chaiml-1102-quang-ir-mi_71940

developer_uid: chai_backend_admin

submission_id: chaiml-1102-quang-ir-mi_71940_v1

model_name: training123

model_group: ChaiML/1102-quang-ir-mix

status: inactive

timestamp: 2025-11-03T05:56:52+00:00

num_battles: 6045

num_wins: 3045

celo_rating: 1291.64

family_friendly_score: 0.49960000000000004

family_friendly_standard_error: 0.007071065549123414

submission_type: basic

model_repo: ChaiML/1102-quang-ir-mixo31n1-cld-iq8-adh8-onlyh-dpo_1e6011e128

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': 0.3770894370879828, 'latency_mean': 2.6517902171611785, 'latency_p50': 2.6507456302642822, 'latency_p90': 2.907057356834412}, {'batch_size': 2, 'throughput': 0.563896283222756, 'latency_mean': 3.5370670092105865, 'latency_p50': 3.5350372791290283, 'latency_p90': 3.855388355255127}, {'batch_size': 3, 'throughput': 0.6990139870727183, 'latency_mean': 4.2788408088684085, 'latency_p50': 4.271747946739197, 'latency_p90': 4.667947220802307}, {'batch_size': 4, 'throughput': 0.7908357244944741, 'latency_mean': 5.038068828582763, 'latency_p50': 5.048557877540588, 'latency_p90': 5.687615776062012}, {'batch_size': 5, 'throughput': 0.8578003357370007, 'latency_mean': 5.809115698337555, 'latency_p50': 5.82715904712677, 'latency_p90': 6.652203488349914}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1102-quang-ir-mixo31n1-cld-iq8-adh8-onlyh-dpo_1e6011e128

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-02

win_ratio: 0.5037220843672456

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-1102-quang-ir-mi-71940-v1-mkmlizer
Waiting for job on chaiml-1102-quang-ir-mi-71940-v1-mkmlizer to finish
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║                                                                     ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║                                                                     ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║                                                                     ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║                                                                     ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ║                                                                     ║
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: Downloaded to shared memory in 64.797s
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: Checking if ChaiML/1102-quang-ir-mixo31n1-cld-iq8-adh8-onlyh-dpo_1e6011e128 already exists in ChaiML
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp23pi9rj3, device:0
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: quantized model in 42.794s
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: Processed model ChaiML/1102-quang-ir-mixo31n1-cld-iq8-adh8-onlyh-dpo_1e6011e128 in 107.592s
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1102-quang-ir-mi-71940-v1/nvidia
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1102-quang-ir-mi-71940-v1/nvidia/config.json
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1102-quang-ir-mi-71940-v1/nvidia/special_tokens_map.json
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1102-quang-ir-mi-71940-v1/nvidia/tokenizer_config.json
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1102-quang-ir-mi-71940-v1/nvidia/tokenizer.json
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1102-quang-ir-mi-71940-v1/nvidia/flywheel_model.1.safetensors
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1102-quang-ir-mi-71940-v1/nvidia/flywheel_model.0.safetensors
chaiml-1102-quang-ir-mi-71940-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 30.27it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.34it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:11, 31.71it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.07it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 34.18it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 35.16it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 41.16it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.78it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.22it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.04it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.87it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.39it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.42it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.52it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.75it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.82it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.65it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.97it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 26.97it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.62it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.05it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.16it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.55it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.11it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 30.93it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.36it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 31.05it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.21it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.30it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.54it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.60it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.29it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.84it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.94it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.98it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.43it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.58it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.27it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.27it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.85it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.61it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.92it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.64it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:40,  3.68it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.69it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  5.99it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.22it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.57it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.30it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.87it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 19.17it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.82it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 25.09it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.45it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 29.31it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 36.12it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.90it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.48it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.62it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.87it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 34.02it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.55it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.09it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.35it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.98it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:02, 24.37it/s]
Loading 0:  87%|████████▋ | 316/363 [00:23<00:01, 26.78it/s]
Loading 0:  88%|████████▊ | 320/363 [00:23<00:01, 25.25it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.35it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.96it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.87it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.83it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.43it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.96it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.42it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 26.50it/s]
Loading 0: 100%|██████████| 363/363 [00:25<00:00, 29.00it/s]
                                                            
Job chaiml-1102-quang-ir-mi-71940-v1-mkmlizer completed after 206.27s with status: succeeded
Stopping job with name chaiml-1102-quang-ir-mi-71940-v1-mkmlizer
Pipeline stage MKMLizer completed in 206.95s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1102-quang-ir-mi-71940-v1
Waiting for inference service chaiml-1102-quang-ir-mi-71940-v1 to be ready
Inference service chaiml-1102-quang-ir-mi-71940-v1 ready after 140.62122464179993s
Pipeline stage MKMLDeployer completed in 141.07s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.6872639656066895s
Received healthy response to inference request in 2.7463929653167725s
Received healthy response to inference request in 2.122974157333374s
Received healthy response to inference request in 2.568499803543091s
5 requests
1 failed requests
5th percentile: 2.2120792865753174
10th percentile: 2.3011844158172607
20th percentile: 2.4793946743011475
30th percentile: 2.5922526359558105
40th percentile: 2.63975830078125
50th percentile: 2.6872639656066895
60th percentile: 2.7109155654907227
70th percentile: 2.734567165374756
80th percentile: 6.227797174453738
90th percentile: 13.190605592727664
95th percentile: 16.672009801864622
99th percentile: 19.457133169174195
mean time: 6.055708980560302
%s, retrying in %s seconds...
Received healthy response to inference request in 2.458388566970825s
Received healthy response to inference request in 2.296699285507202s
Received healthy response to inference request in 2.2644388675689697s
Received healthy response to inference request in 2.06959867477417s
Received healthy response to inference request in 2.089139938354492s
5 requests
0 failed requests
5th percentile: 2.0735069274902345
10th percentile: 2.077415180206299
20th percentile: 2.0852316856384276
30th percentile: 2.124199724197388
40th percentile: 2.1943192958831785
50th percentile: 2.2644388675689697
60th percentile: 2.2773430347442627
70th percentile: 2.2902472019195557
80th percentile: 2.329037141799927
90th percentile: 2.393712854385376
95th percentile: 2.4260507106781004
99th percentile: 2.45192099571228
mean time: 2.2356530666351317
Pipeline stage StressChecker completed in 43.96s
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 0.70s
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-1102-quang-ir-mi_71940_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1102-quang-ir-mi-71940-v1-profiler
Waiting for inference service chaiml-1102-quang-ir-mi-71940-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 3140.87s
Shutdown handler de-registered
chaiml-1102-quang-ir-mi_71940_v1 status is now inactive due to auto deactivation removed underperforming models