chaiml-kimid-v1-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v1-cosine_v1

model_name: training123

model_group: ChaiML/kimid-v1_cosine

status: inactive

timestamp: 2025-12-04T02:26:53+00:00

num_battles: 9150

num_wins: 4829

celo_rating: 1315.22

family_friendly_score: 0.5045999999999999

family_friendly_standard_error: 0.00707076855794333

submission_type: basic

model_repo: ChaiML/kimid-v1_cosine

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': 0.35221752841100806, 'latency_mean': 2.8390890407562255, 'latency_p50': 2.8373299837112427, 'latency_p90': 3.096428060531616}, {'batch_size': 2, 'throughput': 0.5361388544545376, 'latency_mean': 3.7206139016151427, 'latency_p50': 3.7397541999816895, 'latency_p90': 4.004176306724548}, {'batch_size': 3, 'throughput': 0.6737143267877339, 'latency_mean': 4.437571765184402, 'latency_p50': 4.441359996795654, 'latency_p90': 4.788835191726684}, {'batch_size': 4, 'throughput': 0.7740579623878595, 'latency_mean': 5.147714389562607, 'latency_p50': 5.149300217628479, 'latency_p90': 5.74600727558136}, {'batch_size': 5, 'throughput': 0.8391221252861115, 'latency_mean': 5.927757066488266, 'latency_p50': 5.948190689086914, 'latency_p90': 6.59031879901886}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v1_cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.53

us_pacific_date: 2025-12-03

win_ratio: 0.52775956284153

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-v1-mkmlizer
Waiting for job on chaiml-kimid-v1-cosine-v1-mkmlizer to finish
chaiml-kimid-v1-cosine-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v1-cosine-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v1-cosine-v1-mkmlizer: Downloaded to shared memory in 66.055s
chaiml-kimid-v1-cosine-v1-mkmlizer: Checking if ChaiML/kimid-v1_cosine already exists in ChaiML
chaiml-kimid-v1-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkqqhe36a, device:0
chaiml-kimid-v1-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v1-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.2it/s]
Loading 0:   9%|▉         | 32.0/363 [00:01<00:10, 31.2it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.2it/s]
Loading 0:  15%|█▌        | 55.0/363 [00:02<00:11, 26.2it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.8it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:03<00:11, 24.8it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.3it/s] 
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 25.3it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.4it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.4it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 24.8it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 24.8it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 25.5it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 25.5it/s]
Loading 0:  52%|█████▏    | 187/363 [00:20<00:06, 25.5it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:35, 4.51it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:35, 4.51it/s]
Loading 0:  61%|██████    | 222/363 [00:21<00:23, 5.88it/s]
Loading 0:  61%|██████    | 222/363 [00:21<00:23, 5.88it/s]
Loading 0:  67%|██████▋   | 244/363 [00:22<00:15, 7.55it/s]
Loading 0:  67%|██████▋   | 244/363 [00:22<00:15, 7.55it/s]
Loading 0:  74%|███████▍  | 270/363 [00:23<00:09, 9.80it/s]
Loading 0:  74%|███████▍  | 270/363 [00:23<00:09, 9.80it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:05, 12.7it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:05, 12.7it/s]
Loading 0:  89%|████████▉ | 323/363 [00:26<00:02, 14.7it/s]
Loading 0:  89%|████████▉ | 323/363 [00:26<00:02, 14.7it/s]
Loading 0:  94%|█████████▍| 343/363 [00:27<00:01, 15.8it/s]
Loading 0:  94%|█████████▍| 343/363 [00:27<00:01, 15.8it/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-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpkqqhe36a' 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-v1-mkmlizer: quantized model in 44.500s
chaiml-kimid-v1-cosine-v1-mkmlizer: Processed model ChaiML/kimid-v1_cosine in 110.555s
chaiml-kimid-v1-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v1-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v1-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v1/nvidia
chaiml-kimid-v1-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v1/nvidia/config.json
chaiml-kimid-v1-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v1/nvidia/special_tokens_map.json
chaiml-kimid-v1-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v1/nvidia/tokenizer_config.json
chaiml-kimid-v1-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v1/nvidia/tokenizer.json
chaiml-kimid-v1-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v1/nvidia/flywheel_model.1.safetensors
Job chaiml-kimid-v1-cosine-v1-mkmlizer completed after 163.36s with status: succeeded
Stopping job with name chaiml-kimid-v1-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 163.91s
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-v1-cosine-v1
Waiting for inference service chaiml-kimid-v1-cosine-v1 to be ready
Inference service chaiml-kimid-v1-cosine-v1 ready after 170.9204385280609s
Pipeline stage MKMLDeployer completed in 171.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.771653652191162s
Received healthy response to inference request in 2.6793670654296875s
Received healthy response to inference request in 2.5364155769348145s
Received healthy response to inference request in 2.3415892124176025s
Received healthy response to inference request in 2.3678395748138428s
5 requests
0 failed requests
5th percentile: 2.3468392848968507
10th percentile: 2.352089357376099
20th percentile: 2.3625895023345946
30th percentile: 2.4015547752380373
40th percentile: 2.468985176086426
50th percentile: 2.5364155769348145
60th percentile: 2.593596172332764
70th percentile: 2.650776767730713
80th percentile: 2.6978243827819823
90th percentile: 2.7347390174865724
95th percentile: 2.7531963348388673
99th percentile: 2.7679621887207033
mean time: 2.539373016357422
Pipeline stage StressChecker completed in 13.84s
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 0.68s
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 0.72s
Shutdown handler de-registered
chaiml-kimid-v1-cosine_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 2701.07s
Shutdown handler de-registered