chaiml-1105-quang-ir-mi_60363

developer_uid: chai_backend_admin

submission_id: chaiml-1105-quang-ir-mi_60363_v1

model_name: training123

model_group: ChaiML/1105-quang-ir-mix

status: torndown

timestamp: 2025-11-09T07:26:50+00:00

num_battles: 5859

num_wins: 2880

celo_rating: 1300.88

family_friendly_score: 0.5172

family_friendly_standard_error: 0.00706688276399149

submission_type: basic

model_repo: ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250002

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': 0.37783777599158824, 'latency_mean': 2.646537631750107, 'latency_p50': 2.64763867855072, 'latency_p90': 2.902261924743652}, {'batch_size': 2, 'throughput': 0.5656845042273672, 'latency_mean': 3.5298980498313903, 'latency_p50': 3.558875560760498, 'latency_p90': 3.833250331878662}, {'batch_size': 3, 'throughput': 0.7050414834688685, 'latency_mean': 4.251549109220504, 'latency_p50': 4.235548615455627, 'latency_p90': 4.780239248275757}, {'batch_size': 4, 'throughput': 0.7914239508402018, 'latency_mean': 5.02901344537735, 'latency_p50': 5.056743144989014, 'latency_p90': 5.839766120910644}, {'batch_size': 5, 'throughput': 0.8591492389853163, 'latency_mean': 5.796993646621704, 'latency_p50': 5.811370134353638, 'latency_p90': 6.647070384025573}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250002

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-05

win_ratio: 0.4915514592933948

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', '####\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-1105-quang-ir-mi-60363-v1-mkmlizer
Waiting for job on chaiml-1105-quang-ir-mi-60363-v1-mkmlizer to finish
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ║                                                                     ║
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: Downloaded to shared memory in 73.965s
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: Checking if ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250002 already exists in ChaiML
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa7c33j1y, device:0
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: quantized model in 42.387s
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: Processed model ChaiML/1105-quang-ir-mixall-cld-i8a8-hl-mult-sth-f250002 in 116.352s
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-60363-v1/nvidia
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-60363-v1/nvidia/config.json
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-60363-v1/nvidia/special_tokens_map.json
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-60363-v1/nvidia/tokenizer_config.json
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-60363-v1/nvidia/tokenizer.json
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-60363-v1/nvidia/flywheel_model.1.safetensors
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1105-quang-ir-mi-60363-v1/nvidia/flywheel_model.0.safetensors
chaiml-1105-quang-ir-mi-60363-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.79it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.83it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.07it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.53it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.99it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.81it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.40it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.82it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.63it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.28it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.38it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.54it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 31.07it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.34it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.35it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.47it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.62it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.53it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.90it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.12it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 25.31it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:09, 27.31it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:09, 26.80it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 30.94it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.21it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.77it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.17it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.54it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.82it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.38it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 26.95it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.23it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.94it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.01it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.98it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.44it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:06, 27.55it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:07, 24.64it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.41it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 22.64it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:11,  1.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.70it/s]
Loading 0:  60%|██████    | 219/363 [00:20<00:29,  4.93it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.85it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.43it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:11, 11.03it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 14.92it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 17.17it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 21.16it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 22.71it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.16it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.31it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.50it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.39it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.13it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.32it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 27.03it/s]
Loading 0:  80%|███████▉  | 290/363 [00:22<00:02, 28.53it/s]
Loading 0:  81%|████████  | 294/363 [00:22<00:02, 24.52it/s]
Loading 0:  82%|████████▏ | 298/363 [00:22<00:02, 27.05it/s]
Loading 0:  83%|████████▎ | 303/363 [00:23<00:02, 29.96it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:02, 22.97it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 22.26it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 29.85it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.54it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.05it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 30.82it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.10it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.44it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.57it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 28.97it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.78it/s]
                                                            
Job chaiml-1105-quang-ir-mi-60363-v1-mkmlizer completed after 185.28s with status: succeeded
Stopping job with name chaiml-1105-quang-ir-mi-60363-v1-mkmlizer
Pipeline stage MKMLizer completed in 185.79s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1105-quang-ir-mi-60363-v1
Waiting for inference service chaiml-1105-quang-ir-mi-60363-v1 to be ready
Inference service chaiml-1105-quang-ir-mi-60363-v1 ready after 160.6807520389557s
Pipeline stage MKMLDeployer completed in 162.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5582380294799805s
Received healthy response to inference request in 2.3144326210021973s
Received healthy response to inference request in 2.4921748638153076s
Received healthy response to inference request in 2.0774521827697754s
Received healthy response to inference request in 2.086275339126587s
5 requests
0 failed requests
5th percentile: 2.079216814041138
10th percentile: 2.0809814453125
20th percentile: 2.0845107078552245
30th percentile: 2.131906795501709
40th percentile: 2.223169708251953
50th percentile: 2.3144326210021973
60th percentile: 2.3855295181274414
70th percentile: 2.4566264152526855
80th percentile: 2.5053874969482424
90th percentile: 2.5318127632141114
95th percentile: 2.5450253963470457
99th percentile: 2.5555955028533934
mean time: 2.3057146072387695
Pipeline stage StressChecker completed in 12.85s
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 0.73s
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 0.68s
Shutdown handler de-registered
chaiml-1105-quang-ir-mi_60363_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 0.08s
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-1105-quang-ir-mi-60363-v1-profiler
Waiting for inference service chaiml-1105-quang-ir-mi-60363-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 2900.02s
Shutdown handler de-registered
chaiml-1105-quang-ir-mi_60363_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1105-quang-ir-mi_60363_v1 status is now torndown due to DeploymentManager action