chaiml-1103-quang-ir-mi_56939

developer_uid: chai_backend_admin

submission_id: chaiml-1103-quang-ir-mi_56939_v1

model_name: training123

model_group: ChaiML/1103-quang-ir-mix

status: torndown

timestamp: 2025-11-07T02:51:16+00:00

num_battles: 6908

num_wins: 3536

celo_rating: 1294.05

family_friendly_score: 0.49339999999999995

family_friendly_standard_error: 0.0070704517536010385

submission_type: basic

model_repo: ChaiML/1103-quang-ir-mixallnov3-cld-i8a9-onlyh3

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.38142528093599554, 'latency_mean': 2.6216202461719513, 'latency_p50': 2.6045058965682983, 'latency_p90': 2.890295076370239}, {'batch_size': 2, 'throughput': 0.5716332611924205, 'latency_mean': 3.494771616458893, 'latency_p50': 3.4644054174423218, 'latency_p90': 3.8098784923553466}, {'batch_size': 3, 'throughput': 0.7011325500645617, 'latency_mean': 4.264289671182633, 'latency_p50': 4.281623840332031, 'latency_p90': 4.656611824035644}, {'batch_size': 4, 'throughput': 0.7940577464716791, 'latency_mean': 5.025362468957901, 'latency_p50': 5.0430588722229, 'latency_p90': 5.530043601989746}, {'batch_size': 5, 'throughput': 0.8553814927358464, 'latency_mean': 5.823290790319443, 'latency_p50': 5.809444904327393, 'latency_p90': 6.535694813728332}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1103-quang-ir-mixallnov3-cld-i8a9-onlyh3

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-03

win_ratio: 0.5118702953097858

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>', '\n', '####\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {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-1103-quang-ir-mi-56939-v1-mkmlizer
Waiting for job on chaiml-1103-quang-ir-mi-56939-v1-mkmlizer to finish
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: Downloaded to shared memory in 64.231s
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: Checking if ChaiML/1103-quang-ir-mixallnov3-cld-i8a9-onlyh3 already exists in ChaiML
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdh952wxs, device:0
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: quantized model in 43.139s
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: Processed model ChaiML/1103-quang-ir-mixallnov3-cld-i8a9-onlyh3 in 107.370s
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-56939-v1/nvidia
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-56939-v1/nvidia/config.json
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-56939-v1/nvidia/special_tokens_map.json
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-56939-v1/nvidia/tokenizer_config.json
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-56939-v1/nvidia/tokenizer.json
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-56939-v1/nvidia/flywheel_model.1.safetensors
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-56939-v1/nvidia/flywheel_model.0.safetensors
chaiml-1103-quang-ir-mi-56939-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.75it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 31.97it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:10, 32.67it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 34.32it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 34.49it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 35.59it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 40.95it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.10it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.48it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.96it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.75it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.24it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.62it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 31.86it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 29.07it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.80it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.58it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.70it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.17it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.59it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:08, 30.57it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.30it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:13, 19.02it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:13, 19.53it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:18, 13.88it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:16, 15.61it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:15, 16.10it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:10, 23.16it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:10, 22.55it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 29.07it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.31it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.98it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.81it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 36.62it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 23.95it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:07, 26.60it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 27.95it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.28it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.71it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.24it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.60it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 31.59it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.96it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 27.85it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 23.29it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:06, 23.29it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<02:15,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:55,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:14,  2.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.64it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.40it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.78it/s]
Loading 0:  61%|██████    | 221/363 [00:21<00:23,  6.04it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:19,  7.24it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:12, 10.49it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:10, 12.29it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 16.45it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.55it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 23.16it/s]
Loading 0:  69%|██████▉   | 250/363 [00:22<00:04, 24.11it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:03, 28.28it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:03, 27.89it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 34.95it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 24.02it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.47it/s]
Loading 0:  78%|███████▊  | 282/363 [00:23<00:02, 31.42it/s]
Loading 0:  79%|███████▉  | 286/363 [00:23<00:02, 30.20it/s]
Loading 0:  80%|████████  | 291/363 [00:23<00:02, 33.33it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 30.20it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 31.34it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 27.76it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 27.55it/s]
Loading 0:  86%|████████▌ | 311/363 [00:24<00:02, 23.54it/s]
Loading 0:  88%|████████▊ | 318/363 [00:24<00:01, 31.57it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 30.70it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 33.20it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 31.29it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.46it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.30it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:01, 19.23it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.03it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.43it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 27.98it/s]
                                                            
Job chaiml-1103-quang-ir-mi-56939-v1-mkmlizer completed after 185.73s with status: succeeded
Stopping job with name chaiml-1103-quang-ir-mi-56939-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.34s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1103-quang-ir-mi-56939-v1
Waiting for inference service chaiml-1103-quang-ir-mi-56939-v1 to be ready
Inference service chaiml-1103-quang-ir-mi-56939-v1 ready after 131.29585909843445s
Pipeline stage MKMLDeployer completed in 132.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.387587785720825s
Received healthy response to inference request in 2.250462293624878s
Received healthy response to inference request in 2.217421293258667s
Received healthy response to inference request in 2.3241078853607178s
Received healthy response to inference request in 2.2096660137176514s
5 requests
0 failed requests
5th percentile: 2.2112170696258544
10th percentile: 2.2127681255340574
20th percentile: 2.215870237350464
30th percentile: 2.2240294933319094
40th percentile: 2.2372458934783936
50th percentile: 2.250462293624878
60th percentile: 2.279920530319214
70th percentile: 2.3093787670135497
80th percentile: 2.3368038654327394
90th percentile: 2.3621958255767823
95th percentile: 2.3748918056488035
99th percentile: 2.385048589706421
mean time: 2.277849054336548
Pipeline stage StressChecker completed in 12.77s
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 1.27s
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 0.73s
Shutdown handler de-registered
chaiml-1103-quang-ir-mi_56939_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1103-quang-ir-mi-56939-v1-profiler
Waiting for inference service chaiml-1103-quang-ir-mi-56939-v1-profiler to be ready
Inference service chaiml-1103-quang-ir-mi-56939-v1-profiler ready after 141.29854726791382s
Pipeline stage MKMLProfilerDeployer completed in 142.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-1103-quang-ir0d62981be463fa1c3160ff5a1c40f5c9-deplos6mm6:/code/chaiverse_profiler_1762220859 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1103-quang-ir0d62981be463fa1c3160ff5a1c40f5c9-deplos6mm6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762220859 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1762220859/summary.json'
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2924.58s
Shutdown handler de-registered
chaiml-1103-quang-ir-mi_56939_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1103-quang-ir-mi_56939_v1 status is now torndown due to DeploymentManager action