chaiml-1105-quang-ir-mi_48859

developer_uid: chai_backend_admin

submission_id: chaiml-1105-quang-ir-mi_48859_v1

model_name: training123

model_group: ChaiML/1105-quang-ir-mix

status: torndown

timestamp: 2025-11-09T07:26:48+00:00

num_battles: 6189

num_wins: 3030

celo_rating: 1303.87

family_friendly_score: 0.5412

family_friendly_standard_error: 0.007047021498477211

submission_type: basic

model_repo: ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-f15000-dpo_011616

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': 0.35683821210128996, 'latency_mean': 2.8022694289684296, 'latency_p50': 2.6389347314834595, 'latency_p90': 2.9418970346450806}, {'batch_size': 2, 'throughput': 0.5762499592350564, 'latency_mean': 3.4661338865756988, 'latency_p50': 3.467384696006775, 'latency_p90': 3.7392547130584717}, {'batch_size': 3, 'throughput': 0.7111804158249427, 'latency_mean': 4.205669726133347, 'latency_p50': 4.20746922492981, 'latency_p90': 4.682070755958557}, {'batch_size': 4, 'throughput': 0.8174657926227243, 'latency_mean': 4.881669944524765, 'latency_p50': 4.873448491096497, 'latency_p90': 5.498455619812011}, {'batch_size': 5, 'throughput': 0.8763303851490517, 'latency_mean': 5.679639716148376, 'latency_p50': 5.663774609565735, 'latency_p90': 6.560432004928589}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-f15000-dpo_011616

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-11-05

win_ratio: 0.48957828405235093

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:'], '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-1105-quang-ir-mi-48859-v1-mkmlizer
Waiting for job on chaiml-1105-quang-ir-mi-48859-v1-mkmlizer to finish
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: Downloaded to shared memory in 57.072s
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: Checking if ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-f15000-dpo_011616 already exists in ChaiML
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjk7p3b_r, device:0
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: quantized model in 42.813s
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: Processed model ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-f15000-dpo_011616 in 99.886s
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-48859-v1/nvidia
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-48859-v1/nvidia/config.json
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-48859-v1/nvidia/special_tokens_map.json
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-48859-v1/nvidia/tokenizer_config.json
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-48859-v1/nvidia/tokenizer.json
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-48859-v1/nvidia/flywheel_model.1.safetensors
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-48859-v1/nvidia/flywheel_model.0.safetensors
chaiml-1105-quang-ir-mi-48859-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.54it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.23it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 39.57it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 30.69it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.86it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.74it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.33it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.43it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.97it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.55it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 34.53it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.14it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.63it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.36it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.14it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 31.00it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.48it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 26.79it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.09it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.18it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.91it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.26it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 30.93it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.84it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.07it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.37it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.03it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.54it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 31.50it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 37.81it/s]
Loading 0:  42%|████▏     | 153/363 [00:04<00:08, 24.80it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.81it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.62it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.32it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.36it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.01it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.00it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 29.20it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.15it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.87it/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<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.41it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.79it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.06it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.22it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.52it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.84it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 18.94it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 22.66it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.79it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.16it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.20it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.27it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:03, 23.96it/s]
Loading 0:  75%|███████▌  | 274/363 [00:22<00:03, 26.65it/s]
Loading 0:  77%|███████▋  | 278/363 [00:22<00:02, 28.65it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.94it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.72it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.41it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.57it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.44it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 29.32it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.08it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 23.28it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.32it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 26.36it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 28.56it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 23.29it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:01, 24.12it/s]
Loading 0:  93%|█████████▎| 338/363 [00:24<00:01, 23.91it/s]
Loading 0:  94%|█████████▍| 341/363 [00:24<00:01, 16.30it/s]
Loading 0:  96%|█████████▌| 347/363 [00:24<00:00, 22.01it/s]
Loading 0:  96%|█████████▋| 350/363 [00:24<00:00, 22.69it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 27.16it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 27.13it/s]
                                                            
Job chaiml-1105-quang-ir-mi-48859-v1-mkmlizer completed after 205.04s with status: succeeded
Stopping job with name chaiml-1105-quang-ir-mi-48859-v1-mkmlizer
Pipeline stage MKMLizer completed in 205.54s
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-1105-quang-ir-mi-48859-v1
Waiting for inference service chaiml-1105-quang-ir-mi-48859-v1 to be ready
Inference service chaiml-1105-quang-ir-mi-48859-v1 ready after 160.68079352378845s
Pipeline stage MKMLDeployer completed in 161.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.415698528289795s
Received healthy response to inference request in 2.2420876026153564s
Received healthy response to inference request in 2.136434316635132s
Received healthy response to inference request in 2.411952495574951s
Received healthy response to inference request in 2.3106634616851807s
5 requests
0 failed requests
5th percentile: 2.157564973831177
10th percentile: 2.178695631027222
20th percentile: 2.2209569454193114
30th percentile: 2.255802774429321
40th percentile: 2.283233118057251
50th percentile: 2.3106634616851807
60th percentile: 2.351179075241089
70th percentile: 2.391694688796997
80th percentile: 2.41270170211792
90th percentile: 2.4142001152038572
95th percentile: 2.414949321746826
99th percentile: 2.415548686981201
mean time: 2.303367280960083
Pipeline stage StressChecker completed in 12.77s
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 0.61s
Shutdown handler de-registered
chaiml-1105-quang-ir-mi_48859_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
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 0.13s
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-1105-quang-ir-mi-48859-v1-profiler
Waiting for inference service chaiml-1105-quang-ir-mi-48859-v1-profiler to be ready
Inference service chaiml-1105-quang-ir-mi-48859-v1-profiler ready after 161.2794451713562s
Pipeline stage MKMLProfilerDeployer completed in 161.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-1105-quang-ir3e3af0cfa6e707c6aa8e0c6328606698-deplon765t:/code/chaiverse_profiler_1762405672 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1105-quang-ir3e3af0cfa6e707c6aa8e0c6328606698-deplon765t --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762405672 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1762405672/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-1105-quang-ir3e3af0cfa6e707c6aa8e0c6328606698-deplon765t:/code/chaiverse_profiler_1762406978 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1105-quang-ir3e3af0cfa6e707c6aa8e0c6328606698-deplon765t --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762406978 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1762406978/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1105-quang-ir3e3af0cfa6e707c6aa8e0c6328606698-deplon765t --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1762406978/summary.json'
Pipeline stage MKMLProfilerRunner completed in 2975.30s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-1105-quang-ir-mi-48859-v1-profiler is running
Tearing down inference service chaiml-1105-quang-ir-mi-48859-v1-profiler
Service chaiml-1105-quang-ir-mi-48859-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.81s
Shutdown handler de-registered
chaiml-1105-quang-ir-mi_48859_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1105-quang-ir-mi_48859_v1 status is now torndown due to DeploymentManager action