chaiml-1113-quang-ir-cl_78567

developer_uid: chai_backend_admin

submission_id: chaiml-1113-quang-ir-cl_78567_v1

model_name: training123

model_group: ChaiML/1113-quang-ir-cld

status: torndown

timestamp: 2025-11-16T21:06:33+00:00

num_battles: 5971

num_wins: 3054

celo_rating: 1289.45

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1113-quang-ir-cld-freev2-rm-fs07-dporm_freev22rm_0164642ep_5e6ct

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': 0.31769134035989566, 'latency_mean': 3.147583757638931, 'latency_p50': 2.909201741218567, 'latency_p90': 4.6643362760543825}, {'batch_size': 2, 'throughput': 0.5112468077623381, 'latency_mean': 3.904159824848175, 'latency_p50': 3.8723033666610718, 'latency_p90': 4.374815225601196}, {'batch_size': 3, 'throughput': 0.629310337713655, 'latency_mean': 4.764631482362748, 'latency_p50': 4.764898896217346, 'latency_p90': 5.506213235855102}, {'batch_size': 4, 'throughput': 0.7025734495677906, 'latency_mean': 5.670970324277878, 'latency_p50': 5.531836271286011, 'latency_p90': 6.702788043022156}, {'batch_size': 5, 'throughput': 0.7590999886155924, 'latency_mean': 6.553801161050797, 'latency_p50': 6.599842667579651, 'latency_p90': 7.5204199790954585}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1113-quang-ir-cld-freev2-rm-fs07-dporm_freev22rm_0164642ep_5e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.47

us_pacific_date: 2025-11-13

win_ratio: 0.5114721152235806

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-78567-v1-mkmlizer
Waiting for job on chaiml-1113-quang-ir-cl-78567-v1-mkmlizer to finish
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ║                                                                     ║
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: Downloaded to shared memory in 49.110s
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: Checking if ChaiML/1113-quang-ir-cld-freev2-rm-fs07-dporm_freev22rm_0164642ep_5e6ct already exists in ChaiML
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp104drn64, device:0
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: quantized model in 42.201s
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: Processed model ChaiML/1113-quang-ir-cld-freev2-rm-fs07-dporm_freev22rm_0164642ep_5e6ct in 91.312s
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-78567-v1/nvidia
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-78567-v1/nvidia/config.json
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-78567-v1/nvidia/special_tokens_map.json
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-78567-v1/nvidia/tokenizer_config.json
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-78567-v1/nvidia/tokenizer.json
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1113-quang-ir-cl-78567-v1/nvidia/flywheel_model.0.safetensors
chaiml-1113-quang-ir-cl-78567-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.49it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.05it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.31it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.22it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.54it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.61it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.20it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.69it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.69it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.23it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:16, 18.42it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:14, 21.15it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:13, 22.50it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.36it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 24.97it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 25.78it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 28.75it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:09, 28.43it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:09, 28.34it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 32.34it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.37it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.55it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.55it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:07, 31.28it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:07, 32.33it/s]
Loading 0:  34%|███▍      | 125/363 [00:04<00:07, 33.87it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.27it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 32.86it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.26it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.83it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.20it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.98it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 26.00it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.26it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.99it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.13it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.57it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 34.29it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 31.28it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 30.45it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 27.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:53,  2.82it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:32,  4.40it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.73it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:20,  6.66it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:16,  8.26it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 12.77it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:08, 14.66it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:06, 18.52it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 20.44it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 24.79it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:04, 25.83it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 32.90it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.05it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.96it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.05it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.64it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.84it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.30it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.15it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.33it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.89it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.84it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.60it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.96it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.34it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.23it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.12it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.55it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.10it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.69it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.27it/s]
                                                            
Job chaiml-1113-quang-ir-cl-78567-v1-mkmlizer completed after 165.43s with status: succeeded
Stopping job with name chaiml-1113-quang-ir-cl-78567-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1113-quang-ir-cl-78567-v1
Waiting for inference service chaiml-1113-quang-ir-cl-78567-v1 to be ready
Inference service chaiml-1113-quang-ir-cl-78567-v1 ready after 140.98638463020325s
Pipeline stage MKMLDeployer completed in 141.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6827826499938965s
Received healthy response to inference request in 2.2473561763763428s
Received healthy response to inference request in 2.1348800659179688s
Received healthy response to inference request in 2.290034055709839s
Received healthy response to inference request in 2.288621187210083s
5 requests
0 failed requests
5th percentile: 2.1573752880096437
10th percentile: 2.1798705101013183
20th percentile: 2.224860954284668
30th percentile: 2.2556091785430907
40th percentile: 2.272115182876587
50th percentile: 2.288621187210083
60th percentile: 2.2891863346099854
70th percentile: 2.289751482009888
80th percentile: 2.3685837745666505
90th percentile: 2.5256832122802733
95th percentile: 2.604232931137085
99th percentile: 2.6670727062225343
mean time: 2.328734827041626
Pipeline stage StressChecker completed in 13.16s
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_78567_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6099.69s
Shutdown handler de-registered
chaiml-1113-quang-ir-cl_78567_v1 status is now torndown due to DeploymentManager action