developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v1-cosine-lr5e6_v1
model_name: training123
model_group: ChaiML/kimid-v1_cosine-l
status: inactive
timestamp: 2025-12-04T02:25:23+00:00
num_battles: 10207
num_wins: 5047
celo_rating: 1292.86
family_friendly_score: 0.5048
family_friendly_standard_error: 0.007070741969553125
submission_type: basic
model_repo: ChaiML/kimid-v1_cosine-lr5e6
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': 0.34729421142031763, 'latency_mean': 2.8793384432792664, 'latency_p50': 2.872356414794922, 'latency_p90': 3.121711826324463}, {'batch_size': 2, 'throughput': 0.5283690032984515, 'latency_mean': 3.7800784957408906, 'latency_p50': 3.7779442071914673, 'latency_p90': 4.071254682540894}, {'batch_size': 3, 'throughput': 0.662159053820434, 'latency_mean': 4.524006758928299, 'latency_p50': 4.514127612113953, 'latency_p90': 4.855529808998107}, {'batch_size': 4, 'throughput': 0.7483890652123819, 'latency_mean': 5.332320632934571, 'latency_p50': 5.342805981636047, 'latency_p90': 6.006705355644226}, {'batch_size': 5, 'throughput': 0.8096841092263112, 'latency_mean': 6.161336984634399, 'latency_p50': 6.130086183547974, 'latency_p90': 6.940693306922912}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v1_cosine-lr5e6
model_size: 24B
ranking_group: single
throughput_3p7s: 0.52
us_pacific_date: 2025-12-03
win_ratio: 0.49446458312922503
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:', '</s>', '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-v1-cosine-lr5e6-v1-mkmlizer
Waiting for job on chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer to finish
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v1-cosine-lr5e6-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-v1-cosine-lr5e6-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: Downloaded to shared memory in 54.167s
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: Checking if ChaiML/kimid-v1_cosine-lr5e6 already exists in ChaiML
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6cetd5h0, device:0
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:11, 30.0it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:11, 30.0it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:12, 25.2it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:12, 25.2it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.2it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.2it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 24.9it/s] 
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 24.9it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.3it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.3it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 24.3it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 24.3it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 25.8it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 25.8it/s]
Loading 0:  51%|█████     | 186/363 [00:20<00:06, 25.8it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:35, 4.50it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:35, 4.50it/s]
Loading 0:  61%|██████▏   | 223/363 [00:21<00:23, 5.94it/s]
Loading 0:  61%|██████▏   | 223/363 [00:21<00:23, 5.94it/s]
Loading 0:  68%|██████▊   | 248/363 [00:23<00:14, 7.93it/s]
Loading 0:  68%|██████▊   | 248/363 [00:23<00:14, 7.93it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:08, 10.3it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:08, 10.3it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:04, 13.2it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:04, 13.2it/s]
Loading 0:  90%|█████████ | 328/363 [00:26<00:02, 15.1it/s]
Loading 0:  90%|█████████ | 328/363 [00:26<00:02, 15.1it/s]
Loading 0:  96%|█████████▌| 348/363 [00:27<00:00, 15.9it/s]
Loading 0:  96%|█████████▌| 348/363 [00:27<00:00, 15.9it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.9it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.9it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.1it/s]
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp6cetd5h0' 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-v1-cosine-lr5e6-v1-mkmlizer: quantized model in 44.373s
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: Processed model ChaiML/kimid-v1_cosine-lr5e6 in 98.541s
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-lr5e6-v1/nvidia
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-lr5e6-v1/nvidia/config.json
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-lr5e6-v1/nvidia/special_tokens_map.json
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-lr5e6-v1/nvidia/tokenizer_config.json
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-lr5e6-v1/nvidia/tokenizer.json
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-lr5e6-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-lr5e6-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer completed after 175.67s with status: succeeded
Stopping job with name chaiml-kimid-v1-cosine-lr5e6-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v1-cosine-lr5e6-v1
Waiting for inference service chaiml-kimid-v1-cosine-lr5e6-v1 to be ready
Inference service chaiml-kimid-v1-cosine-lr5e6-v1 ready after 180.9054615497589s
Pipeline stage MKMLDeployer completed in 181.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.749744176864624s
Received healthy response to inference request in 2.608569860458374s
Received healthy response to inference request in 2.814319610595703s
Received healthy response to inference request in 2.644796133041382s
Received healthy response to inference request in 2.670172929763794s
5 requests
0 failed requests
5th percentile: 2.6158151149749758
10th percentile: 2.623060369491577
20th percentile: 2.63755087852478
30th percentile: 2.649871492385864
40th percentile: 2.6600222110748293
50th percentile: 2.670172929763794
60th percentile: 2.702001428604126
70th percentile: 2.733829927444458
80th percentile: 2.76265926361084
90th percentile: 2.7884894371032716
95th percentile: 2.801404523849487
99th percentile: 2.8117365932464597
mean time: 2.697520542144775
Pipeline stage StressChecker completed in 14.99s
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 0.69s
Shutdown handler de-registered
chaiml-kimid-v1-cosine-lr5e6_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-kimid-v1-cosine-lr5e6-v1-profiler
Waiting for inference service chaiml-kimid-v1-cosine-lr5e6-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 2697.63s
Shutdown handler de-registered