chaiml-1106-quang-ir-mi_84594

developer_uid: chai_backend_admin

submission_id: chaiml-1106-quang-ir-mi_84594_v1

model_name: training123

model_group: ChaiML/1106-quang-ir-mix

status: torndown

timestamp: 2025-11-09T22:21:25+00:00

num_battles: 6512

num_wins: 3260

celo_rating: 1302.36

family_friendly_score: 0.5134000000000001

family_friendly_standard_error: 0.00706852799386124

submission_type: basic

model_repo: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f25000_2e616

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': 0.3816451505391141, 'latency_mean': 2.6201256453990935, 'latency_p50': 2.625600576400757, 'latency_p90': 2.8591091871261596}, {'batch_size': 2, 'throughput': 0.5763405200620068, 'latency_mean': 3.467753223180771, 'latency_p50': 3.4976887702941895, 'latency_p90': 3.7704342126846315}, {'batch_size': 3, 'throughput': 0.7089699676945177, 'latency_mean': 4.205038518905639, 'latency_p50': 4.248124122619629, 'latency_p90': 4.6494293212890625}, {'batch_size': 4, 'throughput': 0.8140847698987603, 'latency_mean': 4.900996176004409, 'latency_p50': 4.86935293674469, 'latency_p90': 5.595909643173218}, {'batch_size': 5, 'throughput': 0.8759026403244738, 'latency_mean': 5.678631238937378, 'latency_p50': 5.697974681854248, 'latency_p90': 6.549600887298584}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f25000_2e616

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-11-06

win_ratio: 0.5006142506142506

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>', '####\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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage MKMLizer
Starting job with name chaiml-1106-quang-ir-mi-84594-v1-mkmlizer
Waiting for job on chaiml-1106-quang-ir-mi-84594-v1-mkmlizer to finish
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-84594-v1-mkmlizer: Downloaded to shared memory in 65.406s
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: Checking if ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f25000_2e616 already exists in ChaiML
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxr6kfjla, device:0
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: quantized model in 43.007s
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: Processed model ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-f25000_2e616 in 108.413s
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-84594-v1/nvidia
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-84594-v1/nvidia/config.json
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-84594-v1/nvidia/special_tokens_map.json
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-84594-v1/nvidia/tokenizer_config.json
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-84594-v1/nvidia/flywheel_model.1.safetensors
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-84594-v1/nvidia/flywheel_model.0.safetensors
chaiml-1106-quang-ir-mi-84594-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.62it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.82it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.98it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.45it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.30it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 41.23it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.80it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.03it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.58it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.37it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.77it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.67it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.90it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.42it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 26.27it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.11it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.17it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.31it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.77it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.97it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.39it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.20it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.69it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.35it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.25it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.06it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.56it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.53it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.63it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 31.31it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 37.38it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.52it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:07, 27.24it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:06, 29.05it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.17it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 29.62it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.07it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.03it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.03it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.78it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 27.72it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.39it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:15,  1.19it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:58,  2.62it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:44,  3.37it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.75it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.02it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.22it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.51it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.92it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 19.17it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.89it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.81it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.59it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.11it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.02it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.70it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.00it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.88it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.77it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.82it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.00it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 31.88it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 28.72it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.01it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 23.58it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.30it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.45it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 32.74it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 31.04it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.11it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.09it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.17it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 20.38it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 27.38it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 26.99it/s]
                                                            
Job chaiml-1106-quang-ir-mi-84594-v1-mkmlizer completed after 185.91s with status: succeeded
Stopping job with name chaiml-1106-quang-ir-mi-84594-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.73s
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-1106-quang-ir-mi-84594-v1
Waiting for inference service chaiml-1106-quang-ir-mi-84594-v1 to be ready
Inference service chaiml-1106-quang-ir-mi-84594-v1 ready after 171.3051896095276s
Pipeline stage MKMLDeployer completed in 171.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3133256435394287s
Received healthy response to inference request in 2.1345086097717285s
Received healthy response to inference request in 2.2252585887908936s
Received healthy response to inference request in 2.1989829540252686s
Received healthy response to inference request in 2.1038506031036377s
5 requests
0 failed requests
5th percentile: 2.109982204437256
10th percentile: 2.116113805770874
20th percentile: 2.12837700843811
30th percentile: 2.1474034786224365
40th percentile: 2.1731932163238525
50th percentile: 2.1989829540252686
60th percentile: 2.2094932079315184
70th percentile: 2.2200034618377686
80th percentile: 2.2428719997406006
90th percentile: 2.2780988216400146
95th percentile: 2.2957122325897217
99th percentile: 2.3098029613494875
mean time: 2.1951852798461915
Pipeline stage StressChecker completed in 12.38s
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 0.70s
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-1106-quang-ir-mi_84594_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3036.74s
Shutdown handler de-registered
chaiml-1106-quang-ir-mi_84594_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1106-quang-ir-mi_84594_v1 status is now torndown due to DeploymentManager action