developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v1_v1
model_name: training123
model_group: ChaiML/kimid-v1
status: inactive
timestamp: 2025-12-04T02:21:13+00:00
num_battles: 8344
num_wins: 4230
celo_rating: 1298.57
family_friendly_score: 0.5142
family_friendly_standard_error: 0.0070682156164056
submission_type: basic
model_repo: ChaiML/kimid-v1
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': 0.34827413615161823, 'latency_mean': 2.8712225162982943, 'latency_p50': 2.882623314857483, 'latency_p90': 3.1433951377868654}, {'batch_size': 2, 'throughput': 0.5389246131491724, 'latency_mean': 3.709173890352249, 'latency_p50': 3.6927125453948975, 'latency_p90': 4.013682961463928}, {'batch_size': 3, 'throughput': 0.6717704811267634, 'latency_mean': 4.454809638261795, 'latency_p50': 4.42543637752533, 'latency_p90': 4.88484570980072}, {'batch_size': 4, 'throughput': 0.7664885306050873, 'latency_mean': 5.208494683504105, 'latency_p50': 5.16510534286499, 'latency_p90': 5.949387073516846}, {'batch_size': 5, 'throughput': 0.8317654068976209, 'latency_mean': 5.98340145945549, 'latency_p50': 6.001071333885193, 'latency_p90': 6.680250740051269}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v1
model_size: 24B
ranking_group: single
throughput_3p7s: 0.54
us_pacific_date: 2025-12-03
win_ratio: 0.5069511025886865
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Starting job with name chaiml-kimid-v1-v1-mkmlizer
Waiting for job on chaiml-kimid-v1-v1-mkmlizer to finish
chaiml-kimid-v1-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v1-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v1-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-v1-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v1-v1-mkmlizer: ║ ║
chaiml-kimid-v1-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-kimid-v1-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-kimid-v1-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-kimid-v1-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-kimid-v1-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-kimid-v1-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-kimid-v1-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-kimid-v1-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-kimid-v1-v1-mkmlizer: ║ ║
chaiml-kimid-v1-v1-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-kimid-v1-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-kimid-v1-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-kimid-v1-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-kimid-v1-v1-mkmlizer: ║ ║
chaiml-kimid-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-kimid-v1-v1-mkmlizer: ║ belonging to: ║
chaiml-kimid-v1-v1-mkmlizer: ║ ║
chaiml-kimid-v1-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-kimid-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-kimid-v1-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-kimid-v1-v1-mkmlizer: ║ ║
chaiml-kimid-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v1-v1-mkmlizer: Downloaded to shared memory in 69.804s
chaiml-kimid-v1-v1-mkmlizer: Checking if ChaiML/kimid-v1 already exists in ChaiML
chaiml-kimid-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8hmb218m, device:0
chaiml-kimid-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v1-v1-mkmlizer: Loading 0: 0%| | 0.00/363 [00:00<?, ?it/s] Loading 0: 9%|▉ | 33.0/363 [00:01<00:11, 28.9it/s] Loading 0: 9%|▉ | 33.0/363 [00:01<00:11, 28.9it/s] Loading 0: 16%|█▋ | 59.0/363 [00:02<00:11, 26.5it/s] Loading 0: 16%|█▋ | 59.0/363 [00:02<00:11, 26.5it/s] Loading 0: 24%|██▎ | 86.0/363 [00:03<00:10, 26.7it/s] Loading 0: 24%|██▎ | 86.0/363 [00:03<00:10, 26.7it/s] Loading 0: 31%|███ | 112/363 [00:04<00:09, 26.1it/s] Loading 0: 31%|███ | 112/363 [00:04<00:09, 26.1it/s] Loading 0: 39%|███▊ | 140/363 [00:05<00:08, 25.9it/s] Loading 0: 39%|███▊ | 140/363 [00:05<00:08, 25.9it/s] Loading 0: 46%|████▌ | 166/363 [00:06<00:07, 25.9it/s] Loading 0: 46%|████▌ | 166/363 [00:06<00:07, 25.9it/s] Loading 0: 52%|█████▏ | 189/363 [00:07<00:06, 24.9it/s] Loading 0: 52%|█████▏ | 189/363 [00:07<00:06, 24.9it/s] Loading 0: 52%|█████▏ | 189/363 [00:20<00:06, 24.9it/s] Loading 0: 55%|█████▌ | 201/363 [00:20<00:37, 4.31it/s] Loading 0: 55%|█████▌ | 201/363 [00:20<00:37, 4.31it/s] Loading 0: 62%|██████▏ | 224/363 [00:21<00:23, 5.83it/s] Loading 0: 62%|██████▏ | 224/363 [00:21<00:23, 5.83it/s] Loading 0: 70%|███████ | 255/363 [00:22<00:12, 8.48it/s] Loading 0: 70%|███████ | 255/363 [00:22<00:12, 8.48it/s] Loading 0: 77%|███████▋ | 280/363 [00:23<00:07, 10.6it/s] Loading 0: 77%|███████▋ | 280/363 [00:23<00:07, 10.6it/s] Loading 0: 84%|████████▍ | 306/363 [00:25<00:04, 12.7it/s] Loading 0: 84%|████████▍ | 306/363 [00:25<00:04, 12.7it/s] Loading 0: 91%|█████████ | 329/363 [00:26<00:02, 14.5it/s] Loading 0: 91%|█████████ | 329/363 [00:26<00:02, 14.5it/s] Loading 0: 97%|█████████▋| 353/363 [00:27<00:00, 16.3it/s] Loading 0: 97%|█████████▋| 353/363 [00:27<00:00, 16.3it/s] Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.3it/s] Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.3it/s] Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.2it/s]
chaiml-kimid-v1-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp8hmb218m' 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-v1-mkmlizer: quantized model in 44.235s
chaiml-kimid-v1-v1-mkmlizer: Processed model ChaiML/kimid-v1 in 114.040s
chaiml-kimid-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v1-v1/nvidia
chaiml-kimid-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v1-v1/nvidia/config.json
chaiml-kimid-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v1-v1/nvidia/special_tokens_map.json
chaiml-kimid-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v1-v1/nvidia/tokenizer_config.json
chaiml-kimid-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v1-v1/nvidia/tokenizer.json
chaiml-kimid-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v1-v1/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v1-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v1-v1-mkmlizer completed after 195.02s with status: succeeded
Stopping job with name chaiml-kimid-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 196.57s
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-v1-v1
Waiting for inference service chaiml-kimid-v1-v1 to be ready
Inference service chaiml-kimid-v1-v1 ready after 180.84453868865967s
Pipeline stage MKMLDeployer completed in 181.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.580289125442505s
Received healthy response to inference request in 2.685333490371704s
Received healthy response to inference request in 2.7209391593933105s
Received healthy response to inference request in 2.33305287361145s
Received healthy response to inference request in 2.6846585273742676s
5 requests
0 failed requests
5th percentile: 2.3825001239776613
10th percentile: 2.431947374343872
20th percentile: 2.5308418750762938
30th percentile: 2.6011630058288575
40th percentile: 2.6429107666015623
50th percentile: 2.6846585273742676
60th percentile: 2.6849285125732423
70th percentile: 2.685198497772217
80th percentile: 2.692454624176025
90th percentile: 2.706696891784668
95th percentile: 2.7138180255889894
99th percentile: 2.719514932632446
mean time: 2.6008546352386475
Pipeline stage StressChecker completed in 14.53s
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 0.95s
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_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 2617.69s
Shutdown handler de-registered