chaiml-1108-quang-ir-mi_36604

developer_uid: chai_backend_admin

submission_id: chaiml-1108-quang-ir-mi_36604_v1

model_name: training123

model_group: ChaiML/1108-quang-ir-mix

status: torndown

timestamp: 2025-11-11T13:11:34+00:00

num_battles: 6639

num_wins: 3231

celo_rating: 1299.25

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f10000-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': 0.38084547695156845, 'latency_mean': 2.6256118762493132, 'latency_p50': 2.6184139251708984, 'latency_p90': 2.8681878089904784}, {'batch_size': 2, 'throughput': 0.5645219709448774, 'latency_mean': 3.5383952486515047, 'latency_p50': 3.56948184967041, 'latency_p90': 3.791117715835571}, {'batch_size': 3, 'throughput': 0.6988365681838188, 'latency_mean': 4.279644408226013, 'latency_p50': 4.292966961860657, 'latency_p90': 4.643942499160767}, {'batch_size': 4, 'throughput': 0.7908311214332002, 'latency_mean': 5.034554203748703, 'latency_p50': 5.010890960693359, 'latency_p90': 5.734834289550781}, {'batch_size': 5, 'throughput': 0.8550282347613903, 'latency_mean': 5.830869446992875, 'latency_p50': 5.812995433807373, 'latency_p90': 6.619564032554626}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f10000-dpo_mult25k_0164641ep_5e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-08

win_ratio: 0.4866696791685495

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:', '</s>', '\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-1108-quang-ir-mi-36604-v1-mkmlizer
Waiting for job on chaiml-1108-quang-ir-mi-36604-v1-mkmlizer to finish
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: Downloaded to shared memory in 53.441s
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: Checking if ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f10000-dpo_mult25k_0164641ep_5e6ct already exists in ChaiML
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmplvzqmb, device:0
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: quantized model in 43.168s
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: Processed model ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f10000-dpo_mult25k_0164641ep_5e6ct in 96.610s
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-36604-v1/nvidia
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-36604-v1/nvidia/config.json
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-36604-v1/nvidia/special_tokens_map.json
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-36604-v1/nvidia/tokenizer_config.json
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-36604-v1/nvidia/tokenizer.json
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-36604-v1/nvidia/flywheel_model.0.safetensors
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-36604-v1/nvidia/flywheel_model.1.safetensors
chaiml-1108-quang-ir-mi-36604-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.29it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.44it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 40.09it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:09, 35.36it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 45.26it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.85it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.07it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.46it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.27it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.77it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.68it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:07, 37.03it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.73it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.97it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.11it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.77it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.08it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.48it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.15it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.32it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.65it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 28.59it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:09, 26.40it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:08, 28.40it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.38it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:09, 24.21it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:09, 23.76it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.17it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 29.92it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 37.02it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.77it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.63it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.18it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 29.54it/s]
Loading 0:  48%|████▊     | 173/363 [00:05<00:06, 29.24it/s]
Loading 0:  49%|████▉     | 177/363 [00:05<00:07, 26.45it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.88it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.57it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.24it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.99it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:55,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:14,  2.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:58,  2.61it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:44,  3.34it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:31,  4.64it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:24,  5.79it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:20,  6.84it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:13, 10.02it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:11, 11.79it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 15.77it/s]
Loading 0:  66%|██████▌   | 240/363 [00:21<00:07, 15.72it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 20.95it/s]
Loading 0:  69%|██████▊   | 249/363 [00:21<00:05, 19.99it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:04, 24.94it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:04, 24.08it/s]
Loading 0:  73%|███████▎  | 264/363 [00:22<00:03, 28.72it/s]
Loading 0:  74%|███████▍  | 268/363 [00:22<00:04, 23.01it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:04, 21.64it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:04, 20.52it/s]
Loading 0:  78%|███████▊  | 282/363 [00:23<00:02, 27.18it/s]
Loading 0:  79%|███████▉  | 286/363 [00:23<00:02, 25.79it/s]
Loading 0:  80%|████████  | 291/363 [00:23<00:02, 28.52it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 26.92it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 28.02it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 26.10it/s]
Loading 0:  85%|████████▍ | 307/363 [00:24<00:02, 24.03it/s]
Loading 0:  85%|████████▌ | 310/363 [00:24<00:02, 24.82it/s]
Loading 0:  86%|████████▌ | 313/363 [00:24<00:01, 25.68it/s]
Loading 0:  88%|████████▊ | 318/363 [00:24<00:01, 29.56it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 27.62it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 30.85it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 29.00it/s]
Loading 0:  92%|█████████▏| 335/363 [00:25<00:00, 30.05it/s]
Loading 0:  93%|█████████▎| 339/363 [00:25<00:00, 30.11it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:01, 18.50it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 20.15it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 27.18it/s]
Loading 0:  99%|█████████▉| 359/363 [00:26<00:00, 26.41it/s]
                                                            
Job chaiml-1108-quang-ir-mi-36604-v1-mkmlizer completed after 155.39s with status: succeeded
Stopping job with name chaiml-1108-quang-ir-mi-36604-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.87s
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-36604-v1
Waiting for inference service chaiml-1108-quang-ir-mi-36604-v1 to be ready
Inference service chaiml-1108-quang-ir-mi-36604-v1 ready after 180.75662302970886s
Pipeline stage MKMLDeployer completed in 181.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.998474359512329s
Received healthy response to inference request in 2.1271932125091553s
Received healthy response to inference request in 2.6741933822631836s
Received healthy response to inference request in 2.261213541030884s
Received healthy response to inference request in 2.4390480518341064s
5 requests
0 failed requests
5th percentile: 2.153997278213501
10th percentile: 2.180801343917847
20th percentile: 2.234409475326538
30th percentile: 2.2967804431915284
40th percentile: 2.367914247512817
50th percentile: 2.4390480518341064
60th percentile: 2.5331061840057374
70th percentile: 2.6271643161773683
80th percentile: 2.7390495777130126
90th percentile: 2.868761968612671
95th percentile: 2.9336181640625
99th percentile: 2.985503120422363
mean time: 2.500024509429932
Pipeline stage StressChecker completed in 14.08s
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 0.62s
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 0.67s
Shutdown handler de-registered
chaiml-1108-quang-ir-mi_36604_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-1108-quang-ir-mi-36604-v1-profiler
Waiting for inference service chaiml-1108-quang-ir-mi-36604-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 5851.26s
Shutdown handler de-registered
chaiml-1108-quang-ir-mi_36604_v1 status is now torndown due to DeploymentManager action