9it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.7it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.7it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.1it/s] 
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.1it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.8it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.8it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.6it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.6it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:07, 24.7it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:07, 24.7it/s]
Loading 0:  52%|█████▏    | 189/363 [00:20<00:07, 24.7it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.46it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.46it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 5.96it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 5.96it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.60it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.60it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 10.7it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 10.7it/s]
Loading 0:  84%|████████▍ | 306/363 [00:24<00:04, 12.9it/s]
Loading 0:  84%|████████▍ | 306/363 [00:24<00:04, 12.9it/s]
Loading 0:  93%|█████████▎| 336/363 [00:25<00:01, 15.9it/s]
Loading 0:  93%|█████████▎| 336/363 [00:25<00:01, 15.9it/s]
Loading 0: 100%|█████████▉| 362/363 [00:27<00:00, 17.7it/s]
Loading 0: 100%|█████████▉| 362/363 [00:27<00:00, 17.7it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.7it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.4it/s]
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpkr4proos' 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-lr2e6g32-v1-mkmlizer: quantized model in 43.803s
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: Processed model ChaiML/kimid-v3b_lr2e6g32 in 110.308s
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g32-v1/nvidia
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g32-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g32-v1/nvidia/config.json
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g32-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g32-v1/nvidia/tokenizer.json
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g32-v1/nvidia/flywheel_model.0.safetensors
chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3b-lr2e6g32-v1/nvidia/flywheel_model.1.safetensors
Job chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer completed after 185.46s with status: succeeded
Stopping job with name chaiml-kimid-v3b-lr2e6g32-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.30s
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-v3b-lr2e6g32-v1
Waiting for inference service chaiml-kimid-v3b-lr2e6g32-v1 to be ready
Inference service chaiml-kimid-v3b-lr2e6g32-v1 ready after 190.81260633468628s
Pipeline stage MKMLDeployer completed in 191.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.758117437362671s
Received healthy response to inference request in 2.5731394290924072s
Received healthy response to inference request in 2.5764594078063965s
Received healthy response to inference request in 3.2999958992004395s
Received healthy response to inference request in 2.48880672454834s
5 requests
0 failed requests
5th percentile: 2.5056732654571534
10th percentile: 2.522539806365967
20th percentile: 2.5562728881835937
30th percentile: 2.573803424835205
40th percentile: 2.575131416320801
50th percentile: 2.5764594078063965
60th percentile: 2.649122619628906
70th percentile: 2.721785831451416
80th percentile: 2.8664931297302245
90th percentile: 3.083244514465332
95th percentile: 3.191620206832886
99th percentile: 3.278320760726929
mean time: 2.739303779602051
Pipeline stage StressChecker completed in 14.98s
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 0.60s
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 0.61s
Shutdown handler de-registered
chaiml-kimid-v3b-lr2e6g32_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 2808.71s
Shutdown handler de-registered