chaiml-1114-quang-ir-cl_60880

developer_uid: chai_backend_admin

submission_id: chaiml-1114-quang-ir-cl_60880_v1

model_name: training123

model_group: ChaiML/1114-quang-ir-cld

status: torndown

timestamp: 2025-11-17T20:06:24+00:00

num_battles: 5665

num_wins: 2981

celo_rating: 1305.08

family_friendly_score: 0.4756

family_friendly_standard_error: 0.007062643131292986

submission_type: basic

model_repo: ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_5e5cs

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': 0.28660915750494403, 'latency_mean': 3.4889478349685668, 'latency_p50': 2.788951873779297, 'latency_p90': 5.332172060012818}, {'batch_size': 2, 'throughput': 0.5618018738446103, 'latency_mean': 3.5521734809875487, 'latency_p50': 3.548563241958618, 'latency_p90': 3.834656763076782}, {'batch_size': 3, 'throughput': 0.6951307093209631, 'latency_mean': 4.305247311592102, 'latency_p50': 4.293483376502991, 'latency_p90': 4.79250099658966}, {'batch_size': 4, 'throughput': 0.7879925197012126, 'latency_mean': 5.0585581803321835, 'latency_p50': 5.063571929931641, 'latency_p90': 5.693514108657837}, {'batch_size': 5, 'throughput': 0.8466721583863532, 'latency_mean': 5.900532867908478, 'latency_p50': 5.910497546195984, 'latency_p90': 6.716070818901062}]

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_5e5cs

model_size: 24B

ranking_group: single

throughput_3p7s: 0.59

us_pacific_date: 2025-11-14

win_ratio: 0.5262135922330097

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>', '####', '\n', '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-1114-quang-ir-cl-60880-v1-mkmlizer
Waiting for job on chaiml-1114-quang-ir-cl-60880-v1-mkmlizer to finish
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ║                                                                     ║
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: Downloaded to shared memory in 82.739s
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: Checking if ChaiML/1114-quang-ir-cld-mult25k-rm-fs06-b16-dporm_mult25k_0164642ep_5e5cs already exists in ChaiML
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaa_1nip_, device:0
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-60880-v1/nvidia
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-60880-v1/nvidia/config.json
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-60880-v1/nvidia/special_tokens_map.json
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-60880-v1/nvidia/tokenizer_config.json
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-60880-v1/nvidia/tokenizer.json
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-60880-v1/nvidia/flywheel_model.1.safetensors
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1114-quang-ir-cl-60880-v1/nvidia/flywheel_model.0.safetensors
chaiml-1114-quang-ir-cl-60880-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.56it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.05it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.94it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.61it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.98it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 29.82it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.28it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.68it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.79it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.83it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 34.39it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:07, 37.56it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:10, 28.27it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:09, 29.54it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:10, 26.59it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 32.24it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:08, 31.20it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:08, 30.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.80it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.58it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.85it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 31.42it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.89it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 33.06it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:07, 33.61it/s]
Loading 0:  36%|███▌      | 130/363 [00:04<00:06, 34.40it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:06, 34.21it/s]
Loading 0:  38%|███▊      | 139/363 [00:04<00:06, 34.37it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 34.97it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.90it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.41it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.44it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.84it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.77it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.20it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.42it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 34.33it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 31.20it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 30.20it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.93it/s]
Loading 0:  55%|█████▌    | 201/363 [00:18<02:13,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:19<00:39,  3.74it/s]
Loading 0:  60%|██████    | 219/363 [00:19<00:28,  5.00it/s]
Loading 0:  62%|██████▏   | 224/363 [00:19<00:19,  7.01it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:13,  9.64it/s]
Loading 0:  64%|██████▍   | 233/363 [00:20<00:10, 12.02it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.65it/s]
Loading 0:  66%|██████▌   | 240/363 [00:20<00:08, 14.85it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 20.56it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 22.40it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 26.92it/s]
Loading 0:  71%|███████▏  | 259/363 [00:20<00:03, 26.96it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.47it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:03, 23.95it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.62it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 31.68it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 30.98it/s]
Loading 0:  80%|████████  | 291/363 [00:21<00:02, 34.38it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.89it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.76it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 31.33it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 30.33it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 26.82it/s]
Loading 0:  88%|████████▊ | 318/363 [00:22<00:01, 32.61it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.09it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.78it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.91it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 34.01it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 34.93it/s]
Loading 0:  94%|█████████▍| 343/363 [00:23<00:00, 21.29it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.84it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 30.33it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.94it/s]
                                                            
Job chaiml-1114-quang-ir-cl-60880-v1-mkmlizer completed after 206.38s with status: succeeded
Stopping job with name chaiml-1114-quang-ir-cl-60880-v1-mkmlizer
Pipeline stage MKMLizer completed in 206.90s
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-1114-quang-ir-cl-60880-v1
Waiting for inference service chaiml-1114-quang-ir-cl-60880-v1 to be ready
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', '')
Inference service chaiml-1114-quang-ir-cl-60880-v1 ready after 161.6140444278717s
Pipeline stage MKMLDeployer completed in 162.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0050694942474365s
Received healthy response to inference request in 2.347383499145508s
Received healthy response to inference request in 2.146836519241333s
Received healthy response to inference request in 2.09737229347229s
Received healthy response to inference request in 2.460867166519165s
5 requests
0 failed requests
5th percentile: 2.1072651386260985
10th percentile: 2.117157983779907
20th percentile: 2.1369436740875245
30th percentile: 2.186945915222168
40th percentile: 2.267164707183838
50th percentile: 2.347383499145508
60th percentile: 2.3927769660949707
70th percentile: 2.4381704330444336
80th percentile: 2.5697076320648193
90th percentile: 2.787388563156128
95th percentile: 2.8962290287017822
99th percentile: 2.9833014011383057
mean time: 2.4115057945251466
Pipeline stage StressChecker completed in 13.88s
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 0.65s
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 0.67s
Shutdown handler de-registered
chaiml-1114-quang-ir-cl_60880_v1 status is now deployed due to DeploymentManager action
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-cl-60880-v1-profiler
Waiting for inference service chaiml-1114-quang-ir-cl-60880-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3115.35s
Shutdown handler de-registered
chaiml-1114-quang-ir-cl_60880_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1114-quang-ir-cl_60880_v1 status is now torndown due to DeploymentManager action