chaiml-1026-quang-ir-lt_71564

developer_uid: chai_backend_admin

submission_id: chaiml-1026-quang-ir-lt_71564_v1

model_name: chaiml-1026-quang-ir-lt_71564_v1

model_group: ChaiML/1026-quang-ir-ltr

status: inactive

timestamp: 2025-10-27T03:17:39+00:00

num_battles: 5845

num_wins: 3088

celo_rating: 1295.3

family_friendly_score: 0.4544

family_friendly_standard_error: 0.007041599818223129

submission_type: basic

model_repo: ChaiML/1026-quang-ir-ltry-t16-adj

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': 0.3801641321885124, 'latency_mean': 2.630342136621475, 'latency_p50': 2.631732702255249, 'latency_p90': 2.8765021562576294}, {'batch_size': 2, 'throughput': 0.578294870487752, 'latency_mean': 3.4503304779529573, 'latency_p50': 3.4535030126571655, 'latency_p90': 3.7288768529891967}, {'batch_size': 3, 'throughput': 0.7177565968509445, 'latency_mean': 4.167553269863129, 'latency_p50': 4.20719313621521, 'latency_p90': 4.552679181098938}, {'batch_size': 4, 'throughput': 0.8178023127553306, 'latency_mean': 4.858271963596344, 'latency_p50': 4.873135924339294, 'latency_p90': 5.266585040092468}, {'batch_size': 5, 'throughput': 0.8856713938854481, 'latency_mean': 5.623309696912766, 'latency_p50': 5.6269049644470215, 'latency_p90': 6.490455651283264}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-1026-quang-ir-lt_71564_v1

is_internal_developer: True

language_model: ChaiML/1026-quang-ir-ltry-t16-adj

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-10-26

win_ratio: 0.5283147989734817

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', '####\n', '####', '</s>', 'You:'], '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-1026-quang-ir-lt-71564-v1-mkmlizer
Waiting for job on chaiml-1026-quang-ir-lt-71564-v1-mkmlizer to finish
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║                                                                     ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║                                                                     ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║                                                                     ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║                                                                     ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ║                                                                     ║
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: Downloaded to shared memory in 68.167s
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: Checking if ChaiML/1026-quang-ir-ltry-t16-adj already exists in ChaiML
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzl_yeqts, device:0
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: quantized model in 42.590s
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: Processed model ChaiML/1026-quang-ir-ltry-t16-adj in 110.757s
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1026-quang-ir-lt-71564-v1/nvidia
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1026-quang-ir-lt-71564-v1/nvidia/config.json
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1026-quang-ir-lt-71564-v1/nvidia/special_tokens_map.json
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1026-quang-ir-lt-71564-v1/nvidia/tokenizer_config.json
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1026-quang-ir-lt-71564-v1/nvidia/tokenizer.json
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1026-quang-ir-lt-71564-v1/nvidia/flywheel_model.0.safetensors
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1026-quang-ir-lt-71564-v1/nvidia/flywheel_model.1.safetensors
chaiml-1026-quang-ir-lt-71564-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.70it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.87it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.12it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.44it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:10, 33.36it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:09, 34.93it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:18, 17.42it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:20, 15.84it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:17, 17.98it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:18, 17.47it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 19.49it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:14, 21.05it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 22.27it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.05it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.27it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.72it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 26.88it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 22.89it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:09, 29.68it/s]
Loading 0:  23%|██▎       | 83/363 [00:03<00:09, 30.93it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 27.51it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 27.06it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.39it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.45it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 27.51it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 29.88it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 29.59it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.87it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.86it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.44it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.16it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.43it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:06, 32.97it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 39.59it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.64it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.69it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.78it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.66it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.81it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.74it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 32.30it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.78it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.35it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:11,  1.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:12,  2.13it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:56,  2.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.74it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.74it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.03it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.26it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:12, 10.63it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:10, 12.52it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 17.10it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 19.39it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 24.07it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 25.04it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.40it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 29.16it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 36.27it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 25.85it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.44it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.47it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.35it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.47it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 32.01it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 32.90it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 29.48it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.85it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.05it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.42it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.48it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 33.99it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:00, 32.23it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 33.08it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.63it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.36it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.89it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 29.36it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 29.00it/s]
                                                            
Job chaiml-1026-quang-ir-lt-71564-v1-mkmlizer completed after 164.52s with status: succeeded
Stopping job with name chaiml-1026-quang-ir-lt-71564-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.01s
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-1026-quang-ir-lt-71564-v1
Waiting for inference service chaiml-1026-quang-ir-lt-71564-v1 to be ready
Inference service chaiml-1026-quang-ir-lt-71564-v1 ready after 90.24189305305481s
Pipeline stage MKMLDeployer completed in 90.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.387068510055542s
Received healthy response to inference request in 2.3628807067871094s
Received healthy response to inference request in 2.5438990592956543s
Received healthy response to inference request in 2.4279980659484863s
Received healthy response to inference request in 2.1622750759124756s
5 requests
0 failed requests
5th percentile: 2.202396202087402
10th percentile: 2.242517328262329
20th percentile: 2.322759580612183
30th percentile: 2.3677182674407957
40th percentile: 2.377393388748169
50th percentile: 2.387068510055542
60th percentile: 2.40344033241272
70th percentile: 2.4198121547698976
80th percentile: 2.45117826461792
90th percentile: 2.497538661956787
95th percentile: 2.5207188606262205
99th percentile: 2.5392630195617674
mean time: 2.3768242835998534
Pipeline stage StressChecker completed in 13.19s
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 0.61s
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 0.58s
Shutdown handler de-registered
chaiml-1026-quang-ir-lt_71564_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 3144.41s
Shutdown handler de-registered
chaiml-1026-quang-ir-lt_71564_v1 status is now inactive due to auto deactivation removed underperforming models