chaiml-1103-quang-ir-mi_50882

developer_uid: chai_backend_admin

submission_id: chaiml-1103-quang-ir-mi_50882_v1

model_name: training123

model_group: ChaiML/1103-quang-ir-mix

status: torndown

timestamp: 2025-11-07T04:06:36+00:00

num_battles: 6192

num_wins: 3135

celo_rating: 1289.86

family_friendly_score: 0.48019999999999996

family_friendly_standard_error: 0.007065521353728966

submission_type: basic

model_repo: ChaiML/1103-quang-ir-mix4bnov3-cld-i8a9-onlyh2

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': 0.37699968506404125, 'latency_mean': 2.652420781850815, 'latency_p50': 2.6478145122528076, 'latency_p90': 2.892938995361328}, {'batch_size': 2, 'throughput': 0.5687122739839675, 'latency_mean': 3.51046826839447, 'latency_p50': 3.501275420188904, 'latency_p90': 3.844778370857239}, {'batch_size': 3, 'throughput': 0.6930388079667202, 'latency_mean': 4.308866780996323, 'latency_p50': 4.3071959018707275, 'latency_p90': 4.846591949462891}, {'batch_size': 4, 'throughput': 0.7813715848913715, 'latency_mean': 5.103304316997528, 'latency_p50': 5.12648606300354, 'latency_p90': 5.811138391494751}, {'batch_size': 5, 'throughput': 0.8463255513181553, 'latency_mean': 5.882228226661682, 'latency_p50': 5.8856223821640015, 'latency_p90': 6.628185534477233}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1103-quang-ir-mix4bnov3-cld-i8a9-onlyh2

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-03

win_ratio: 0.5062984496124031

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', '####\n', '</s>'], '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-50882-v1-mkmlizer
Waiting for job on chaiml-1103-quang-ir-mi-50882-v1-mkmlizer to finish
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: Downloaded to shared memory in 64.443s
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: Checking if ChaiML/1103-quang-ir-mix4bnov3-cld-i8a9-onlyh2 already exists in ChaiML
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv26cni3p, device:0
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: quantized model in 43.660s
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: Processed model ChaiML/1103-quang-ir-mix4bnov3-cld-i8a9-onlyh2 in 108.103s
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-50882-v1/nvidia
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-50882-v1/nvidia/config.json
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-50882-v1/nvidia/special_tokens_map.json
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-50882-v1/nvidia/tokenizer_config.json
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-50882-v1/nvidia/tokenizer.json
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-50882-v1/nvidia/flywheel_model.0.safetensors
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-50882-v1/nvidia/flywheel_model.1.safetensors
chaiml-1103-quang-ir-mi-50882-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.11it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 40.64it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.45it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.49it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.92it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 29.74it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 24.34it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.64it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.09it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 32.84it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.01it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.49it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 29.21it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.32it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.24it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.41it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 26.10it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:11, 24.46it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:11, 23.63it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 30.28it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:10, 24.79it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:11, 22.95it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:10, 24.17it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:13, 18.00it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.41it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 26.41it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.40it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:10, 21.72it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:09, 24.72it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.53it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 32.79it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.01it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:10, 20.46it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.10it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:08, 23.93it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:07, 24.63it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 23.84it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:07, 24.10it/s]
Loading 0:  51%|█████     | 184/363 [00:06<00:07, 24.61it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:08, 21.09it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:10, 16.67it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:10, 15.42it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:10, 15.42it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<02:21,  1.14it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<02:01,  1.32it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:17,  2.01it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<00:59,  2.57it/s]
Loading 0:  59%|█████▉    | 214/363 [00:21<00:44,  3.33it/s]
Loading 0:  60%|██████    | 218/363 [00:21<00:30,  4.71it/s]
Loading 0:  61%|██████    | 221/363 [00:21<00:23,  5.99it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:19,  7.19it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:12, 10.52it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:10, 12.45it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:07, 17.09it/s]
Loading 0:  66%|██████▋   | 241/363 [00:22<00:06, 19.40it/s]
Loading 0:  68%|██████▊   | 246/363 [00:22<00:04, 24.15it/s]
Loading 0:  69%|██████▉   | 250/363 [00:22<00:04, 25.35it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:03, 29.82it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:03, 29.52it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 36.80it/s]
Loading 0:  75%|███████▍  | 271/363 [00:23<00:03, 25.29it/s]
Loading 0:  76%|███████▌  | 275/363 [00:23<00:03, 24.00it/s]
Loading 0:  78%|███████▊  | 282/363 [00:23<00:02, 31.15it/s]
Loading 0:  79%|███████▉  | 286/363 [00:23<00:02, 30.03it/s]
Loading 0:  80%|████████  | 291/363 [00:23<00:02, 33.35it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 31.85it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 32.87it/s]
Loading 0:  84%|████████▎ | 304/363 [00:24<00:01, 29.89it/s]
Loading 0:  85%|████████▍ | 308/363 [00:24<00:01, 29.20it/s]
Loading 0:  86%|████████▌ | 312/363 [00:24<00:01, 26.00it/s]
Loading 0:  88%|████████▊ | 318/363 [00:24<00:01, 31.64it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 30.31it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 33.93it/s]
Loading 0:  91%|█████████ | 331/363 [00:25<00:00, 32.29it/s]
Loading 0:  92%|█████████▏| 335/363 [00:25<00:00, 32.95it/s]
Loading 0:  93%|█████████▎| 339/363 [00:25<00:00, 33.89it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:00, 20.27it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.89it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 29.39it/s]
Loading 0:  99%|█████████▉| 359/363 [00:26<00:00, 28.58it/s]
                                                            
Job chaiml-1103-quang-ir-mi-50882-v1-mkmlizer completed after 186.22s with status: succeeded
Stopping job with name chaiml-1103-quang-ir-mi-50882-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.92s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1103-quang-ir-mi-50882-v1
Waiting for inference service chaiml-1103-quang-ir-mi-50882-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
Inference service chaiml-1103-quang-ir-mi-50882-v1 ready after 140.84882998466492s
Pipeline stage MKMLDeployer completed in 141.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4012465476989746s
Received healthy response to inference request in 2.125293254852295s
Received healthy response to inference request in 2.2171871662139893s
Received healthy response to inference request in 2.675637722015381s
Received healthy response to inference request in 2.566568613052368s
5 requests
0 failed requests
5th percentile: 2.1436720371246336
10th percentile: 2.1620508193969727
20th percentile: 2.1988083839416506
30th percentile: 2.253999042510986
40th percentile: 2.3276227951049804
50th percentile: 2.4012465476989746
60th percentile: 2.467375373840332
70th percentile: 2.5335041999816896
80th percentile: 2.588382434844971
90th percentile: 2.632010078430176
95th percentile: 2.653823900222778
99th percentile: 2.6712749576568604
mean time: 2.3971866607666015
Pipeline stage StressChecker completed in 13.57s
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 0.82s
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-1103-quang-ir-mi_50882_v1 status is now deployed due to DeploymentManager action
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 3030.64s
Shutdown handler de-registered
chaiml-1103-quang-ir-mi_50882_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1103-quang-ir-mi_50882_v1 status is now torndown due to DeploymentManager action