developer_uid: chai_backend_admin
submission_id: chaiml-1106-quang-ir-mi_75573_v1
model_name: training123
model_group: ChaiML/1106-quang-ir-mix
status: torndown
timestamp: 2025-11-10T10:21:25+00:00
num_battles: 6299
num_wins: 3120
celo_rating: 1292.6
family_friendly_score: 0.5636
family_friendly_standard_error: 0.007013630158484265
submission_type: basic
model_repo: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-sth-f5000-dpo_00564642ep_2e6ct
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': 0.37828649699623285, 'latency_mean': 2.6434040236473084, 'latency_p50': 2.6466726064682007, 'latency_p90': 2.891125774383545}, {'batch_size': 2, 'throughput': 0.5624038163410335, 'latency_mean': 3.55546826839447, 'latency_p50': 3.543949842453003, 'latency_p90': 3.9046806573867796}, {'batch_size': 3, 'throughput': 0.6857718777813957, 'latency_mean': 4.359562126398086, 'latency_p50': 4.387012720108032, 'latency_p90': 4.801216793060302}, {'batch_size': 4, 'throughput': 0.778855044030216, 'latency_mean': 5.131419159173966, 'latency_p50': 5.135409832000732, 'latency_p90': 5.985101985931396}, {'batch_size': 5, 'throughput': 0.8334450258820072, 'latency_mean': 5.977968895435334, 'latency_p50': 6.0143654346466064, 'latency_p90': 6.7875325918197635}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-sth-f5000-dpo_00564642ep_2e6ct
model_size: 24B
ranking_group: single
throughput_3p7s: 0.59
us_pacific_date: 2025-11-07
win_ratio: 0.4953167169391967
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-1106-quang-ir-mi-75573-v1-mkmlizer
Waiting for job on chaiml-1106-quang-ir-mi-75573-v1-mkmlizer to finish
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ║                                                                     ║
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: Downloaded to shared memory in 71.158s
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: Checking if ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-sth-f5000-dpo_00564642ep_2e6ct already exists in ChaiML
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9ijxmqq0, device:0
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: quantized model in 42.651s
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: Processed model ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-sth-f5000-dpo_00564642ep_2e6ct in 113.809s
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-75573-v1/nvidia
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-75573-v1/nvidia/config.json
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-75573-v1/nvidia/special_tokens_map.json
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-75573-v1/nvidia/tokenizer_config.json
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-75573-v1/nvidia/tokenizer.json
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-75573-v1/nvidia/flywheel_model.1.safetensors
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-75573-v1/nvidia/flywheel_model.0.safetensors
chaiml-1106-quang-ir-mi-75573-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.28it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 38.86it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.20it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.76it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 35.69it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 40.25it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.29it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.90it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.76it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.15it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.16it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.44it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.13it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.40it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.40it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.57it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 26.90it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.26it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:08, 30.49it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 32.54it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 30.11it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 25.75it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 28.39it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.37it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 30.75it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.50it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 33.11it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.05it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.18it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 31.66it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.18it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.48it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.80it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.61it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.42it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.08it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.36it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.27it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.59it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.13it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.66it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:14,  2.08it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.39it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.70it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  5.94it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.17it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.45it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.33it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 16.76it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.97it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.63it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.59it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.05it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.55it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.48it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 24.12it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.63it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.57it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.23it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.49it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.55it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 24.91it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 24.86it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:02, 23.58it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 20.77it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 28.45it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 28.20it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 31.82it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 30.65it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 31.81it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.66it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 20.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.66it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 29.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.86it/s]
                                                            

Job chaiml-1106-quang-ir-mi-75573-v1-mkmlizer completed after 157.61s with status: succeeded
Stopping job with name chaiml-1106-quang-ir-mi-75573-v1-mkmlizer
Pipeline stage MKMLizer completed in 158.26s
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-1106-quang-ir-mi-75573-v1
Waiting for inference service chaiml-1106-quang-ir-mi-75573-v1 to be ready
Inference service chaiml-1106-quang-ir-mi-75573-v1 ready after 151.90767359733582s
Pipeline stage MKMLDeployer completed in 152.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4347736835479736s
Received healthy response to inference request in 2.5158045291900635s
Received healthy response to inference request in 2.3434691429138184s
Received healthy response to inference request in 2.14742112159729s
Received healthy response to inference request in 2.0595486164093018s
5 requests
0 failed requests
5th percentile: 2.0771231174468996
10th percentile: 2.094697618484497
20th percentile: 2.129846620559692
30th percentile: 2.1866307258605957
40th percentile: 2.265049934387207
50th percentile: 2.3434691429138184
60th percentile: 2.3799909591674804
70th percentile: 2.4165127754211424
80th percentile: 2.4509798526763915
90th percentile: 2.4833921909332277
95th percentile: 2.4995983600616456
99th percentile: 2.5125632953643797
mean time: 2.3002034187316895
Pipeline stage StressChecker completed in 12.91s
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 0.76s
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 0.72s
Shutdown handler de-registered
chaiml-1106-quang-ir-mi_75573_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1106-quang-ir-mi-75573-v1-profiler
Waiting for inference service chaiml-1106-quang-ir-mi-75573-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 2915.44s
Shutdown handler de-registered
chaiml-1106-quang-ir-mi_75573_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1106-quang-ir-mi_75573_v1 status is now torndown due to DeploymentManager action