chaiml-1106-quang-ir-mi_78312

developer_uid: chai_backend_admin

submission_id: chaiml-1106-quang-ir-mi_78312_v1

model_name: training123

model_group: ChaiML/1106-quang-ir-mix

status: torndown

timestamp: 2025-11-09T16:31:42+00:00

num_battles: 5611

num_wins: 2884

celo_rating: 1305.32

family_friendly_score: 0.5454

family_friendly_standard_error: 0.007041858277471934

submission_type: basic

model_repo: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_0164642ep

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': 0.3788114843686719, 'latency_mean': 2.639717812538147, 'latency_p50': 2.6453975439071655, 'latency_p90': 2.862371587753296}, {'batch_size': 2, 'throughput': 0.5708387548565234, 'latency_mean': 3.498607349395752, 'latency_p50': 3.4734896421432495, 'latency_p90': 3.7876612186431884}, {'batch_size': 3, 'throughput': 0.7035702052518557, 'latency_mean': 4.251484794616699, 'latency_p50': 4.242303490638733, 'latency_p90': 4.866907787322997}, {'batch_size': 4, 'throughput': 0.7980576843680168, 'latency_mean': 4.988964395523071, 'latency_p50': 4.953553676605225, 'latency_p90': 5.655650568008423}, {'batch_size': 5, 'throughput': 0.8694220717294581, 'latency_mean': 5.724545159339905, 'latency_p50': 5.719886779785156, 'latency_p90': 6.58054301738739}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_0164642ep

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-06

win_ratio: 0.5139903760470504

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': ['\n', '</s>', '####', 'You:'], '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-1106-quang-ir-mi-78312-v1-mkmlizer
Waiting for job on chaiml-1106-quang-ir-mi-78312-v1-mkmlizer to finish
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-1106-quang-ir-mi-78312-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: Downloaded to shared memory in 57.575s
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: Checking if ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_0164642ep already exists in ChaiML
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpze86omso, device:0
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: quantized model in 42.753s
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: Processed model ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_0164642ep in 100.328s
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-78312-v1/nvidia
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-78312-v1/nvidia/config.json
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-78312-v1/nvidia/special_tokens_map.json
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-78312-v1/nvidia/tokenizer_config.json
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-78312-v1/nvidia/tokenizer.json
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-78312-v1/nvidia/flywheel_model.1.safetensors
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-78312-v1/nvidia/flywheel_model.0.safetensors
chaiml-1106-quang-ir-mi-78312-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.26it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 38.99it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.09it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.70it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.79it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 41.86it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.70it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.83it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.34it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.22it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.73it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.68it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.73it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.69it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 22.28it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.48it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 29.75it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 26.38it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.01it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.31it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.49it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.27it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.79it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.34it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.42it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.76it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 33.21it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.27it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.52it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.06it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.48it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.89it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.09it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.92it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.24it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.26it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.09it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 31.96it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 29.01it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.25it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.85it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 212/363 [00:20<00:53,  2.82it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:33,  4.38it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.70it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  6.98it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.58it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.22it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:08, 15.18it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:06, 19.04it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 20.54it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 24.67it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:04, 25.46it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:03, 32.32it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:04, 22.29it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.34it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.10it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.28it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.36it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 28.96it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 28.09it/s]
Loading 0:  83%|████████▎ | 303/363 [00:23<00:01, 30.19it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:02, 20.99it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 20.74it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 28.38it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 28.10it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 31.67it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 30.38it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 31.57it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 31.79it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.44it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.09it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.20it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 27.84it/s]
                                                            
Job chaiml-1106-quang-ir-mi-78312-v1-mkmlizer completed after 312.25s with status: succeeded
Stopping job with name chaiml-1106-quang-ir-mi-78312-v1-mkmlizer
Pipeline stage MKMLizer completed in 312.83s
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-1106-quang-ir-mi-78312-v1
Waiting for inference service chaiml-1106-quang-ir-mi-78312-v1 to be ready
Failed to get response for submission chaiml-prm-v1-pair-new8_86832_v1: HTTPConnectionPool(host='chaiml-prm-v1-pair-new8-86832-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-prm-v1-pair-new8_86832_v1: HTTPConnectionPool(host='chaiml-prm-v1-pair-new8-86832-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
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', '')
Tearing down inference service chaiml-1106-quang-ir-mi-78312-v1
%s, retrying in %s seconds...
Creating inference service chaiml-1106-quang-ir-mi-78312-v1
Waiting for inference service chaiml-1106-quang-ir-mi-78312-v1 to be ready
Inference service chaiml-1106-quang-ir-mi-78312-v1 ready after 160.9385530948639s
Pipeline stage MKMLDeployer completed in 775.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3318135738372803s
Received healthy response to inference request in 2.1410562992095947s
Received healthy response to inference request in 2.338576316833496s
Received healthy response to inference request in 2.4987504482269287s
Received healthy response to inference request in 2.582829475402832s
5 requests
0 failed requests
5th percentile: 2.179207754135132
10th percentile: 2.217359209060669
20th percentile: 2.293662118911743
30th percentile: 2.3331661224365234
40th percentile: 2.3358712196350098
50th percentile: 2.338576316833496
60th percentile: 2.402645969390869
70th percentile: 2.466715621948242
80th percentile: 2.5155662536621093
90th percentile: 2.549197864532471
95th percentile: 2.5660136699676515
99th percentile: 2.579466314315796
mean time: 2.3786052227020265
Pipeline stage StressChecker completed in 13.30s
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 0.66s
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-1106-quang-ir-mi_78312_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1106-quang-ir-mi-78312-v1-profiler
Waiting for inference service chaiml-1106-quang-ir-mi-78312-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3158.87s
Shutdown handler de-registered
chaiml-1106-quang-ir-mi_78312_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1106-quang-ir-mi_78312_v1 status is now torndown due to DeploymentManager action