chaiml-1025-quang-ir-lt_20520

developer_uid: chai_backend_admin

submission_id: chaiml-1025-quang-ir-lt_20520_v1

model_name: chaiml-1025-quang-ir-lt_20520_v1

model_group: ChaiML/1025-quang-ir-ltr

status: inactive

timestamp: 2025-10-26T06:01:27+00:00

num_battles: 6810

num_wins: 3598

celo_rating: 1293.0

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1025-quang-ir-ltry-cam484-mem-15k

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': 0.3835635328394826, 'latency_mean': 2.6070028626918793, 'latency_p50': 2.602108597755432, 'latency_p90': 2.866999316215515}, {'batch_size': 2, 'throughput': 0.5756580404495193, 'latency_mean': 3.467076895236969, 'latency_p50': 3.4819064140319824, 'latency_p90': 3.8027572631835938}, {'batch_size': 3, 'throughput': 0.7130490434572573, 'latency_mean': 4.194397555589676, 'latency_p50': 4.170889616012573, 'latency_p90': 4.695719933509826}, {'batch_size': 4, 'throughput': 0.808832462118484, 'latency_mean': 4.9305263924598695, 'latency_p50': 4.938736319541931, 'latency_p90': 5.480224967002869}, {'batch_size': 5, 'throughput': 0.8748945152163594, 'latency_mean': 5.69608925819397, 'latency_p50': 5.670599102973938, 'latency_p90': 6.585730457305908}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-1025-quang-ir-lt_20520_v1

is_internal_developer: True

language_model: ChaiML/1025-quang-ir-ltry-cam484-mem-15k

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-10-25

win_ratio: 0.5283406754772394

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', '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-1025-quang-ir-lt-20520-v1-mkmlizer
Waiting for job on chaiml-1025-quang-ir-lt-20520-v1-mkmlizer to finish
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║                                                                     ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║                                                                     ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║                                                                     ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║                                                                     ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ║                                                                     ║
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: Downloaded to shared memory in 71.776s
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: Checking if ChaiML/1025-quang-ir-ltry-cam484-mem-15k already exists in ChaiML
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxv7s4y4o, device:0
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: quantized model in 41.873s
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: Processed model ChaiML/1025-quang-ir-ltry-cam484-mem-15k in 113.649s
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1025-quang-ir-lt-20520-v1/nvidia
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1025-quang-ir-lt-20520-v1/nvidia/config.json
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1025-quang-ir-lt-20520-v1/nvidia/special_tokens_map.json
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1025-quang-ir-lt-20520-v1/nvidia/tokenizer_config.json
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1025-quang-ir-lt-20520-v1/nvidia/tokenizer.json
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1025-quang-ir-lt-20520-v1/nvidia/flywheel_model.1.safetensors
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1025-quang-ir-lt-20520-v1/nvidia/flywheel_model.0.safetensors
chaiml-1025-quang-ir-lt-20520-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.30it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.10it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.00it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.54it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.66it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.33it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.89it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.08it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.77it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.35it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.59it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 34.99it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 29.16it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 26.21it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.75it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.91it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.26it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.65it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.03it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.01it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.38it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.98it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.64it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.56it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.72it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.21it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.12it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.50it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 31.46it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.11it/s]
Loading 0:  42%|████▏     | 153/363 [00:04<00:08, 25.04it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.20it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.89it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.40it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.35it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.39it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.39it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.72it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.50it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 24.03it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:11,  1.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:52,  1.42it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.14it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.69it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.46it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.86it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.10it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:18,  7.32it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.67it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.61it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.26it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 19.51it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:04, 24.34it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 25.14it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.61it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.91it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.69it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.57it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.05it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.17it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.26it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.39it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.59it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.66it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.05it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.81it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.80it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.58it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.54it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.95it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.80it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.89it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.58it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.34it/s]
Loading 0:  96%|█████████▌| 347/363 [00:24<00:00, 22.19it/s]
Loading 0:  96%|█████████▋| 350/363 [00:24<00:00, 21.99it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 26.21it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 26.27it/s]
                                                            
Job chaiml-1025-quang-ir-lt-20520-v1-mkmlizer completed after 184.66s with status: succeeded
Stopping job with name chaiml-1025-quang-ir-lt-20520-v1-mkmlizer
Pipeline stage MKMLizer completed in 185.48s
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-1025-quang-ir-lt-20520-v1
Waiting for inference service chaiml-1025-quang-ir-lt-20520-v1 to be ready
Inference service chaiml-1025-quang-ir-lt-20520-v1 ready after 90.5125961303711s
Pipeline stage MKMLDeployer completed in 90.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3254733085632324s
Received healthy response to inference request in 2.4074056148529053s
Received healthy response to inference request in 2.990694046020508s
Received healthy response to inference request in 2.165752649307251s
Received healthy response to inference request in 2.181004285812378s
5 requests
0 failed requests
5th percentile: 2.1688029766082764
10th percentile: 2.1718533039093018
20th percentile: 2.1779539585113525
30th percentile: 2.209898090362549
40th percentile: 2.2676856994628904
50th percentile: 2.3254733085632324
60th percentile: 2.3582462310791015
70th percentile: 2.3910191535949705
80th percentile: 2.524063301086426
90th percentile: 2.757378673553467
95th percentile: 2.874036359786987
99th percentile: 2.9673625087738036
mean time: 2.414065980911255
Pipeline stage StressChecker completed in 13.43s
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 0.86s
Shutdown handler de-registered
chaiml-1025-quang-ir-lt_20520_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-1025-quang-ir-lt-20520-v1-profiler
Waiting for inference service chaiml-1025-quang-ir-lt-20520-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 5969.54s
Shutdown handler de-registered