developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v3b-lr5e6g32_v1
model_name: training123
model_group: ChaiML/kimid-v3b_lr5e6g3
status: inactive
timestamp: 2025-12-05T21:54:39+00:00
num_battles: 8304
num_wins: 4346
celo_rating: 1309.58
family_friendly_score: 0.49839999999999995
family_friendly_standard_error: 0.007071031607905596
submission_type: basic
model_repo: ChaiML/kimid-v3b_lr5e6g32
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': 0.3473493734590514, 'latency_mean': 2.878865442276001, 'latency_p50': 2.8652853965759277, 'latency_p90': 3.128660202026367}, {'batch_size': 2, 'throughput': 0.5333653207253384, 'latency_mean': 3.7438929045200346, 'latency_p50': 3.737955331802368, 'latency_p90': 4.067068648338318}, {'batch_size': 3, 'throughput': 0.6682473974765634, 'latency_mean': 4.472754349708557, 'latency_p50': 4.470449447631836, 'latency_p90': 4.867685079574585}, {'batch_size': 4, 'throughput': 0.7632756940506372, 'latency_mean': 5.223052978515625, 'latency_p50': 5.232908248901367, 'latency_p90': 5.945830011367797}, {'batch_size': 5, 'throughput': 0.8244670295191555, 'latency_mean': 6.03361781001091, 'latency_p50': 6.047250747680664, 'latency_p90': 6.900476503372192}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v3b_lr5e6g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.53
us_pacific_date: 2025-12-05
win_ratio: 0.5233622350674374
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-v3b-lr5e6g32-v1-mkmlizer
Waiting for job on chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer to finish
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v3b-lr5e6g32-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-lr5e6g32-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: Downloaded to shared memory in 94.198s
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: Checking if ChaiML/kimid-v3b_lr5e6g32 already exists in ChaiML
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8b3d5aa6, device:0
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.8it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.8it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:12, 25.3it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:12, 25.3it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.3it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.3it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 24.6it/s] 
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 24.6it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.5it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.5it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.9it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.9it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:06, 25.4it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:06, 25.4it/s]
Loading 0:  52%|█████▏    | 189/363 [00:20<00:06, 25.4it/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:  61%|██████    | 221/363 [00:21<00:24, 5.77it/s]
Loading 0:  61%|██████    | 221/363 [00:21<00:24, 5.77it/s]
Loading 0:  68%|██████▊   | 248/363 [00:22<00:14, 7.97it/s]
Loading 0:  68%|██████▊   | 248/363 [00:22<00:14, 7.97it/s]
Loading 0:  76%|███████▌  | 275/363 [00:23<00:08, 10.4it/s]
Loading 0:  76%|███████▌  | 275/363 [00:23<00:08, 10.4it/s]
Loading 0:  84%|████████▎ | 304/363 [00:24<00:04, 13.3it/s]
Loading 0:  84%|████████▎ | 304/363 [00:24<00:04, 13.3it/s]
Loading 0:  91%|█████████▏| 332/363 [00:25<00:01, 16.0it/s]
Loading 0:  91%|█████████▏| 332/363 [00:25<00:01, 16.0it/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, 18.0it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 18.0it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.4it/s]
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp8b3d5aa6' 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-lr5e6g32-v1-mkmlizer: quantized model in 43.955s
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: Processed model ChaiML/kimid-v3b_lr5e6g32 in 138.154s
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v3b-lr5e6g32-v1/nvidia
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr5e6g32-v1/nvidia/config.json
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr5e6g32-v1/nvidia/special_tokens_map.json
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr5e6g32-v1/nvidia/tokenizer_config.json
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v3b-lr5e6g32-v1/nvidia/tokenizer.json
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3b-lr5e6g32-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v3b-lr5e6g32-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer completed after 256.22s with status: succeeded
Stopping job with name chaiml-kimid-v3b-lr5e6g32-v1-mkmlizer
Pipeline stage MKMLizer completed in 256.72s
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-lr5e6g32-v1
Waiting for inference service chaiml-kimid-v3b-lr5e6g32-v1 to be ready
Inference service chaiml-kimid-v3b-lr5e6g32-v1 ready after 192.19234466552734s
Pipeline stage MKMLDeployer completed in 192.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7749290466308594s
Received healthy response to inference request in 2.575176477432251s
Received healthy response to inference request in 2.677755832672119s
Received healthy response to inference request in 2.6564362049102783s
Received healthy response to inference request in 2.3473563194274902s
5 requests
0 failed requests
5th percentile: 2.3929203510284425
10th percentile: 2.4384843826293947
20th percentile: 2.5296124458312987
30th percentile: 2.5914284229278564
40th percentile: 2.6239323139190676
50th percentile: 2.6564362049102783
60th percentile: 2.6649640560150147
70th percentile: 2.673491907119751
80th percentile: 2.6971904754638674
90th percentile: 2.7360597610473634
95th percentile: 2.755494403839111
99th percentile: 2.7710421180725096
mean time: 2.6063307762145995
Pipeline stage StressChecker completed in 14.26s
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 0.77s
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-lr5e6g32_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-lr5e6g32-v1-profiler
Waiting for inference service chaiml-kimid-v3b-lr5e6g32-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 2764.11s
Shutdown handler de-registered