chaiml-1114-quang-ir-cl_61867

developer_uid: chai_backend_admin

submission_id: chaiml-1114-quang-ir-cl_61867_v1

model_name: training123

model_group: ChaiML/1114-quang-ir-cld

status: torndown

timestamp: 2025-11-17T20:06:25+00:00

num_battles: 5909

num_wins: 3059

celo_rating: 1300.57

family_friendly_score: 0.45799999999999996

family_friendly_standard_error: 0.0070460769226570324

submission_type: basic

model_repo: ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_2e5cs

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': 0.31841858089100744, 'latency_mean': 3.140419918298721, 'latency_p50': 2.7233344316482544, 'latency_p90': 5.158252286911011}, {'batch_size': 2, 'throughput': 0.5555329677853159, 'latency_mean': 3.5931485521793367, 'latency_p50': 3.5836974382400513, 'latency_p90': 3.8668498039245605}, {'batch_size': 3, 'throughput': 0.6845953904976093, 'latency_mean': 4.363154678344727, 'latency_p50': 4.367054224014282, 'latency_p90': 4.727863001823425}, {'batch_size': 4, 'throughput': 0.7754037090415595, 'latency_mean': 5.1490227663517, 'latency_p50': 5.109687328338623, 'latency_p90': 5.974729990959167}, {'batch_size': 5, 'throughput': 0.833682299031337, 'latency_mean': 5.973130177259446, 'latency_p50': 6.009559392929077, 'latency_p90': 6.820548939704895}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_2e5cs

model_size: 24B

ranking_group: single

throughput_3p7s: 0.58

us_pacific_date: 2025-11-14

win_ratio: 0.5176848874598071

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-1114-quang-ir-cl-61867-v1-mkmlizer
Waiting for job on chaiml-1114-quang-ir-cl-61867-v1-mkmlizer to finish
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: Downloaded to shared memory in 80.295s
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: Checking if ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_2e5cs already exists in ChaiML
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplep2m5ac, device:0
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: quantized model in 41.764s
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: Processed model ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_2e5cs in 122.060s
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-61867-v1/nvidia
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-61867-v1/nvidia/config.json
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-61867-v1/nvidia/special_tokens_map.json
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-61867-v1/nvidia/tokenizer_config.json
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-61867-v1/nvidia/tokenizer.json
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-61867-v1/nvidia/flywheel_model.0.safetensors
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-61867-v1/nvidia/flywheel_model.1.safetensors
chaiml-1114-quang-ir-cl-61867-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.23it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 40.03it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 43.28it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.61it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.14it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 32.20it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 30.40it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 34.10it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 34.13it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 34.68it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 35.07it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:07, 38.31it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:09, 29.31it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:09, 30.42it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:10, 27.75it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 33.61it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:08, 32.14it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:08, 31.18it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:07, 34.64it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.92it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.97it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 31.46it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 32.01it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 32.86it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:07, 33.44it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 34.24it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:06, 35.08it/s]
Loading 0:  38%|███▊      | 139/363 [00:04<00:06, 35.48it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 35.18it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.35it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.98it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 26.17it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 33.70it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 32.60it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.92it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:06, 28.97it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:08, 22.23it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:07, 23.42it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:09, 18.82it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:09, 18.06it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:11,  1.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.67it/s]
Loading 0:  59%|█████▉    | 215/363 [00:19<00:39,  3.71it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.73it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.05it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:18,  7.35it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.77it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.72it/s]
Loading 0:  65%|██████▍   | 235/363 [00:20<00:08, 14.85it/s]
Loading 0:  66%|██████▌   | 238/363 [00:20<00:07, 17.00it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 18.55it/s]
Loading 0:  67%|██████▋   | 244/363 [00:20<00:05, 20.51it/s]
Loading 0:  68%|██████▊   | 248/363 [00:21<00:05, 19.21it/s]
Loading 0:  70%|██████▉   | 253/363 [00:21<00:04, 24.54it/s]
Loading 0:  71%|███████   | 257/363 [00:21<00:04, 22.88it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.13it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:03, 24.54it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 25.10it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 32.10it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 31.14it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 34.39it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.67it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.61it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 31.24it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 30.25it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 27.35it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 33.38it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 32.21it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 35.57it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 33.21it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 34.09it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.83it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 21.29it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.83it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 30.57it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 30.38it/s]
                                                            
Job chaiml-1114-quang-ir-cl-61867-v1-mkmlizer completed after 165.52s with status: succeeded
Stopping job with name chaiml-1114-quang-ir-cl-61867-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.10s
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-1114-quang-ir-cl-61867-v1
Waiting for inference service chaiml-1114-quang-ir-cl-61867-v1 to be ready
Inference service chaiml-1114-quang-ir-cl-61867-v1 ready after 151.06914830207825s
Pipeline stage MKMLDeployer completed in 151.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5082812309265137s
Received healthy response to inference request in 2.4367761611938477s
Received healthy response to inference request in 2.628329038619995s
Received healthy response to inference request in 2.1991634368896484s
Received healthy response to inference request in 2.544928550720215s
5 requests
0 failed requests
5th percentile: 2.2466859817504883
10th percentile: 2.294208526611328
20th percentile: 2.389253616333008
30th percentile: 2.451077175140381
40th percentile: 2.4796792030334474
50th percentile: 2.5082812309265137
60th percentile: 2.522940158843994
70th percentile: 2.5375990867614746
80th percentile: 2.561608648300171
90th percentile: 2.594968843460083
95th percentile: 2.611648941040039
99th percentile: 2.624993019104004
mean time: 2.463495683670044
Pipeline stage StressChecker completed in 13.63s
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 1.13s
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 0.71s
Shutdown handler de-registered
chaiml-1114-quang-ir-cl_61867_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-1114-quang-ir-cl-61867-v1-profiler
Waiting for inference service chaiml-1114-quang-ir-cl-61867-v1-profiler to be ready
Inference service chaiml-1114-quang-ir-cl-61867-v1-profiler ready after 161.6298167705536s
Pipeline stage MKMLProfilerDeployer completed in 162.51s
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-1114-quang-ir68d390ee23f7997ed666c1163fb6a904-deplonbnpm:/code/chaiverse_profiler_1763146266 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1114-quang-ir68d390ee23f7997ed666c1163fb6a904-deplonbnpm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763146266 && 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_1763146266/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-1114-quang-ir68d390ee23f7997ed666c1163fb6a904-deplonbnpm:/code/chaiverse_profiler_1763147520 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1114-quang-ir68d390ee23f7997ed666c1163fb6a904-deplonbnpm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763147520 && 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_1763147520/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1114-quang-ir68d390ee23f7997ed666c1163fb6a904-deplonbnpm --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1763147520/summary.json'
Pipeline stage MKMLProfilerRunner completed in 3036.61s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-1114-quang-ir-cl-61867-v1-profiler is running
Tearing down inference service chaiml-1114-quang-ir-cl-61867-v1-profiler
Service chaiml-1114-quang-ir-cl-61867-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.74s
Shutdown handler de-registered
chaiml-1114-quang-ir-cl_61867_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1114-quang-ir-cl_61867_v1 status is now torndown due to DeploymentManager action