developer_uid: chai_backend_admin
submission_id: chaiml-1106-quang-ir-mi_31446_v1
model_name: training123
model_group: ChaiML/1106-quang-ir-mix
status: torndown
timestamp: 2025-11-10T09:36:38+00:00
num_battles: 5450
num_wins: 2736
celo_rating: 1289.2
family_friendly_score: 0.5392
family_friendly_standard_error: 0.0070493029442633545
submission_type: basic
model_repo: ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-sth-f5000-dpo_00564641ep_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': 0.3323055931261836, 'latency_mean': 3.0091577625274657, 'latency_p50': 2.622572660446167, 'latency_p90': 3.230684947967514}, {'batch_size': 2, 'throughput': 0.5685018372037032, 'latency_mean': 3.5108176600933074, 'latency_p50': 3.523905873298645, 'latency_p90': 3.821395111083984}, {'batch_size': 3, 'throughput': 0.7084445283518582, 'latency_mean': 4.2181367635726925, 'latency_p50': 4.204607129096985, 'latency_p90': 4.579310297966003}, {'batch_size': 4, 'throughput': 0.8047216662501853, 'latency_mean': 4.95781707406044, 'latency_p50': 4.93838107585907, 'latency_p90': 5.669526934623718}, {'batch_size': 5, 'throughput': 0.8698341149865082, 'latency_mean': 5.733698295354843, 'latency_p50': 5.740326642990112, 'latency_p90': 6.444159412384034}]
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_00564641ep_2e6ct
model_size: 24B
ranking_group: single
throughput_3p7s: 0.61
us_pacific_date: 2025-11-07
win_ratio: 0.5020183486238532
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-1106-quang-ir-mi-31446-v1-mkmlizer
Waiting for job on chaiml-1106-quang-ir-mi-31446-v1-mkmlizer to finish
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ Version: 0.30.2 ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ belonging to: ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ║ ║
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: Downloaded to shared memory in 60.882s
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: Checking if ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-sth-f5000-dpo_00564641ep_2e6ct already exists in ChaiML
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqo991e_m, device:0
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: quantized model in 42.674s
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: Processed model ChaiML/1106-quang-ir-mixall-cld-i8a8-hl-mult-sth-f5000-dpo_00564641ep_2e6ct in 103.556s
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-31446-v1/nvidia
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-31446-v1/nvidia/config.json
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-31446-v1/nvidia/special_tokens_map.json
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-31446-v1/nvidia/tokenizer_config.json
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-31446-v1/nvidia/tokenizer.json
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-31446-v1/nvidia/flywheel_model.1.safetensors
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1106-quang-ir-mi-31446-v1/nvidia/flywheel_model.0.safetensors
chaiml-1106-quang-ir-mi-31446-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 22.38it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:09, 38.22it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:08, 40.35it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:10, 31.22it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:07, 42.32it/s] Loading 0: 10%|█ | 37/363 [00:01<00:11, 28.03it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:12, 25.63it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 32.75it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:09, 32.34it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:09, 33.10it/s] Loading 0: 17%|█▋ | 62/363 [00:01<00:09, 33.19it/s] Loading 0: 18%|█▊ | 66/363 [00:02<00:08, 34.56it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:10, 28.94it/s] Loading 0: 20%|██ | 74/363 [00:02<00:11, 25.95it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 30.07it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:08, 31.45it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:09, 27.80it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:10, 26.57it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 30.45it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:11, 22.80it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:11, 22.95it/s] Loading 0: 30%|███ | 109/363 [00:03<00:15, 16.85it/s] Loading 0: 31%|███ | 112/363 [00:04<00:13, 18.47it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:13, 18.79it/s] Loading 0: 33%|███▎ | 118/363 [00:04<00:12, 20.09it/s] Loading 0: 33%|███▎ | 121/363 [00:04<00:11, 21.73it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:10, 