chaiml-1106-quang-ir-mi_12481

developer_uid: chai_backend_admin

submission_id: chaiml-1106-quang-ir-mi_12481_v1

model_name: training123

model_group: ChaiML/1106-quang-ir-mix

status: torndown

timestamp: 2025-11-09T17:56:49+00:00

num_battles: 5467

num_wins: 2771

celo_rating: 1306.52

family_friendly_score: 0.5631999999999999

family_friendly_standard_error: 0.007014353284515972

submission_type: basic

model_repo: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f15000-dpo_0164642ep

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': 0.38001570327799133, 'latency_mean': 2.6313465785980226, 'latency_p50': 2.63948655128479, 'latency_p90': 2.8671353578567507}, {'batch_size': 2, 'throughput': 0.577333506496973, 'latency_mean': 3.459328656196594, 'latency_p50': 3.4611481428146362, 'latency_p90': 3.7692791938781736}, {'batch_size': 3, 'throughput': 0.7066527884884071, 'latency_mean': 4.224783097505569, 'latency_p50': 4.21469247341156, 'latency_p90': 4.562752771377563}, {'batch_size': 4, 'throughput': 0.8112456296499541, 'latency_mean': 4.912357195615768, 'latency_p50': 4.934717416763306, 'latency_p90': 5.449467611312866}, {'batch_size': 5, 'throughput': 0.8651756958618266, 'latency_mean': 5.743227463960648, 'latency_p50': 5.726882100105286, 'latency_p90': 6.59597601890564}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f15000-dpo_0164642ep

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-11-06

win_ratio: 0.5068593378452534

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', 'You:', '</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-1106-quang-ir-mi-12481-v1-mkmlizer
Waiting for job on chaiml-1106-quang-ir-mi-12481-v1-mkmlizer to finish
Failed to get response for submission chaiml-prm-v1-pair-llam_69602_v1: HTTPConnectionPool(host='chaiml-prm-v1-pair-llam-69602-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
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-1106-quang-ir-mi-12481-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: Downloaded to shared memory in 58.179s
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: Checking if ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f15000-dpo_0164642ep already exists in ChaiML
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzm5ipi06, device:0
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: quantized model in 42.131s
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: Processed model ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f15000-dpo_0164642ep in 100.310s
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-12481-v1/nvidia
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-12481-v1/nvidia/config.json
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-12481-v1/nvidia/special_tokens_map.json
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-12481-v1/nvidia/tokenizer_config.json
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-12481-v1/nvidia/tokenizer.json
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-12481-v1/nvidia/flywheel_model.1.safetensors
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-12481-v1/nvidia/flywheel_model.0.safetensors
chaiml-1106-quang-ir-mi-12481-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.67it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.14it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 38.57it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 38.37it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 41.59it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.56it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.15it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.93it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.87it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.61it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 34.29it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 35.15it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:07, 38.30it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:09, 29.57it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:09, 30.41it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:10, 27.21it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 32.82it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:08, 31.58it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:08, 30.33it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:07, 33.65it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.36it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.31it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.32it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.03it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.12it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.63it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 34.99it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.85it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.01it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.63it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.90it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.30it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:08, 25.39it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.60it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.31it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.44it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.28it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.18it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.35it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 24.87it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 21.90it/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<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.67it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.43it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:30,  4.82it/s]
Loading 0:  61%|██████    | 221/363 [00:19<00:23,  6.11it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:18,  7.33it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.69it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.62it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.29it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 17.42it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 21.99it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 23.56it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.89it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.15it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:03, 24.32it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 22.91it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 29.91it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.60it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.70it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 29.94it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 31.13it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 29.13it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.81it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.40it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.24it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.02it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.70it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.97it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 31.55it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 31.56it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.80it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.55it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.06it/s]
                                                            
Job chaiml-1106-quang-ir-mi-12481-v1-mkmlizer completed after 788.01s with status: succeeded
Stopping job with name chaiml-1106-quang-ir-mi-12481-v1-mkmlizer
Pipeline stage MKMLizer completed in 788.68s
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-1106-quang-ir-mi-12481-v1
Waiting for inference service chaiml-1106-quang-ir-mi-12481-v1 to be ready
Inference service chaiml-1106-quang-ir-mi-12481-v1 ready after 352.5951268672943s
Pipeline stage MKMLDeployer completed in 353.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.38771915435791s
Received healthy response to inference request in 2.4632551670074463s
Received healthy response to inference request in 2.4362688064575195s
Received healthy response to inference request in 2.5016491413116455s
Received healthy response to inference request in 2.568530559539795s
5 requests
0 failed requests
5th percentile: 2.397429084777832
10th percentile: 2.407139015197754
20th percentile: 2.4265588760375976
30th percentile: 2.441666078567505
40th percentile: 2.4524606227874757
50th percentile: 2.4632551670074463
60th percentile: 2.478612756729126
70th percentile: 2.493970346450806
80th percentile: 2.515025424957275
90th percentile: 2.541777992248535
95th percentile: 2.555154275894165
99th percentile: 2.565855302810669
mean time: 2.471484565734863
Pipeline stage StressChecker completed in 13.84s
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 0.99s
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 0.70s
Shutdown handler de-registered
chaiml-1106-quang-ir-mi_12481_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4373.85s
Shutdown handler de-registered
chaiml-1106-quang-ir-mi_12481_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1106-quang-ir-mi_12481_v1 status is now torndown due to DeploymentManager action