developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v3-lr2e6g32_v1
model_name: training123
model_group: ChaiML/kimid-v3_lr2e6g32
status: inactive
timestamp: 2025-12-05T18:36:33+00:00
num_battles: 20279
num_wins: 10568
celo_rating: 1307.77
family_friendly_score: 0.5114000000000001
family_friendly_standard_error: 0.007069229661002675
submission_type: basic
model_repo: ChaiML/kimid-v3_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': 0.34875687444383874, 'latency_mean': 2.8672607934474943, 'latency_p50': 2.8674793243408203, 'latency_p90': 3.145142602920532}, {'batch_size': 2, 'throughput': 0.5294966643127466, 'latency_mean': 3.7754089546203615, 'latency_p50': 3.772610068321228, 'latency_p90': 4.043659734725952}, {'batch_size': 3, 'throughput': 0.6666468064608677, 'latency_mean': 4.483665704727173, 'latency_p50': 4.479667544364929, 'latency_p90': 4.9178780794143675}, {'batch_size': 4, 'throughput': 0.7585495149840238, 'latency_mean': 5.258379105329514, 'latency_p50': 5.259100317955017, 'latency_p90': 5.985551285743713}, {'batch_size': 5, 'throughput': 0.8223780365546738, 'latency_mean': 6.057837913036346, 'latency_p50': 6.110453248023987, 'latency_p90': 6.892748236656189}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v3_lr2e6g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.52
us_pacific_date: 2025-12-05
win_ratio: 0.5211302332462153
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>', 'User:', '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-v3-lr2e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v3-lr2e6g32-v1-mkmlizer to finish
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3-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-v3-lr2e6g32-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: Downloaded to shared memory in 56.195s
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: Checking if ChaiML/kimid-v3_lr2e6g32 already exists in ChaiML
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1rkej9fv, device:0
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 22.0/363 [00:01<00:17, 19.1it/s]
Loading 0:   6%|▌         | 22.0/363 [00:01<00:17, 19.1it/s]
Loading 0:  11%|█         | 39.0/363 [00:02<00:18, 17.4it/s]
Loading 0:  11%|█         | 39.0/363 [00:02<00:18, 17.4it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:03<00:18, 16.7it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:03<00:18, 16.7it/s]
Loading 0:  21%|██▏       | 78.0/363 [00:04<00:15, 18.7it/s]
Loading 0:  21%|██▏       | 78.0/363 [00:04<00:15, 18.7it/s]
Loading 0:  24%|██▍       | 87.0/363 [00:05<00:18, 14.9it/s]
Loading 0:  24%|██▍       | 87.0/363 [00:05<00:18, 14.9it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:14, 17.8it/s] 
Loading 0:  31%|███       | 111/363 [00:06<00:14, 17.8it/s]
Loading 0:  37%|███▋      | 136/363 [00:07<00:11, 19.8it/s]
Loading 0:  37%|███▋      | 136/363 [00:07<00:11, 19.8it/s]
Loading 0:  43%|████▎     | 157/363 [00:08<00:10, 20.1it/s]
Loading 0:  43%|████▎     | 157/363 [00:08<00:10, 20.1it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:08, 21.3it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:08, 21.3it/s]
Loading 0:  50%|█████     | 182/363 [00:20<00:08, 21.3it/s]
Loading 0:  55%|█████▌    | 201/363 [00:24<00:40, 3.97it/s]
Loading 0:  55%|█████▌    | 201/363 [00:24<00:40, 3.97it/s]
Loading 0:  60%|██████    | 219/363 [00:25<00:28, 5.03it/s]
Loading 0:  60%|██████    | 219/363 [00:25<00:28, 5.03it/s]
Loading 0:  67%|██████▋   | 242/363 [00:26<00:17, 6.78it/s]
Loading 0:  67%|██████▋   | 242/363 [00:26<00:17, 6.78it/s]
Loading 0:  74%|███████▎  | 267/363 [00:27<00:10, 8.88it/s]
Loading 0:  74%|███████▎  | 267/363 [00:27<00:10, 8.88it/s]
Loading 0:  80%|████████  | 291/363 [00:28<00:06, 11.0it/s]
Loading 0:  80%|████████  | 291/363 [00:28<00:06, 11.0it/s]
Loading 0:  86%|████████▌ | 311/363 [00:29<00:04, 12.3it/s]
Loading 0:  86%|████████▌ | 311/363 [00:29<00:04, 12.3it/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:  96%|█████████▌| 348/363 [00:32<00:01, 13.3it/s]
Loading 0:  96%|█████████▌| 348/363 [00:32<00:01, 13.3it/s]
Loading 0: 100%|██████████| 363/363 [00:32<00:00, 15.1it/s]
Loading 0: 100%|██████████| 363/363 [00:32<00:00, 15.1it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:32<00:00, 11.1it/s]
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp1rkej9fv' 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-v3-lr2e6g32-v1-mkmlizer: quantized model in 51.323s
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: Processed model ChaiML/kimid-v3_lr2e6g32 in 107.518s
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g32-v1/nvidia
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g32-v1/nvidia/config.json
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g32-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g32-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g32-v1/nvidia/tokenizer.json
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g32-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3-lr2e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3-lr2e6g32-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3-lr2e6g32-v1-mkmlizer completed after 187.14s with status: succeeded
Stopping job with name chaiml-kimid-v3-lr2e6g32-v1-mkmlizer
Pipeline stage MKMLizer completed in 187.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v3-lr2e6g32-v1
Waiting for inference service chaiml-kimid-v3-lr2e6g32-v1 to be ready
Inference service chaiml-kimid-v3-lr2e6g32-v1 ready after 181.19678044319153s
Pipeline stage MKMLDeployer completed in 182.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.746800661087036s
Received healthy response to inference request in 3.6763226985931396s
Received healthy response to inference request in 2.610205888748169s
Received healthy response to inference request in 2.4452946186065674s
Received healthy response to inference request in 2.531500816345215s
5 requests
0 failed requests
5th percentile: 2.462535858154297
10th percentile: 2.4797770977020264
20th percentile: 2.5142595767974854
30th percentile: 2.5472418308258056
40th percentile: 2.5787238597869875
50th percentile: 2.610205888748169
60th percentile: 2.664843797683716
70th percentile: 2.7194817066192627
80th percentile: 2.932705068588257
90th percentile: 3.3045138835906984
95th percentile: 3.4904182910919186
99th percentile: 3.6391418170928955
mean time: 2.8020249366760255
Pipeline stage StressChecker completed in 15.55s
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 0.64s
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 0.88s
Shutdown handler de-registered
chaiml-kimid-v3-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 0.18s
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-v3-lr2e6g32-v1-profiler
Waiting for inference service chaiml-kimid-v3-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 2666.79s
Shutdown handler de-registered
chaiml-kimid-v3-lr2e6g32_v1 status is now inactive due to auto deactivation removed underperforming models