chaiml-1109-quang-ir-mi_62308

developer_uid: chai_backend_admin

submission_id: chaiml-1109-quang-ir-mi_62308_v1

model_name: training123

model_group: ChaiML/1109-quang-ir-mix

status: torndown

timestamp: 2025-11-12T21:06:38+00:00

num_battles: 5749

num_wins: 2950

celo_rating: 1296.89

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1109-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_mult_0164641ep_3e6ct

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': 0.3828664469902501, 'latency_mean': 2.6117527115345003, 'latency_p50': 2.6085065603256226, 'latency_p90': 2.883356142044067}, {'batch_size': 2, 'throughput': 0.5721216298461265, 'latency_mean': 3.4872266340255735, 'latency_p50': 3.501343607902527, 'latency_p90': 3.759660768508911}, {'batch_size': 3, 'throughput': 0.7181362039148605, 'latency_mean': 4.1651833319664, 'latency_p50': 4.175996899604797, 'latency_p90': 4.581749773025512}, {'batch_size': 4, 'throughput': 0.8166256116837455, 'latency_mean': 4.884416806697845, 'latency_p50': 4.8800448179244995, 'latency_p90': 5.521274137496948}, {'batch_size': 5, 'throughput': 0.8727798674191567, 'latency_mean': 5.67997590303421, 'latency_p50': 5.668089151382446, 'latency_p90': 6.600240683555603}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1109-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_mult_0164641ep_3e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-11-09

win_ratio: 0.5131327187336928

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>'], '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-1109-quang-ir-mi-62308-v1-mkmlizer
Waiting for job on chaiml-1109-quang-ir-mi-62308-v1-mkmlizer to finish
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║                                                                     ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║                                                                     ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║                                                                     ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║                                                                     ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ║                                                                     ║
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: Downloaded to shared memory in 69.895s
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: Checking if ChaiML/1109-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_mult_0164641ep_3e6ct already exists in ChaiML
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbvznse91, device:0
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: quantized model in 42.305s
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: Processed model ChaiML/1109-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_mult_0164641ep_3e6ct in 112.200s
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1109-quang-ir-mi-62308-v1/nvidia
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1109-quang-ir-mi-62308-v1/nvidia/config.json
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1109-quang-ir-mi-62308-v1/nvidia/special_tokens_map.json
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1109-quang-ir-mi-62308-v1/nvidia/tokenizer_config.json
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1109-quang-ir-mi-62308-v1/nvidia/tokenizer.json
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1109-quang-ir-mi-62308-v1/nvidia/flywheel_model.1.safetensors
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1109-quang-ir-mi-62308-v1/nvidia/flywheel_model.0.safetensors
chaiml-1109-quang-ir-mi-62308-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:13, 26.18it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:18, 18.92it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:12, 28.29it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 31.55it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:10, 33.47it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 34.74it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 40.72it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.13it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.35it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.21it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.80it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.84it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:09, 31.15it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.56it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.47it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.48it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.41it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.69it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.58it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:09, 27.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.82it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.82it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.04it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.55it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.57it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.31it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.66it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.35it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.86it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.31it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.96it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.59it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.88it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.87it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.88it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.82it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.35it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.39it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.54it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.63it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.62it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  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,  2.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.44it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:29,  4.85it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:21,  6.64it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.23it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:13, 10.13it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 15.84it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 17.81it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 22.08it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.34it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.43it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.30it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.28it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 24.82it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.56it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.65it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.41it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.62it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 30.75it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 31.70it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 29.76it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 29.08it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.61it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.52it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.57it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 32.80it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 30.64it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 31.13it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 32.22it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.30it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.92it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.45it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.95it/s]
                                                            
Job chaiml-1109-quang-ir-mi-62308-v1-mkmlizer completed after 167.27s with status: succeeded
Stopping job with name chaiml-1109-quang-ir-mi-62308-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.48s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1109-quang-ir-mi-62308-v1
Waiting for inference service chaiml-1109-quang-ir-mi-62308-v1 to be ready
Inference service chaiml-1109-quang-ir-mi-62308-v1 ready after 181.33720707893372s
Pipeline stage MKMLDeployer completed in 181.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8125052452087402s
Received healthy response to inference request in 3.0448122024536133s
Received healthy response to inference request in 2.381925344467163s
Received healthy response to inference request in 2.1454615592956543s
Received healthy response to inference request in 2.1768081188201904s
5 requests
0 failed requests
5th percentile: 2.1517308712005616
10th percentile: 2.158000183105469
20th percentile: 2.170538806915283
30th percentile: 2.217831563949585
40th percentile: 2.299878454208374
50th percentile: 2.381925344467163
60th percentile: 2.5541573047637938
70th percentile: 2.726389265060425
80th percentile: 2.8589666366577147
90th percentile: 2.951889419555664
95th percentile: 2.998350811004639
99th percentile: 3.035519924163818
mean time: 2.5123024940490724
Pipeline stage StressChecker completed in 14.02s
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 0.71s
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-1109-quang-ir-mi_62308_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1109-quang-ir-mi-62308-v1-profiler
Waiting for inference service chaiml-1109-quang-ir-mi-62308-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5467.25s
Shutdown handler de-registered
chaiml-1109-quang-ir-mi_62308_v1 status is now torndown due to DeploymentManager action