chaiml-kimid-v4a-lr2e6g16

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v4a-lr2e6g16_v1

model_name: training123

model_group: ChaiML/kimid-v4a_lr2e6g1

status: inactive

timestamp: 2025-12-07T00:15:20+00:00

num_battles: 6428

num_wins: 3439

celo_rating: 1319.44

family_friendly_score: 0.503

family_friendly_standard_error: 0.007070940531499328

submission_type: basic

model_repo: ChaiML/kimid-v4a_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': 0.3477156403289286, 'latency_mean': 2.8758338952064513, 'latency_p50': 2.8743478059768677, 'latency_p90': 3.133284854888916}, {'batch_size': 2, 'throughput': 0.5270818321705916, 'latency_mean': 3.7902320408821106, 'latency_p50': 3.821569561958313, 'latency_p90': 4.098921489715576}, {'batch_size': 3, 'throughput': 0.6571851350705438, 'latency_mean': 4.541289570331574, 'latency_p50': 4.5455628633499146, 'latency_p90': 5.162352752685547}, {'batch_size': 4, 'throughput': 0.7523216944084317, 'latency_mean': 5.2987390851974485, 'latency_p50': 5.303540229797363, 'latency_p90': 5.995484924316406}, {'batch_size': 5, 'throughput': 0.8130877691197541, 'latency_mean': 6.120016640424728, 'latency_p50': 6.097461700439453, 'latency_p90': 6.943428611755371}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v4a_lr2e6g16

model_size: 24B

ranking_group: single

throughput_3p7s: 0.51

us_pacific_date: 2025-12-06

win_ratio: 0.5350031113876789

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:', 'You:', '</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-lr2e6g16-v1-mkmlizer
Waiting for job on chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer to finish
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v4a-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-v4a-lr2e6g16-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: Downloaded to shared memory in 66.499s
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: Checking if ChaiML/kimid-v4a_lr2e6g16 already exists in ChaiML
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptl4y2kv1, device:0
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.1it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.1it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.0it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.0it/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, 26.7it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.7it/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, 24.8it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:07, 24.8it/s]
Loading 0:  52%|█████▏    | 189/363 [00:20<00:07, 24.8it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.45it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:36, 4.45it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 5.97it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 5.97it/s]
Loading 0:  68%|██████▊   | 248/363 [00:22<00:14, 7.87it/s]
Loading 0:  68%|██████▊   | 248/363 [00:22<00:14, 7.87it/s]
Loading 0:  76%|███████▌  | 275/363 [00:23<00:08, 10.3it/s]
Loading 0:  76%|███████▌  | 275/363 [00:23<00:08, 10.3it/s]
Loading 0:  84%|████████▎ | 304/363 [00:24<00:04, 13.2it/s]
Loading 0:  84%|████████▎ | 304/363 [00:24<00:04, 13.2it/s]
Loading 0:  91%|█████████ | 329/363 [00:25<00:02, 15.3it/s]
Loading 0:  91%|█████████ | 329/363 [00:25<00:02, 15.3it/s]
Loading 0:  97%|█████████▋| 353/363 [00:26<00:00, 17.0it/s]
Loading 0:  97%|█████████▋| 353/363 [00:26<00:00, 17.0it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 18.1it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 18.1it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.3it/s]
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmptl4y2kv1' 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-lr2e6g16-v1-mkmlizer: quantized model in 43.946s
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: Processed model ChaiML/kimid-v4a_lr2e6g16 in 110.445s
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g16-v1/nvidia
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g16-v1/nvidia/config.json
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g16-v1/nvidia/special_tokens_map.json
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g16-v1/nvidia/tokenizer_config.json
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g16-v1/nvidia/tokenizer.json
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g16-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4a-lr2e6g16-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer completed after 185.99s with status: succeeded
Stopping job with name chaiml-kimid-v4a-lr2e6g16-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.47s
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-lr2e6g16-v1
Waiting for inference service chaiml-kimid-v4a-lr2e6g16-v1 to be ready
Inference service chaiml-kimid-v4a-lr2e6g16-v1 ready after 191.16431260108948s
Pipeline stage MKMLDeployer completed in 191.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7757527828216553s
Received healthy response to inference request in 3.1638574600219727s
Received healthy response to inference request in 2.8662946224212646s
Received healthy response to inference request in 2.7419393062591553s
Received healthy response to inference request in 3.1932919025421143s
5 requests
0 failed requests
5th percentile: 2.7487020015716555
10th percentile: 2.755464696884155
20th percentile: 2.768990087509155
30th percentile: 2.793861150741577
40th percentile: 2.830077886581421
50th percentile: 2.8662946224212646
60th percentile: 2.9853197574615478
70th percentile: 3.104344892501831
80th percentile: 3.169744348526001
90th percentile: 3.1815181255340574
95th percentile: 3.187405014038086
99th percentile: 3.1921145248413088
mean time: 2.9482272148132322
Pipeline stage StressChecker completed in 16.06s
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 0.72s
Shutdown handler de-registered
chaiml-kimid-v4a-lr2e6g16_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 2818.26s
Shutdown handler de-registered