chaiml-1104-quang-ir-mi_88716

developer_uid: chai_backend_admin

submission_id: chaiml-1104-quang-ir-mi_88716_v1

model_name: training123

model_group: ChaiML/1104-quang-ir-mix

status: torndown

timestamp: 2025-11-08T01:01:52+00:00

num_battles: 7093

num_wins: 3555

celo_rating: 1295.26

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f150002

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': 0.38096787271328264, 'latency_mean': 2.6247956669330597, 'latency_p50': 2.6210315227508545, 'latency_p90': 2.898666429519653}, {'batch_size': 2, 'throughput': 0.5658846456967441, 'latency_mean': 3.5241681814193724, 'latency_p50': 3.525314211845398, 'latency_p90': 3.812992238998413}, {'batch_size': 3, 'throughput': 0.705531375681067, 'latency_mean': 4.237408945560455, 'latency_p50': 4.242892265319824, 'latency_p90': 4.764973545074462}, {'batch_size': 4, 'throughput': 0.8011950296802094, 'latency_mean': 4.980177707672119, 'latency_p50': 4.9555217027664185, 'latency_p90': 5.663846135139465}, {'batch_size': 5, 'throughput': 0.8632941898513264, 'latency_mean': 5.777111390829086, 'latency_p50': 5.79500675201416, 'latency_p90': 6.569186329841614}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f150002

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-04

win_ratio: 0.5011983645848019

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:', '\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-88716-v1-mkmlizer
Waiting for job on chaiml-1104-quang-ir-mi-88716-v1-mkmlizer to finish
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ║                                                                     ║
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: Downloaded to shared memory in 62.751s
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: Checking if ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f150002 already exists in ChaiML
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpate2mee5, device:0
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: quantized model in 41.911s
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: Processed model ChaiML/1104-quang-ir-mixall-cld-i8a8-hl-f150002 in 104.662s
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-88716-v1/nvidia
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-88716-v1/nvidia/config.json
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-88716-v1/nvidia/special_tokens_map.json
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-88716-v1/nvidia/tokenizer_config.json
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-88716-v1/nvidia/tokenizer.json
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-88716-v1/nvidia/flywheel_model.1.safetensors
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1104-quang-ir-mi-88716-v1/nvidia/flywheel_model.0.safetensors
chaiml-1104-quang-ir-mi-88716-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.07it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 40.43it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.87it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.90it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 45.32it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 31.24it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.52it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.88it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.36it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.04it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.05it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.56it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.25it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:19, 15.17it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:14, 19.14it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:14, 18.87it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:13, 20.40it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:12, 21.42it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 19.68it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.22it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.27it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 25.72it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 28.70it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 29.41it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:07, 30.99it/s]
Loading 0:  34%|███▍      | 125/363 [00:04<00:07, 32.67it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.29it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.21it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.79it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.25it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 39.77it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.10it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.35it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.61it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.73it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.68it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.50it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.30it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.92it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.26it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.30it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:56,  2.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.73it/s]
Loading 0:  60%|██████    | 219/363 [00:20<00:28,  4.97it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.93it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.55it/s]
Loading 0:  64%|██████▍   | 233/363 [00:20<00:10, 11.91it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 14.85it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:07, 17.26it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 21.81it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 22.91it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.43it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.65it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.90it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.07it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.08it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.28it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.42it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.71it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.50it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.53it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.39it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.56it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.71it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.46it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.70it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 35.26it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 33.29it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 34.00it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.62it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.75it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.29it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.93it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.49it/s]
                                                            
Job chaiml-1104-quang-ir-mi-88716-v1-mkmlizer completed after 175.14s with status: succeeded
Stopping job with name chaiml-1104-quang-ir-mi-88716-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1104-quang-ir-mi-88716-v1
Waiting for inference service chaiml-1104-quang-ir-mi-88716-v1 to be ready
Inference service chaiml-1104-quang-ir-mi-88716-v1 ready after 150.99802350997925s
Pipeline stage MKMLDeployer completed in 151.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.296532392501831s
Received healthy response to inference request in 2.4363632202148438s
Received healthy response to inference request in 2.4430410861968994s
Received healthy response to inference request in 2.1954703330993652s
Received healthy response to inference request in 2.0813045501708984s
5 requests
0 failed requests
5th percentile: 2.1041377067565916
10th percentile: 2.1269708633422852
20th percentile: 2.172637176513672
30th percentile: 2.2156827449798584
40th percentile: 2.2561075687408447
50th percentile: 2.296532392501831
60th percentile: 2.352464723587036
70th percentile: 2.4083970546722413
80th percentile: 2.437698793411255
90th percentile: 2.4403699398040772
95th percentile: 2.441705513000488
99th percentile: 2.4427739715576173
mean time: 2.2905423164367678
Pipeline stage StressChecker completed in 13.02s
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 0.78s
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_88716_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 0.12s
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-88716-v1-profiler
Waiting for inference service chaiml-1104-quang-ir-mi-88716-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5652.31s
Shutdown handler de-registered
chaiml-1104-quang-ir-mi_88716_v1 status is now torndown due to DeploymentManager action