22.98it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:08, 28.48it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:08, 28.36it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 32.55it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:07, 31.13it/s] Loading 0: 41%|████ | 149/363 [00:05<00:05, 38.12it/s] Loading 0: 42%|████▏ | 153/363 [00:05<00:08, 24.38it/s] Loading 0: 44%|████▎ | 158/363 [00:05<00:08, 24.97it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 31.93it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 31.04it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 34.08it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:05, 32.41it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:05, 33.04it/s] Loading 0: 52%|█████▏ | 187/363 [00:06<00:05, 29.97it/s] Loading 0: 53%|█████▎ | 191/363 [00:06<00:05, 29.12it/s] Loading 0: 54%|█████▎ | 195/363 [00:06<00:06, 26.21it/s] Loading 0: 55%|█████▌ | 201/363 [00:19<02:14, 1.20it/s] Loading 0: 56%|█████▌ | 203/363 [00:20<01:55, 1.38it/s] Loading 0: 57%|█████▋ | 208/363 [00:20<01:13, 2.10it/s] Loading 0: 58%|█████▊ | 212/363 [00:20<00:53, 2.80it/s] Loading 0: 60%|██████ | 218/363 [00:20<00:33, 4.37it/s] Loading 0: 61%|██████ | 222/363 [00:20<00:24, 5.70it/s] Loading 0: 62%|██████▏ | 226/363 [00:20<00:19, 7.01it/s] Loading 0: 63%|██████▎ | 230/363 [00:21<00:15, 8.63it/s] Loading 0: 65%|██████▌ | 237/363 [00:21<00:09, 13.34it/s] Loading 0: 66%|██████▋ | 241/363 [00:21<00:07, 15.40it/s] Loading 0: 68%|██████▊ | 246/363 [00:21<00:06, 19.31it/s] Loading 0: 69%|██████▉ | 250/363 [00:21<00:05, 21.05it/s] Loading 0: 70%|███████ | 255/363 [00:21<00:04, 25.25it/s] Loading 0: 71%|███████▏ | 259/363 [00:21<00:04, 25.41it/s] Loading 0: 73%|███████▎ | 266/363 [00:22<00:03, 32.28it/s] Loading 0: 75%|███████▍ | 271/363 [00:22<00:03, 24.39it/s] Loading 0: 76%|███████▌ | 275/363 [00:22<00:03, 23.28it/s] Loading 0: 78%|███████▊ | 282/363 [00:22<00:02, 30.27it/s] Loading 0: 79%|███████▉ | 286/363 [00:22<00:02, 29.59it/s] Loading 0: 80%|████████ | 291/363 [00:22<00:02, 32.77it/s] Loading 0: 81%|████████▏ | 295/363 [00:23<00:02, 31.07it/s] Loading 0: 82%|████████▏ | 299/363 [00:23<00:02, 31.88it/s] Loading 0: 84%|████████▎ | 304/363 [00:23<00:02, 29.20it/s] Loading 0: 85%|████████▍ | 308/363 [00:23<00:01, 28.44it/s] Loading 0: 86%|████████▌ | 312/363 [00:23<00:01, 25.76it/s] Loading 0: 88%|████████▊ | 318/363 [00:23<00:01, 31.50it/s] Loading 0: 89%|████████▊ | 322/363 [00:24<00:01, 30.13it/s] Loading 0: 90%|█████████ | 327/363 [00:24<00:01, 33.49it/s] Loading 0: 91%|█████████ | 331/363 [00:24<00:01, 31.34it/s] Loading 0: 92%|█████████▏| 335/363 [00:24<00:00, 32.35it/s] Loading 0: 93%|█████████▎| 339/363 [00:24<00:00, 33.05it/s] Loading 0: 94%|█████████▍| 343/363 [00:24<00:00, 20.01it/s] Loading 0: 96%|█████████▌| 348/363 [00:25<00:00, 21.24it/s] Loading 0: 98%|█████████▊| 355/363 [00:25<00:00, 28.63it/s] Loading 0: 99%|█████████▉| 359/363 [00:25<00:00, 28.22it/s]
Job chaiml-1106-quang-ir-mi-31446-v1-mkmlizer completed after 174.56s with status: succeeded
Stopping job with name chaiml-1106-quang-ir-mi-31446-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1106-quang-ir-mi-31446-v1
Waiting for inference service chaiml-1106-quang-ir-mi-31446-v1 to be ready
Inference service chaiml-1106-quang-ir-mi-31446-v1 ready after 311.1325476169586s
Pipeline stage MKMLDeployer completed in 312.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3641350269317627s
Received healthy response to inference request in 2.1205906867980957s
Received healthy response to inference request in 2.131798028945923s
Received healthy response to inference request in 2.0825517177581787s
Received healthy response to inference request in 2.4242849349975586s
5 requests
0 failed requests
5th percentile: 2.090159511566162
10th percentile: 2.0977673053741457
20th percentile: 2.112982892990112
30th percentile: 2.122832155227661
40th percentile: 2.127315092086792
50th percentile: 2.131798028945923
60th percentile: 2.224732828140259
70th percentile: 2.3176676273345946
80th percentile: 2.376165008544922
90th percentile: 2.40022497177124
95th percentile: 2.4122549533843993
99th percentile: 2.4218789386749267
mean time: 2.2246720790863037
Pipeline stage StressChecker completed in 13.13s
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 0.64s
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 0.64s
Shutdown handler de-registered
chaiml-1106-quang-ir-mi_31446_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 2906.85s
Shutdown handler de-registered
chaiml-1106-quang-ir-mi_31446_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1106-quang-ir-mi_31446_v1 status is now torndown due to DeploymentManager action