chaiml-1113-quang-ir-cl_57487

developer_uid: chai_backend_admin

submission_id: chaiml-1113-quang-ir-cl_57487_v1

model_name: training123

model_group: ChaiML/1113-quang-ir-cld

status: torndown

timestamp: 2025-11-16T10:56:41+00:00

num_battles: 5536

num_wins: 2951

celo_rating: 1304.3

family_friendly_score: 0.508

family_friendly_standard_error: 0.007070162657251953

submission_type: basic

model_repo: ChaiML/1113-quang-ir-cld-freev2-rm-f5000-dporm_freev22rm_0164642ep_4e6ct

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': 0.25654346354275454, 'latency_mean': 3.8978609144687653, 'latency_p50': 2.8928617238998413, 'latency_p90': 5.895998573303222}, {'batch_size': 2, 'throughput': 0.5736099258347197, 'latency_mean': 3.4802654933929444, 'latency_p50': 3.4761884212493896, 'latency_p90': 3.7533090829849245}, {'batch_size': 3, 'throughput': 0.7089497737124166, 'latency_mean': 4.216187245845795, 'latency_p50': 4.242153525352478, 'latency_p90': 4.635795331001281}, {'batch_size': 4, 'throughput': 0.8066109193275482, 'latency_mean': 4.935057777166366, 'latency_p50': 4.954395651817322, 'latency_p90': 5.694373369216919}, {'batch_size': 5, 'throughput': 0.8656634590336479, 'latency_mean': 5.758778072595597, 'latency_p50': 5.748706936836243, 'latency_p90': 6.548356509208679}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1113-quang-ir-cld-freev2-rm-f5000-dporm_freev22rm_0164642ep_4e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.27

us_pacific_date: 2025-11-13

win_ratio: 0.5330563583815029

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-1113-quang-ir-cl-57487-v1-mkmlizer
Waiting for job on chaiml-1113-quang-ir-cl-57487-v1-mkmlizer to finish
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: Downloaded to shared memory in 82.370s
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: Checking if ChaiML/1113-quang-ir-cld-freev2-rm-f5000-dporm_freev22rm_0164642ep_4e6ct already exists in ChaiML
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsolb2myw, device:0
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: quantized model in 41.882s
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: Processed model ChaiML/1113-quang-ir-cld-freev2-rm-f5000-dporm_freev22rm_0164642ep_4e6ct in 124.252s
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-57487-v1/nvidia
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-57487-v1/nvidia/config.json
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-57487-v1/nvidia/special_tokens_map.json
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-57487-v1/nvidia/tokenizer_config.json
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-57487-v1/nvidia/flywheel_model.1.safetensors
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-57487-v1/nvidia/flywheel_model.0.safetensors
chaiml-1113-quang-ir-cl-57487-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.32it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.48it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.29it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.17it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.87it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.41it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.38it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.94it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.85it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.45it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.23it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.63it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 31.22it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.64it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 31.80it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 33.09it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.98it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 28.19it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 32.53it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:09, 26.87it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:08, 29.29it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:12, 20.10it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:16, 15.35it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:12, 19.55it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:12, 19.45it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 27.13it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.49it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 31.43it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 30.49it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 37.20it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.11it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.40it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.61it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.00it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.30it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.52it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.61it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 31.02it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 30.07it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.67it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.13it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.69it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:42,  3.47it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:29,  4.90it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:20,  6.72it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:12, 10.36it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.18it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 18.28it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 22.59it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.95it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.35it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.97it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.10it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 26.41it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.65it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.78it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 31.20it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.57it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.47it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.85it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 31.03it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 30.03it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.56it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.46it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.53it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.72it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.77it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.00it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.71it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.53it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.16it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.36it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.89it/s]
                                                            
Job chaiml-1113-quang-ir-cl-57487-v1-mkmlizer completed after 174.68s with status: succeeded
Stopping job with name chaiml-1113-quang-ir-cl-57487-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.23s
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-1113-quang-ir-cl-57487-v1
Waiting for inference service chaiml-1113-quang-ir-cl-57487-v1 to be ready
Failed to get response for submission chaiml-1113-quang-ir-cl_80824_v1: ('http://chaiml-1113-quang-ir-cl-80824-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:44028->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-1113-quang-ir-cl-57487-v1 ready after 150.54484486579895s
Pipeline stage MKMLDeployer completed in 151.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7134780883789062s
Received healthy response to inference request in 2.25286602973938s
Received healthy response to inference request in 2.1240344047546387s
Received healthy response to inference request in 2.0920820236206055s
Received healthy response to inference request in 2.081188678741455s
5 requests
0 failed requests
5th percentile: 2.083367347717285
10th percentile: 2.0855460166931152
20th percentile: 2.0899033546447754
30th percentile: 2.098472499847412
40th percentile: 2.1112534523010256
50th percentile: 2.1240344047546387
60th percentile: 2.175567054748535
70th percentile: 2.2270997047424315
80th percentile: 2.3449884414672852
90th percentile: 2.5292332649230955
95th percentile: 2.621355676651001
99th percentile: 2.695053606033325
mean time: 2.2527298450469972
Pipeline stage StressChecker completed in 12.51s
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 0.68s
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-1113-quang-ir-cl_57487_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1113-quang-ir-cl-57487-v1-profiler
Waiting for inference service chaiml-1113-quang-ir-cl-57487-v1-profiler to be ready
Inference service chaiml-1113-quang-ir-cl-57487-v1-profiler ready after 151.1818664073944s
Pipeline stage MKMLProfilerDeployer completed in 151.85s
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-1113-quang-ir37eb12eeb141c3fedfeece2327e2c50b-deplo66x2r:/code/chaiverse_profiler_1763025410 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1113-quang-ir37eb12eeb141c3fedfeece2327e2c50b-deplo66x2r --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763025410 && 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_1763025410/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-1113-quang-ir37eb12eeb141c3fedfeece2327e2c50b-deplo66x2r:/code/chaiverse_profiler_1763026625 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1113-quang-ir37eb12eeb141c3fedfeece2327e2c50b-deplo66x2r --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763026625 && 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_1763026625/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1113-quang-ir37eb12eeb141c3fedfeece2327e2c50b-deplo66x2r --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1763026625/summary.json'
Pipeline stage MKMLProfilerRunner completed in 3107.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-1113-quang-ir-cl-57487-v1-profiler is running
Tearing down inference service chaiml-1113-quang-ir-cl-57487-v1-profiler
Service chaiml-1113-quang-ir-cl-57487-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.66s
Shutdown handler de-registered
chaiml-1113-quang-ir-cl_57487_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1113-quang-ir-cl_57487_v1 status is now torndown due to DeploymentManager action