chaiml-1108-quang-ir-mi_39031

developer_uid: chai_backend_admin

submission_id: chaiml-1108-quang-ir-mi_39031_v1

model_name: training123

model_group: ChaiML/1108-quang-ir-mix

status: torndown

timestamp: 2025-11-11T14:36:37+00:00

num_battles: 5969

num_wins: 2923

celo_rating: 1302.57

family_friendly_score: 0.5384

family_friendly_standard_error: 0.00705018354371005

submission_type: basic

model_repo: ChaiML/1108-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_mult25k_0164641ep_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': 0.381325565616325, 'latency_mean': 2.6223327362537385, 'latency_p50': 2.627737522125244, 'latency_p90': 2.8774561405181887}, {'batch_size': 2, 'throughput': 0.5660680334782409, 'latency_mean': 3.5239587736129763, 'latency_p50': 3.5112794637680054, 'latency_p90': 3.8159271240234376}, {'batch_size': 3, 'throughput': 0.6958204980186923, 'latency_mean': 4.30061753153801, 'latency_p50': 4.305165886878967, 'latency_p90': 4.63046281337738}, {'batch_size': 4, 'throughput': 0.7902936856322041, 'latency_mean': 5.041498287916183, 'latency_p50': 5.033757925033569, 'latency_p90': 5.842028975486755}, {'batch_size': 5, 'throughput': 0.8540950152053377, 'latency_mean': 5.820459043979644, 'latency_p50': 5.815169334411621, 'latency_p90': 6.722905468940735}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1108-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_mult25k_0164641ep_5e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-08

win_ratio: 0.48969676662757583

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': ['You:', '\n', '####', '</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-1108-quang-ir-mi-39031-v1-mkmlizer
Waiting for job on chaiml-1108-quang-ir-mi-39031-v1-mkmlizer to finish
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: Downloaded to shared memory in 61.300s
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: Checking if ChaiML/1108-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_mult25k_0164641ep_5e6ct already exists in ChaiML
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpipy67y08, device:0
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: quantized model in 42.411s
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: Processed model ChaiML/1108-quang-ir-mixall-cld-i8a8-hl-mult-f5000-dpo_mult25k_0164641ep_5e6ct in 103.712s
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-39031-v1/nvidia
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-39031-v1/nvidia/config.json
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-39031-v1/nvidia/special_tokens_map.json
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-39031-v1/nvidia/tokenizer_config.json
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-39031-v1/nvidia/tokenizer.json
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-39031-v1/nvidia/flywheel_model.0.safetensors
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-39031-v1/nvidia/flywheel_model.1.safetensors
chaiml-1108-quang-ir-mi-39031-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.68it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.83it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 41.03it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:09, 35.89it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 45.63it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 29.12it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.65it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 34.13it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.90it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 34.45it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 34.89it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.11it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.46it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 26.12it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.19it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.48it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.00it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 25.13it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 29.57it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:12, 20.73it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:10, 23.50it/s]
Loading 0:  30%|███       | 109/363 [00:03<00:13, 18.25it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:14, 17.65it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:13, 17.75it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:12, 19.50it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:11, 20.26it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.97it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.71it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 32.52it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 30.64it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 37.60it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.77it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.27it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.45it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.45it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 34.19it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.51it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.41it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.39it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.62it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.84it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.72it/s]
Loading 0:  60%|██████    | 219/363 [00:20<00:29,  4.96it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.91it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.51it/s]
Loading 0:  64%|██████▍   | 233/363 [00:20<00:11, 11.75it/s]
Loading 0:  66%|██████▌   | 238/363 [00:21<00:08, 15.05it/s]
Loading 0:  67%|██████▋   | 242/363 [00:21<00:06, 17.97it/s]
Loading 0:  68%|██████▊   | 247/363 [00:21<00:05, 21.41it/s]
Loading 0:  69%|██████▉   | 251/363 [00:21<00:04, 24.26it/s]
Loading 0:  71%|███████   | 256/363 [00:21<00:03, 26.98it/s]
Loading 0:  72%|███████▏  | 260/363 [00:21<00:03, 29.41it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.26it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 25.42it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.17it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.48it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.24it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.49it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.93it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.94it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 30.15it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.90it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.16it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.00it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.88it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.38it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:00, 32.78it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 33.63it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.24it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.58it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.16it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.79it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 29.58it/s]
                                                            
Job chaiml-1108-quang-ir-mi-39031-v1-mkmlizer completed after 176.03s with status: succeeded
Stopping job with name chaiml-1108-quang-ir-mi-39031-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.61s
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-1108-quang-ir-mi-39031-v1
Waiting for inference service chaiml-1108-quang-ir-mi-39031-v1 to be ready
Inference service chaiml-1108-quang-ir-mi-39031-v1 ready after 180.67980122566223s
Pipeline stage MKMLDeployer completed in 181.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.813261032104492s
Received healthy response to inference request in 2.157076835632324s
Received healthy response to inference request in 2.240281105041504s
Received healthy response to inference request in 2.6177916526794434s
Received healthy response to inference request in 2.091930627822876s
5 requests
0 failed requests
5th percentile: 2.1049598693847655
10th percentile: 2.117989110946655
20th percentile: 2.1440475940704347
30th percentile: 2.1737176895141603
40th percentile: 2.206999397277832
50th percentile: 2.240281105041504
60th percentile: 2.3912853240966796
70th percentile: 2.5422895431518553
80th percentile: 2.656885528564453
90th percentile: 2.735073280334473
95th percentile: 2.7741671562194825
99th percentile: 2.80544225692749
mean time: 2.384068250656128
Pipeline stage StressChecker completed in 13.44s
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 0.92s
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-1108-quang-ir-mi_39031_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 3153.43s
Shutdown handler de-registered
chaiml-1108-quang-ir-mi_39031_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1108-quang-ir-mi_39031_v1 status is now torndown due to DeploymentManager action