chaiml-1104-quang-ir-mi_16588

developer_uid: chai_backend_admin

submission_id: chaiml-1104-quang-ir-mi_16588_v1

model_name: training123

model_group: ChaiML/1104-quang-ir-mix

status: torndown

timestamp: 2025-11-08T01:31:20+00:00

num_battles: 6418

num_wins: 3298

celo_rating: 1293.38

family_friendly_score: 0.508

family_friendly_standard_error: 0.007070162657251953

submission_type: basic

model_repo: ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f100002

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': 0.37968600381252704, 'latency_mean': 2.633659089803696, 'latency_p50': 2.625765323638916, 'latency_p90': 2.8678951025009156}, {'batch_size': 2, 'throughput': 0.5718746823787824, 'latency_mean': 3.495326451063156, 'latency_p50': 3.487301230430603, 'latency_p90': 3.820107936859131}, {'batch_size': 3, 'throughput': 0.7084400668281149, 'latency_mean': 4.2221706771850585, 'latency_p50': 4.188825845718384, 'latency_p90': 4.600949287414551}, {'batch_size': 4, 'throughput': 0.8030436771866979, 'latency_mean': 4.955413988828659, 'latency_p50': 4.953057289123535, 'latency_p90': 5.596755003929138}, {'batch_size': 5, 'throughput': 0.8601142568307437, 'latency_mean': 5.79499981880188, 'latency_p50': 5.778881549835205, 'latency_p90': 6.713057637214661}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f100002

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-04

win_ratio: 0.5138672483639763

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:', '####\n', '####', '</s>', '\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-1104-quang-ir-mi-16588-v1-mkmlizer
Waiting for job on chaiml-1104-quang-ir-mi-16588-v1-mkmlizer to finish
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-16588-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-1104-quang-ir-mi-16588-v1-mkmlizer: Downloaded to shared memory in 65.287s
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: Checking if ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f100002 already exists in ChaiML
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_x2_xjr6, device:0
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: quantized model in 42.140s
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: Processed model ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f100002 in 107.427s
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-16588-v1/nvidia
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-16588-v1/nvidia/config.json
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-16588-v1/nvidia/special_tokens_map.json
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-16588-v1/nvidia/tokenizer_config.json
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-16588-v1/nvidia/tokenizer.json
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-16588-v1/nvidia/flywheel_model.1.safetensors
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-16588-v1/nvidia/flywheel_model.0.safetensors
chaiml-1104-quang-ir-mi-16588-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.91it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.89it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.19it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 37.09it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:08, 37.50it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.21it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.32it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.15it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.80it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.49it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.21it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.89it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 33.04it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.66it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.90it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.90it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.73it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 26.66it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.59it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.75it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.12it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.80it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.58it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.24it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.61it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.21it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.63it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 33.17it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 31.25it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 37.92it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 23.14it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 23.88it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 30.64it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 29.60it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 32.81it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:06, 30.65it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 31.89it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.96it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.49it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.64it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.44it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:29,  4.85it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:21,  6.59it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:17,  7.62it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:14,  9.23it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 14.36it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:07, 16.07it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 20.19it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 21.58it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 25.93it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.41it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.31it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.44it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.94it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.66it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.59it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.89it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.02it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.11it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 29.00it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 27.93it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 23.66it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.95it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.57it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.74it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.78it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.17it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.50it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.10it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.56it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.93it/s]
                                                            
Job chaiml-1104-quang-ir-mi-16588-v1-mkmlizer completed after 186.0s with status: succeeded
Stopping job with name chaiml-1104-quang-ir-mi-16588-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.55s
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-1104-quang-ir-mi-16588-v1
Waiting for inference service chaiml-1104-quang-ir-mi-16588-v1 to be ready
Inference service chaiml-1104-quang-ir-mi-16588-v1 ready after 140.97105503082275s
Pipeline stage MKMLDeployer completed in 141.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5025079250335693s
Received healthy response to inference request in 2.230426549911499s
Received healthy response to inference request in 2.141810894012451s
Received healthy response to inference request in 2.469419002532959s
Received healthy response to inference request in 2.279741048812866s
5 requests
0 failed requests
5th percentile: 2.1595340251922606
10th percentile: 2.1772571563720704
20th percentile: 2.2127034187316896
30th percentile: 2.2402894496917725
40th percentile: 2.2600152492523193
50th percentile: 2.279741048812866
60th percentile: 2.3556122303009035
70th percentile: 2.4314834117889403
80th percentile: 2.476036787033081
90th percentile: 2.489272356033325
95th percentile: 2.4958901405334473
99th percentile: 2.501184368133545
mean time: 2.324781084060669
Pipeline stage StressChecker completed in 13.07s
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 0.79s
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 0.76s
Shutdown handler de-registered
chaiml-1104-quang-ir-mi_16588_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1104-quang-ir-mi-16588-v1-profiler
Waiting for inference service chaiml-1104-quang-ir-mi-16588-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 3004.52s
Shutdown handler de-registered
chaiml-1104-quang-ir-mi_16588_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1104-quang-ir-mi_16588_v1 status is now torndown due to DeploymentManager action