chaiml-1103-quang-ir-mi_67995

developer_uid: chai_backend_admin

submission_id: chaiml-1103-quang-ir-mi_67995_v1

model_name: training123

model_group: ChaiML/1103-quang-ir-mix

status: torndown

timestamp: 2025-11-07T03:01:25+00:00

num_battles: 6376

num_wins: 3283

celo_rating: 1295.89

family_friendly_score: 0.4858

family_friendly_standard_error: 0.0070682156164056

submission_type: basic

model_repo: ChaiML/1103-quang-ir-mixallnov3-cld-i8a8-onlyh2

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': 0.38351220122473106, 'latency_mean': 2.6073574805259705, 'latency_p50': 2.602987051010132, 'latency_p90': 2.8746681451797484}, {'batch_size': 2, 'throughput': 0.5724235987884134, 'latency_mean': 3.4879675233364105, 'latency_p50': 3.463676929473877, 'latency_p90': 3.794664740562439}, {'batch_size': 3, 'throughput': 0.7039412887980898, 'latency_mean': 4.241698235273361, 'latency_p50': 4.2523581981658936, 'latency_p90': 4.818654656410217}, {'batch_size': 4, 'throughput': 0.8012709322040713, 'latency_mean': 4.985166153907776, 'latency_p50': 4.975075364112854, 'latency_p90': 5.72104742527008}, {'batch_size': 5, 'throughput': 0.8584566175167309, 'latency_mean': 5.785171277523041, 'latency_p50': 5.769072413444519, 'latency_p90': 6.708379507064819}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1103-quang-ir-mixallnov3-cld-i8a8-onlyh2

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-03

win_ratio: 0.5148996235884568

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:', '####\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
Running pipeline stage MKMLizer
Starting job with name chaiml-1103-quang-ir-mi-67995-v1-mkmlizer
Waiting for job on chaiml-1103-quang-ir-mi-67995-v1-mkmlizer to finish
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ║                                                                     ║
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: Downloaded to shared memory in 65.852s
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: Checking if ChaiML/1103-quang-ir-mixallnov3-cld-i8a8-onlyh2 already exists in ChaiML
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvlp6hpn4, device:0
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: quantized model in 42.011s
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: Processed model ChaiML/1103-quang-ir-mixallnov3-cld-i8a8-onlyh2 in 107.864s
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-67995-v1/nvidia
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-67995-v1/nvidia/config.json
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-67995-v1/nvidia/special_tokens_map.json
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-67995-v1/nvidia/tokenizer_config.json
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-67995-v1/nvidia/tokenizer.json
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-67995-v1/nvidia/flywheel_model.1.safetensors
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1103-quang-ir-mi-67995-v1/nvidia/flywheel_model.0.safetensors
chaiml-1103-quang-ir-mi-67995-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.19it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 38.95it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.87it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.48it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.87it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.59it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.78it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.04it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.88it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.75it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 34.81it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.87it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.47it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.51it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.61it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.62it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:11, 24.65it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 24.85it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 32.15it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 30.89it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.08it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.78it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.69it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.48it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.76it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.53it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.45it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.85it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.31it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.83it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.31it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.13it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.22it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.11it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.19it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.91it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.87it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.05it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.17it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.40it/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 [00:19<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.67it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.44it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.84it/s]
Loading 0:  61%|██████    | 221/363 [00:19<00:23,  6.14it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:18,  7.34it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.69it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.60it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.20it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 19.37it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:04, 24.05it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 25.07it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.31it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 29.03it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 36.00it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.95it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.86it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 30.86it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.06it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.35it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.71it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.62it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.08it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.94it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.82it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.66it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.51it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.84it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.09it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.00it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.47it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.46it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.97it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.18it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.75it/s]
                                                            
Job chaiml-1103-quang-ir-mi-67995-v1-mkmlizer completed after 185.38s with status: succeeded
Stopping job with name chaiml-1103-quang-ir-mi-67995-v1-mkmlizer
Pipeline stage MKMLizer completed in 185.95s
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-1103-quang-ir-mi-67995-v1
Waiting for inference service chaiml-1103-quang-ir-mi-67995-v1 to be ready
Inference service chaiml-1103-quang-ir-mi-67995-v1 ready after 140.91390895843506s
Pipeline stage MKMLDeployer completed in 141.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3150346279144287s
Received healthy response to inference request in 2.1731033325195312s
Received healthy response to inference request in 2.1326863765716553s
Received healthy response to inference request in 2.1832563877105713s
Received healthy response to inference request in 2.4717657566070557s
5 requests
0 failed requests
5th percentile: 2.1407697677612303
10th percentile: 2.1488531589508058
20th percentile: 2.1650199413299562
30th percentile: 2.1751339435577393
40th percentile: 2.1791951656341553
50th percentile: 2.1832563877105713
60th percentile: 2.235967683792114
70th percentile: 2.2886789798736573
80th percentile: 2.346380853652954
90th percentile: 2.409073305130005
95th percentile: 2.4404195308685304
99th percentile: 2.465496511459351
mean time: 2.2551692962646483
Pipeline stage StressChecker completed in 13.01s
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 0.74s
Shutdown handler de-registered
chaiml-1103-quang-ir-mi_67995_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1103-quang-ir-mi-67995-v1-profiler
Waiting for inference service chaiml-1103-quang-ir-mi-67995-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 2978.23s
Shutdown handler de-registered
chaiml-1103-quang-ir-mi_67995_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1103-quang-ir-mi_67995_v1 status is now torndown due to DeploymentManager action