chaiml-1111-quang-ir-mix_7721

developer_uid: chai_backend_admin

submission_id: chaiml-1111-quang-ir-mix_7721_v1

model_name: training123

model_group: ChaiML/1111-quang-ir-mix

status: torndown

timestamp: 2025-11-14T19:41:26+00:00

num_battles: 5285

num_wins: 2735

celo_rating: 1297.82

family_friendly_score: 0.5860000000000001

family_friendly_standard_error: 0.006965687331484238

submission_type: basic

model_repo: ChaiML/1111-quang-ir-mixall-cld-i0a0-freev2-f5000-dpo_freev22_0164642ep_2e6ct

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': 0.34796458227505234, 'latency_mean': 2.8737532818317413, 'latency_p50': 2.6566696166992188, 'latency_p90': 2.93485255241394}, {'batch_size': 2, 'throughput': 0.5685370086815531, 'latency_mean': 3.5153726649284365, 'latency_p50': 3.5076138973236084, 'latency_p90': 3.8233282566070557}, {'batch_size': 3, 'throughput': 0.7068258017305736, 'latency_mean': 4.233411456346512, 'latency_p50': 4.206021308898926, 'latency_p90': 4.639208817481994}, {'batch_size': 4, 'throughput': 0.7980931363431611, 'latency_mean': 4.9926173210144045, 'latency_p50': 5.0085378885269165, 'latency_p90': 5.734832715988159}, {'batch_size': 5, 'throughput': 0.8585661852346784, 'latency_mean': 5.800075644254685, 'latency_p50': 5.8070677518844604, 'latency_p90': 6.589462447166443}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1111-quang-ir-mixall-cld-i0a0-freev2-f5000-dpo_freev22_0164642ep_2e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-11

win_ratio: 0.5175023651844843

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>', '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-1111-quang-ir-mix-7721-v1-mkmlizer
Waiting for job on chaiml-1111-quang-ir-mix-7721-v1-mkmlizer to finish
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║                                                                     ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║                                                                     ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║                                                                     ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║                                                                     ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ║                                                                     ║
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: Downloaded to shared memory in 79.822s
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: Checking if ChaiML/1111-quang-ir-mixall-cld-i0a0-freev2-f5000-dpo_freev22_0164642ep_2e6ct already exists in ChaiML
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmjczmh88, device:0
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: quantized model in 42.423s
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: Processed model ChaiML/1111-quang-ir-mixall-cld-i0a0-freev2-f5000-dpo_freev22_0164642ep_2e6ct in 122.246s
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1111-quang-ir-mix-7721-v1/nvidia
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1111-quang-ir-mix-7721-v1/nvidia/special_tokens_map.json
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1111-quang-ir-mix-7721-v1/nvidia/config.json
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1111-quang-ir-mix-7721-v1/nvidia/tokenizer_config.json
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1111-quang-ir-mix-7721-v1/nvidia/tokenizer.json
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1111-quang-ir-mix-7721-v1/nvidia/flywheel_model.0.safetensors
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1111-quang-ir-mix-7721-v1/nvidia/flywheel_model.1.safetensors
chaiml-1111-quang-ir-mix-7721-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.38it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.06it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.80it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.47it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.19it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 41.27it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.50it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.02it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.62it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.07it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.56it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.76it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 31.81it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.09it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.46it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.34it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.33it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 26.85it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.49it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.74it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.18it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.50it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.17it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.26it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 31.03it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.47it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.07it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.30it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.89it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.00it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.82it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:07, 27.57it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:06, 29.09it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.05it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 29.75it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.18it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 30.86it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 31.84it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.57it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.11it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.57it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.65it/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, 10.49it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.91it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.89it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 23.24it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.32it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.67it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.02it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.95it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.57it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.27it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.22it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.49it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.60it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 30.83it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 31.91it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 29.45it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.91it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.70it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.26it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 28.15it/s]
Loading 0:  90%|████████▉ | 326/363 [00:23<00:01, 29.30it/s]
Loading 0:  91%|█████████ | 330/363 [00:24<00:01, 24.42it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:01, 27.65it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 29.30it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.04it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 20.48it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 27.16it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 27.02it/s]
                                                            
Job chaiml-1111-quang-ir-mix-7721-v1-mkmlizer completed after 167.0s with status: succeeded
Stopping job with name chaiml-1111-quang-ir-mix-7721-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.60s
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-1111-quang-ir-mix-7721-v1
Waiting for inference service chaiml-1111-quang-ir-mix-7721-v1 to be ready
Inference service chaiml-1111-quang-ir-mix-7721-v1 ready after 140.8903365135193s
Pipeline stage MKMLDeployer completed in 141.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7526705265045166s
Received healthy response to inference request in 2.265367269515991s
Received healthy response to inference request in 2.148076057434082s
Received healthy response to inference request in 2.209895133972168s
Received healthy response to inference request in 2.262883424758911s
5 requests
0 failed requests
5th percentile: 2.160439872741699
10th percentile: 2.1728036880493162
20th percentile: 2.197531318664551
30th percentile: 2.220492792129517
40th percentile: 2.241688108444214
50th percentile: 2.262883424758911
60th percentile: 2.263876962661743
70th percentile: 2.2648705005645753
80th percentile: 2.362827920913696
90th percentile: 2.5577492237091066
95th percentile: 2.6552098751068116
99th percentile: 2.7331783962249756
mean time: 2.3277784824371337
Pipeline stage StressChecker completed in 12.96s
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 0.66s
Shutdown handler de-registered
chaiml-1111-quang-ir-mix_7721_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 0.11s
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-1111-quang-ir-mix-7721-v1-profiler
Waiting for inference service chaiml-1111-quang-ir-mix-7721-v1-profiler to be ready
Inference service chaiml-1111-quang-ir-mix-7721-v1-profiler ready after 151.376323223114s
Pipeline stage MKMLProfilerDeployer completed in 152.16s
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-1111-quang-ird2fa1a7a825f3e48cfb8e051e8a8320b-deplovhwb2:/code/chaiverse_profiler_1762886499 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1111-quang-ird2fa1a7a825f3e48cfb8e051e8a8320b-deplovhwb2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762886499 && 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_1762886499/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-1111-quang-ird2fa1a7a825f3e48cfb8e051e8a8320b-deplovhwb2:/code/chaiverse_profiler_1762888070 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1111-quang-ird2fa1a7a825f3e48cfb8e051e8a8320b-deplovhwb2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762888070 && 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_1762888070/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1111-quang-ird2fa1a7a825f3e48cfb8e051e8a8320b-deplovhwb2 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1762888070/summary.json'
Pipeline stage MKMLProfilerRunner completed in 3272.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-1111-quang-ir-mix-7721-v1-profiler is running
Tearing down inference service chaiml-1111-quang-ir-mix-7721-v1-profiler
Service chaiml-1111-quang-ir-mix-7721-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.82s
Shutdown handler de-registered
chaiml-1111-quang-ir-mix_7721_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1111-quang-ir-mix_7721_v1 status is now torndown due to DeploymentManager action