chaiml-1108-quang-ir-mi_73974

developer_uid: chai_backend_admin

submission_id: chaiml-1108-quang-ir-mi_73974_v1

model_name: training123

model_group: ChaiML/1108-quang-ir-mix

status: torndown

timestamp: 2025-11-11T14:21:51+00:00

num_battles: 6275

num_wins: 2958

celo_rating: 1290.76

family_friendly_score: 0.5662

family_friendly_standard_error: 0.007008816733229655

submission_type: basic

model_repo: ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f10000-dpo_multsth25k_0164641ep_5e6ct

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': 0.3799184040520874, 'latency_mean': 2.63203404545784, 'latency_p50': 2.6388903856277466, 'latency_p90': 2.8729734897613524}, {'batch_size': 2, 'throughput': 0.5678836878536777, 'latency_mean': 3.5182015919685363, 'latency_p50': 3.515384078025818, 'latency_p90': 3.8360639333724977}, {'batch_size': 3, 'throughput': 0.6979227101546164, 'latency_mean': 4.281411139965058, 'latency_p50': 4.272812247276306, 'latency_p90': 4.927290081977844}, {'batch_size': 4, 'throughput': 0.7861022104701525, 'latency_mean': 5.0531394672393795, 'latency_p50': 5.01726233959198, 'latency_p90': 5.857572388648986}, {'batch_size': 5, 'throughput': 0.8410356154953258, 'latency_mean': 5.918111939430236, 'latency_p50': 5.929680109024048, 'latency_p90': 6.771378159523009}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f10000-dpo_multsth25k_0164641ep_5e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-08

win_ratio: 0.47139442231075696

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': ['####', '</s>', '\n', '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
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-1108-quang-ir-mi-73974-v1-mkmlizer
Waiting for job on chaiml-1108-quang-ir-mi-73974-v1-mkmlizer to finish
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: Downloaded to shared memory in 52.591s
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: Checking if ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f10000-dpo_multsth25k_0164641ep_5e6ct already exists in ChaiML
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxdx__9is, device:0
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: quantized model in 41.690s
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: Processed model ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f10000-dpo_multsth25k_0164641ep_5e6ct in 94.282s
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-73974-v1/nvidia
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-73974-v1/nvidia/config.json
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-73974-v1/nvidia/special_tokens_map.json
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-73974-v1/nvidia/tokenizer_config.json
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-73974-v1/nvidia/tokenizer.json
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-73974-v1/nvidia/flywheel_model.1.safetensors
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-73974-v1/nvidia/flywheel_model.0.safetensors
chaiml-1108-quang-ir-mi-73974-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.56it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.84it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.36it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.29it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.86it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.35it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.62it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.58it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.44it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 31.86it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 32.94it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.64it/s]
Loading 0:  18%|█▊        | 67/363 [00:02<00:08, 36.91it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.87it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.34it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.57it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.16it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.22it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.88it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.50it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.70it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.90it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.46it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.70it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.67it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.83it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.52it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.63it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.85it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.01it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.78it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 26.80it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.66it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.89it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.35it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.67it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.32it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.42it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 31.10it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 30.12it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 27.28it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.13it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:53,  2.84it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:32,  4.42it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:24,  5.75it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.08it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.72it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.47it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:08, 15.14it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:06, 19.10it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 20.71it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 24.82it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:04, 25.47it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 32.68it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 24.89it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 22.86it/s]
Loading 0:  77%|███████▋  | 280/363 [00:21<00:03, 27.09it/s]
Loading 0:  78%|███████▊  | 284/363 [00:22<00:03, 23.93it/s]
Loading 0:  80%|███████▉  | 290/363 [00:22<00:02, 30.49it/s]
Loading 0:  81%|████████  | 294/363 [00:22<00:02, 27.00it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 30.39it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 29.32it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.84it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.88it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.36it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.36it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.86it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.73it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.75it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 32.77it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.82it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.58it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.07it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.35it/s]
                                                            
Job chaiml-1108-quang-ir-mi-73974-v1-mkmlizer completed after 134.42s with status: succeeded
Stopping job with name chaiml-1108-quang-ir-mi-73974-v1-mkmlizer
Pipeline stage MKMLizer completed in 134.91s
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-1108-quang-ir-mi-73974-v1
Waiting for inference service chaiml-1108-quang-ir-mi-73974-v1 to be ready
Inference service chaiml-1108-quang-ir-mi-73974-v1 ready after 190.6887927055359s
Pipeline stage MKMLDeployer completed in 191.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.707481622695923s
Received healthy response to inference request in 2.4365828037261963s
Received healthy response to inference request in 2.114198923110962s
Received healthy response to inference request in 2.6652519702911377s
Received healthy response to inference request in 2.248405933380127s
5 requests
0 failed requests
5th percentile: 2.141040325164795
10th percentile: 2.167881727218628
20th percentile: 2.221564531326294
30th percentile: 2.2860413074493406
40th percentile: 2.3613120555877685
50th percentile: 2.4365828037261963
60th percentile: 2.5280504703521727
70th percentile: 2.6195181369781495
80th percentile: 2.673697900772095
90th percentile: 2.690589761734009
95th percentile: 2.6990356922149656
99th percentile: 2.7057924365997312
mean time: 2.434384250640869
Pipeline stage StressChecker completed in 13.43s
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 0.64s
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 0.64s
Shutdown handler de-registered
chaiml-1108-quang-ir-mi_73974_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 0.09s
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-1108-quang-ir-mi-73974-v1-profiler
Waiting for inference service chaiml-1108-quang-ir-mi-73974-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 3199.33s
Shutdown handler de-registered
chaiml-1108-quang-ir-mi_73974_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1108-quang-ir-mi_73974_v1 status is now torndown due to DeploymentManager action