developer_uid: chai_backend_admin
submission_id: chaiml-1114-quang-ir-cld_7634_v1
model_name: training123
model_group: ChaiML/1114-quang-ir-cld
status: torndown
timestamp: 2025-11-17T20:06:25+00:00
num_battles: 5651
num_wins: 2958
celo_rating: 1301.51
family_friendly_score: 0.469
family_friendly_standard_error: 0.00705746413380897
submission_type: basic
model_repo: ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_4e5cs
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': 0.2776689726737405, 'latency_mean': 3.6013043320178983, 'latency_p50': 2.88199520111084, 'latency_p90': 5.3804656028747555}, {'batch_size': 2, 'throughput': 0.5536369139182176, 'latency_mean': 3.605177239179611, 'latency_p50': 3.574441075325012, 'latency_p90': 3.9086448431015013}, {'batch_size': 3, 'throughput': 0.6791967396242797, 'latency_mean': 4.409064618349075, 'latency_p50': 4.412482500076294, 'latency_p90': 4.7815468311309814}, {'batch_size': 4, 'throughput': 0.767566007104595, 'latency_mean': 5.195892961025238, 'latency_p50': 5.2030826807022095, 'latency_p90': 6.001588034629822}, {'batch_size': 5, 'throughput': 0.8206629029516582, 'latency_mean': 6.060453248023987, 'latency_p50': 6.0945481061935425, 'latency_p90': 6.8854172945022585}]
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_4e5cs
model_size: 24B
ranking_group: single
throughput_3p7s: 0.57
us_pacific_date: 2025-11-14
win_ratio: 0.5234471774907096
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-1114-quang-ir-cld-7634-v1-mkmlizer
Waiting for job on chaiml-1114-quang-ir-cld-7634-v1-mkmlizer to finish
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: Downloaded to shared memory in 83.179s
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: Checking if ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_4e5cs already exists in ChaiML
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp18mifob_, device:0
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: quantized model in 42.671s
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: Processed model ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_4e5cs in 125.851s
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1114-quang-ir-cld-7634-v1/nvidia
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cld-7634-v1/nvidia/config.json
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cld-7634-v1/nvidia/special_tokens_map.json
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cld-7634-v1/nvidia/tokenizer_config.json
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cld-7634-v1/nvidia/tokenizer.json
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1114-quang-ir-cld-7634-v1/nvidia/flywheel_model.1.safetensors
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1114-quang-ir-cld-7634-v1/nvidia/flywheel_model.0.safetensors
chaiml-1114-quang-ir-cld-7634-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.73it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.39it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.00it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.59it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 45.09it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 31.25it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 29.02it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.37it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.22it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.87it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.02it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.49it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.71it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.65it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.61it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.74it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.22it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.72it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.14it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.57it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.40it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.82it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.33it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 32.56it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:07, 32.86it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.73it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.12it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.21it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.17it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.54it/s]
Loading 0:  42%|████▏     | 153/363 [00:04<00:08, 25.45it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.22it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.32it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:07, 26.65it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:06, 30.44it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:06, 27.10it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:07, 24.83it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.68it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:08, 19.74it/s]
Loading 0:  53%|█████▎    | 193/363 [00:06<00:09, 18.76it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:08, 18.58it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:43,  1.01s/it]
Loading 0:  56%|█████▌    | 203/363 [00:19<02:15,  1.18it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:22,  1.89it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<01:01,  2.45it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:46,  3.22it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:31,  4.62it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:24,  5.90it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.18it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.56it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.50it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 17.09it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 19.28it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 24.08it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 25.27it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.80it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 29.18it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.73it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 24.58it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.78it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 32.01it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.51it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.84it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.15it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.85it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.71it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 27.51it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 22.72it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 29.74it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 28.42it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 30.97it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 28.71it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 29.43it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 30.15it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 18.93it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 20.46it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 27.30it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 27.00it/s]
                                                            

Job chaiml-1114-quang-ir-cld-7634-v1-mkmlizer completed after 206.42s with status: succeeded
Stopping job with name chaiml-1114-quang-ir-cld-7634-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.12s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.28s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1114-quang-ir-cld-7634-v1
Waiting for inference service chaiml-1114-quang-ir-cld-7634-v1 to be ready
Inference service chaiml-1114-quang-ir-cld-7634-v1 ready after 150.78411889076233s
Pipeline stage MKMLDeployer completed in 151.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.41474986076355s
Received healthy response to inference request in 2.6410341262817383s
Received healthy response to inference request in 2.410391330718994s
Received healthy response to inference request in 2.1486995220184326s
Received healthy response to inference request in 2.1527228355407715s
5 requests
0 failed requests
5th percentile: 2.1495041847229004
10th percentile: 2.150308847427368
20th percentile: 2.1519181728363037
30th percentile: 2.204256534576416
40th percentile: 2.307323932647705
50th percentile: 2.410391330718994
60th percentile: 2.4121347427368165
70th percentile: 2.413878154754639
80th percentile: 2.4600067138671875
90th percentile: 2.550520420074463
95th percentile: 2.5957772731781006
99th percentile: 2.631982755661011
mean time: 2.3535195350646974
Pipeline stage StressChecker completed in 13.89s
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 0.69s
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 0.65s
Shutdown handler de-registered
chaiml-1114-quang-ir-cld_7634_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 0.10s
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-1114-quang-ir-cld-7634-v1-profiler
Waiting for inference service chaiml-1114-quang-ir-cld-7634-v1-profiler to be ready
Inference service chaiml-1114-quang-ir-cld-7634-v1-profiler ready after 161.54753518104553s
Pipeline stage MKMLProfilerDeployer completed in 162.23s
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-ir3086a3d0050fe34231f3b027487923b6-deplo6pdlq:/code/chaiverse_profiler_1763146402 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1114-quang-ir3086a3d0050fe34231f3b027487923b6-deplo6pdlq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763146402 && 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_1763146402/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-ir3086a3d0050fe34231f3b027487923b6-deplo6pdlq:/code/chaiverse_profiler_1763147515 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1114-quang-ir3086a3d0050fe34231f3b027487923b6-deplo6pdlq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763147515 && 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_1763147515/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-1114-quang-ir3086a3d0050fe34231f3b027487923b6-deplo6pdlq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1763147515/summary.json'
Pipeline stage MKMLProfilerRunner completed in 2998.28s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-1114-quang-ir-cld-7634-v1-profiler is running
Tearing down inference service chaiml-1114-quang-ir-cld-7634-v1-profiler
Service chaiml-1114-quang-ir-cld-7634-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.84s
Shutdown handler de-registered
chaiml-1114-quang-ir-cld_7634_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1114-quang-ir-cld_7634_v1 status is now torndown due to DeploymentManager action