chaiml-1104-quang-ir-mi_58780

developer_uid: chai_backend_admin

submission_id: chaiml-1104-quang-ir-mi_58780_v2

model_name: training123

model_group: ChaiML/1104-quang-ir-mix

status: torndown

timestamp: 2025-11-08T05:56:42+00:00

num_battles: 5754

num_wins: 2940

celo_rating: 1302.67

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f200003

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': 0.3801481949356356, 'latency_mean': 2.6304530477523804, 'latency_p50': 2.630343794822693, 'latency_p90': 2.8768932580947877}, {'batch_size': 2, 'throughput': 0.5696126642601792, 'latency_mean': 3.501666861772537, 'latency_p50': 3.5116074085235596, 'latency_p90': 3.7891992330551147}, {'batch_size': 3, 'throughput': 0.711066023306492, 'latency_mean': 4.206861691474915, 'latency_p50': 4.198023796081543, 'latency_p90': 4.5927071332931515}, {'batch_size': 4, 'throughput': 0.8048443373856042, 'latency_mean': 4.950154435634613, 'latency_p50': 4.924638152122498, 'latency_p90': 5.5523881912231445}, {'batch_size': 5, 'throughput': 0.8590307844037056, 'latency_mean': 5.789572751522064, 'latency_p50': 5.799299716949463, 'latency_p90': 6.663883805274963}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f200003

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-04

win_ratio: 0.5109489051094891

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-1104-quang-ir-mi-58780-v2-mkmlizer
Waiting for job on chaiml-1104-quang-ir-mi-58780-v2-mkmlizer to finish
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: Downloaded to shared memory in 50.558s
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: Checking if ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f200003 already exists in ChaiML
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdw3wi034, device:0
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: quantized model in 43.157s
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: Processed model ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f200003 in 93.715s
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-58780-v2/nvidia
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-58780-v2/nvidia/config.json
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-58780-v2/nvidia/special_tokens_map.json
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-58780-v2/nvidia/tokenizer_config.json
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-58780-v2/nvidia/tokenizer.json
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-58780-v2/nvidia/flywheel_model.1.safetensors
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-58780-v2/nvidia/flywheel_model.0.safetensors
chaiml-1104-quang-ir-mi-58780-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.67it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.95it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.22it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.67it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 37.31it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.71it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.18it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.25it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.05it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.03it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 32.91it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.76it/s]
Loading 0:  18%|█▊        | 67/363 [00:02<00:07, 37.07it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:10, 27.15it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:10, 28.41it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:11, 25.05it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:09, 30.59it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:09, 28.88it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:10, 26.12it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.93it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.45it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 24.76it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 27.91it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.15it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:07, 30.72it/s]
Loading 0:  34%|███▍      | 125/363 [00:04<00:07, 31.88it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.80it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.13it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.45it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 27.57it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 35.00it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 23.87it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:10, 18.77it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 25.47it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:07, 24.32it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:07, 26.62it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:08, 22.62it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.10it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.42it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:08, 20.95it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:08, 20.99it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:09,  1.25it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:52,  1.43it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:12,  2.14it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:56,  2.69it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.74it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.76it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:24,  5.89it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:21,  6.39it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:14,  9.41it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:11, 11.24it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:08, 15.60it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.10it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 22.82it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.14it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.54it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:03, 28.12it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 35.23it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 25.42it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.20it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.39it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.42it/s]
Loading 0:  80%|████████  | 291/363 [00:23<00:02, 33.71it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 31.61it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 32.51it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 30.11it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.58it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.62it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.43it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 30.29it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 33.78it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:00, 32.16it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 33.01it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.37it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:00, 20.33it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 22.14it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 29.79it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 29.15it/s]
                                                            
Job chaiml-1104-quang-ir-mi-58780-v2-mkmlizer completed after 164.84s with status: succeeded
Stopping job with name chaiml-1104-quang-ir-mi-58780-v2-mkmlizer
Pipeline stage MKMLizer completed in 165.75s
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-58780-v2
Waiting for inference service chaiml-1104-quang-ir-mi-58780-v2 to be ready
Inference service chaiml-1104-quang-ir-mi-58780-v2 ready after 150.86742186546326s
Pipeline stage MKMLDeployer completed in 151.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.419196844100952s
Received healthy response to inference request in 2.1082067489624023s
Received healthy response to inference request in 2.2661936283111572s
Received healthy response to inference request in 2.147571325302124s
Received healthy response to inference request in 2.20021915435791s
5 requests
0 failed requests
5th percentile: 2.1160796642303468
10th percentile: 2.123952579498291
20th percentile: 2.1396984100341796
30th percentile: 2.158100891113281
40th percentile: 2.1791600227355956
50th percentile: 2.20021915435791
60th percentile: 2.226608943939209
70th percentile: 2.2529987335205077
80th percentile: 2.2967942714691163
90th percentile: 2.357995557785034
95th percentile: 2.388596200942993
99th percentile: 2.4130767154693604
mean time: 2.2282775402069093
Pipeline stage StressChecker completed in 12.80s
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 0.70s
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 0.70s
Shutdown handler de-registered
chaiml-1104-quang-ir-mi_58780_v2 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1104-quang-ir-mi-58780-v2-profiler
Waiting for inference service chaiml-1104-quang-ir-mi-58780-v2-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5408.91s
Shutdown handler de-registered
chaiml-1104-quang-ir-mi_58780_v2 status is now torndown due to DeploymentManager action