chaiml-1106-quang-ir-mix_7883

developer_uid: chai_backend_admin

submission_id: chaiml-1106-quang-ir-mix_7883_v1

model_name: training123

model_group: ChaiML/1106-quang-ir-mix

status: torndown

timestamp: 2025-11-10T06:01:33+00:00

num_battles: 5732

num_wins: 2920

celo_rating: 1303.85

family_friendly_score: 0.5422

family_friendly_standard_error: 0.007045837920361212

submission_type: basic

model_repo: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_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': 0.38448488785734525, 'latency_mean': 2.6007624208927154, 'latency_p50': 2.6015816926956177, 'latency_p90': 2.8628631353378298}, {'batch_size': 2, 'throughput': 0.574063016857289, 'latency_mean': 3.4772146356105806, 'latency_p50': 3.4944595098495483, 'latency_p90': 3.7929267406463625}, {'batch_size': 3, 'throughput': 0.7092247024718509, 'latency_mean': 4.215970219373703, 'latency_p50': 4.204941153526306, 'latency_p90': 4.712328910827637}, {'batch_size': 4, 'throughput': 0.8120558113231409, 'latency_mean': 4.902352598905563, 'latency_p50': 4.86875319480896, 'latency_p90': 5.71987202167511}, {'batch_size': 5, 'throughput': 0.8617222516983332, 'latency_mean': 5.779668477773666, 'latency_p50': 5.780004143714905, 'latency_p90': 6.63025426864624}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_0164641ep_5e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-06

win_ratio: 0.5094207955338451

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>'], '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-1106-quang-ir-mix-7883-v1-mkmlizer
Waiting for job on chaiml-1106-quang-ir-mix-7883-v1-mkmlizer to finish
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: Downloaded to shared memory in 63.445s
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: Checking if ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_0164641ep_5e6ct already exists in ChaiML
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptft696n7, device:0
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: quantized model in 42.883s
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: Processed model ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_0164641ep_5e6ct in 106.328s
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1106-quang-ir-mix-7883-v1/nvidia
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mix-7883-v1/nvidia/config.json
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mix-7883-v1/nvidia/special_tokens_map.json
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mix-7883-v1/nvidia/tokenizer_config.json
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mix-7883-v1/nvidia/tokenizer.json
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mix-7883-v1/nvidia/flywheel_model.0.safetensors
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mix-7883-v1/nvidia/flywheel_model.1.safetensors
chaiml-1106-quang-ir-mix-7883-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.16it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.02it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.13it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 29.15it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:09, 33.76it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.32it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:21, 15.38it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:18, 17.22it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:18, 17.67it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.54it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:16, 19.13it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.72it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.82it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.65it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 27.10it/s]
Loading 0:  20%|██        | 74/363 [00:03<00:11, 24.83it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:09, 29.06it/s]
Loading 0:  23%|██▎       | 83/363 [00:03<00:09, 29.45it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 26.64it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.38it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.89it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.29it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 27.47it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 29.91it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 30.72it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 32.64it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 31.12it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.92it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.48it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.68it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:06, 32.35it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 38.99it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.59it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.84it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.99it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.47it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.64it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.17it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 32.90it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.81it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.91it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.15it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:55,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:14,  2.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.42it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.81it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.09it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.28it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:13, 10.17it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:10, 12.08it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 16.60it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.87it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.42it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.13it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.53it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:03, 27.89it/s]
Loading 0:  73%|███████▎  | 265/363 [00:22<00:02, 34.65it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:04, 23.19it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 22.84it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 29.74it/s]
Loading 0:  79%|███████▉  | 286/363 [00:23<00:02, 28.78it/s]
Loading 0:  80%|████████  | 291/363 [00:23<00:02, 31.98it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 29.99it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 30.86it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 28.03it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 27.55it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 23.31it/s]
Loading 0:  88%|████████▊ | 318/363 [00:24<00:01, 31.26it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 30.06it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 33.58it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 30.46it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 31.73it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.55it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:01, 19.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.67it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 29.15it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 29.01it/s]
                                                            
Job chaiml-1106-quang-ir-mix-7883-v1-mkmlizer completed after 165.22s with status: succeeded
Stopping job with name chaiml-1106-quang-ir-mix-7883-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.80s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1106-quang-ir-mix-7883-v1
Waiting for inference service chaiml-1106-quang-ir-mix-7883-v1 to be ready
Inference service chaiml-1106-quang-ir-mix-7883-v1 ready after 171.1417577266693s
Pipeline stage MKMLDeployer completed in 171.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.426417350769043s
Received healthy response to inference request in 2.1705565452575684s
Received healthy response to inference request in 2.1215288639068604s
Received healthy response to inference request in 2.365934133529663s
Received healthy response to inference request in 2.0832202434539795s
5 requests
0 failed requests
5th percentile: 2.0908819675445556
10th percentile: 2.0985436916351317
20th percentile: 2.1138671398162843
30th percentile: 2.131334400177002
40th percentile: 2.150945472717285
50th percentile: 2.1705565452575684
60th percentile: 2.248707580566406
70th percentile: 2.3268586158752442
80th percentile: 2.378030776977539
90th percentile: 2.402224063873291
95th percentile: 2.414320707321167
99th percentile: 2.4239980220794677
mean time: 2.233531427383423
Pipeline stage StressChecker completed in 12.47s
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 0.81s
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 0.66s
Shutdown handler de-registered
chaiml-1106-quang-ir-mix_7883_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1106-quang-ir-mix-7883-v1-profiler
Waiting for inference service chaiml-1106-quang-ir-mix-7883-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 3020.51s
Shutdown handler de-registered
chaiml-1106-quang-ir-mix_7883_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1106-quang-ir-mix_7883_v1 status is now torndown due to DeploymentManager action