chaiml-kimid-v2-cosine-_80852

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v2-cosine-_80852_v1

model_name: training123

model_group: ChaiML/kimid-v2_cosine-l

status: inactive

timestamp: 2025-12-04T13:16:30+00:00

num_battles: 9399

num_wins: 4914

celo_rating: 1311.76

family_friendly_score: 0.5022

family_friendly_standard_error: 0.007070999363597765

submission_type: basic

model_repo: ChaiML/kimid-v2_cosine-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': 0.41233459660193594, 'latency_mean': 2.4251364612579347, 'latency_p50': 2.422800660133362, 'latency_p90': 2.6359658002853394}, {'batch_size': 2, 'throughput': 0.6324642649096733, 'latency_mean': 3.1508120906353, 'latency_p50': 3.1449650526046753, 'latency_p90': 3.4266876220703124}, {'batch_size': 3, 'throughput': 0.7832710070467432, 'latency_mean': 3.821304259300232, 'latency_p50': 3.851417064666748, 'latency_p90': 4.164138984680176}, {'batch_size': 4, 'throughput': 0.8826326205436207, 'latency_mean': 4.5269377124309536, 'latency_p50': 4.5171942710876465, 'latency_p90': 4.976175355911255}, {'batch_size': 5, 'throughput': 0.953951567004228, 'latency_mean': 5.216737215518951, 'latency_p50': 5.235172152519226, 'latency_p90': 5.758125114440918}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v2_cosine-lr2e6g16

model_size: 24B

ranking_group: single

throughput_3p7s: 0.76

us_pacific_date: 2025-12-04

win_ratio: 0.5228215767634855

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-v2-cosine-80852-v1-mkmlizer
Waiting for job on chaiml-kimid-v2-cosine-80852-v1-mkmlizer to finish
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v2-cosine-80852-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-v2-cosine-80852-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: Downloaded to shared memory in 80.446s
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: Checking if ChaiML/kimid-v2_cosine-lr2e6g16 already exists in ChaiML
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe0filyqk, device:0
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.4it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:11, 29.4it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:02<00:11, 26.3it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:02<00:11, 26.3it/s]
Loading 0:  20%|██        | 73.0/363 [00:03<00:14, 19.6it/s]
Loading 0:  20%|██        | 73.0/363 [00:03<00:14, 19.6it/s]
Loading 0:  27%|██▋       | 97.0/363 [00:04<00:12, 21.1it/s]
Loading 0:  27%|██▋       | 97.0/363 [00:04<00:12, 21.1it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.4it/s] 
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.4it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 24.7it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 24.7it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 25.5it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 25.5it/s]
Loading 0:  50%|████▉     | 181/363 [00:21<00:07, 25.5it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:33, 4.89it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<00:33, 4.89it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21, 6.33it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21, 6.33it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:12, 8.90it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:12, 8.90it/s]
Loading 0:  77%|███████▋  | 280/363 [00:24<00:07, 10.9it/s]
Loading 0:  77%|███████▋  | 280/363 [00:24<00:07, 10.9it/s]
Loading 0:  84%|████████▍ | 306/363 [00:25<00:04, 13.1it/s]
Loading 0:  84%|████████▍ | 306/363 [00:25<00:04, 13.1it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:01, 16.0it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:01, 16.0it/s]
Loading 0:  98%|█████████▊| 357/363 [00:27<00:00, 16.9it/s]
Loading 0:  98%|█████████▊| 357/363 [00:27<00:00, 16.9it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.8it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.8it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.2it/s]
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpe0filyqk' 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-v2-cosine-80852-v1-mkmlizer: quantized model in 44.426s
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: Processed model ChaiML/kimid-v2_cosine-lr2e6g16 in 124.872s
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-80852-v1/nvidia
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-80852-v1/nvidia/config.json
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-80852-v1/nvidia/special_tokens_map.json
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-80852-v1/nvidia/tokenizer_config.json
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-80852-v1/nvidia/tokenizer.json
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-80852-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v2-cosine-80852-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-80852-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v2-cosine-80852-v1-mkmlizer completed after 185.71s with status: succeeded
Stopping job with name chaiml-kimid-v2-cosine-80852-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.21s
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-v2-cosine-80852-v1
Waiting for inference service chaiml-kimid-v2-cosine-80852-v1 to be ready
Inference service chaiml-kimid-v2-cosine-80852-v1 ready after 170.78317618370056s
Pipeline stage MKMLDeployer completed in 171.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0963690280914307s
Received healthy response to inference request in 2.9759299755096436s
Received healthy response to inference request in 2.5021331310272217s
Received healthy response to inference request in 2.1884641647338867s
Received healthy response to inference request in 2.2310004234313965s
5 requests
0 failed requests
5th percentile: 2.1969714164733887
10th percentile: 2.2054786682128906
20th percentile: 2.2224931716918945
30th percentile: 2.2852269649505614
40th percentile: 2.393680047988892
50th percentile: 2.5021331310272217
60th percentile: 2.6916518688201903
70th percentile: 2.8811706066131593
80th percentile: 3.000017786026001
90th percentile: 3.048193407058716
95th percentile: 3.0722812175750733
99th percentile: 3.091551465988159
mean time: 2.5987793445587157
Pipeline stage StressChecker completed in 14.40s
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 0.74s
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 0.66s
Shutdown handler de-registered
chaiml-kimid-v2-cosine-_80852_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 2763.50s
Shutdown handler de-registered
chaiml-kimid-v2-cosine-_80852_v1 status is now inactive due to auto deactivation removed underperforming models