developer_uid: chai_backend_admin
submission_id: chaiml-1030-quang-ir-lt_35485_v1
model_name: training123
model_group: ChaiML/1030-quang-ir-ltr
status: inactive
timestamp: 2025-10-30T20:07:46+00:00
num_battles: 6892
num_wins: 3597
celo_rating: 1303.65
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/1030-quang-ir-ltry-mix3-maxb3-10k-dpo_1e5b001
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': 0.21513453179400882, 'latency_mean': 4.648128292560577, 'latency_p50': 4.447589159011841, 'latency_p90': 6.625527620315552}, {'batch_size': 2, 'throughput': 0.5489404877593403, 'latency_mean': 3.6406481540203095, 'latency_p50': 3.547977089881897, 'latency_p90': 3.9395912170410154}, {'batch_size': 3, 'throughput': 0.7054926867682394, 'latency_mean': 4.240796270370484, 'latency_p50': 4.21082067489624, 'latency_p90': 4.612923693656922}, {'batch_size': 4, 'throughput': 0.7973553506895824, 'latency_mean': 5.007579444646836, 'latency_p50': 5.005332827568054, 'latency_p90': 5.738603472709656}, {'batch_size': 5, 'throughput': 0.6094665382969943, 'latency_mean': 8.166088247299195, 'latency_p50': 8.180573105812073, 'latency_p90': 9.2474196434021}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/1030-quang-ir-ltry-mix3-maxb3-10k-dpo_1e5b001
model_size: 24B
ranking_group: single
throughput_3p7s: 0.27
us_pacific_date: 2025-10-30
win_ratio: 0.5219094602437608
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', '####', '</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-1030-quang-ir-lt-35485-v1-mkmlizer
Waiting for job on chaiml-1030-quang-ir-lt-35485-v1-mkmlizer to finish
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║                                                                     ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║                                                                     ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║                                                                     ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║                                                                     ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ║                                                                     ║
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: Downloaded to shared memory in 76.731s
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: Checking if ChaiML/1030-quang-ir-ltry-mix3-maxb3-10k-dpo_1e5b001 already exists in ChaiML
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpct3313yl, device:0
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: quantized model in 42.116s
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: Processed model ChaiML/1030-quang-ir-ltry-mix3-maxb3-10k-dpo_1e5b001 in 118.848s
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1030-quang-ir-lt-35485-v1/nvidia
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1030-quang-ir-lt-35485-v1/nvidia/config.json
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1030-quang-ir-lt-35485-v1/nvidia/special_tokens_map.json
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1030-quang-ir-lt-35485-v1/nvidia/tokenizer_config.json
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1030-quang-ir-lt-35485-v1/nvidia/tokenizer.json
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1030-quang-ir-lt-35485-v1/nvidia/flywheel_model.1.safetensors
chaiml-1030-quang-ir-lt-35485-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.18it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 37.83it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.92it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.63it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.20it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 29.62it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.01it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.37it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 31.96it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.01it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.68it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:08, 36.97it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.00it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.49it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.64it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.81it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.46it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 26.85it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.26it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.55it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:11, 22.71it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:09, 25.59it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:10, 23.32it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:10, 23.97it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:12, 19.51it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:09, 24.03it/s]
Loading 0:  36%|███▌      | 130/363 [00:04<00:09, 24.00it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:10, 22.39it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:08, 26.68it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:08, 25.41it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.98it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.05it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.79it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.88it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.85it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.17it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.84it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.68it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.22it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.49it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.66it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 212/363 [00:20<00:53,  2.83it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:32,  4.41it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.76it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.08it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.62it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.37it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:07, 15.46it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:06, 19.43it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 21.09it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 25.44it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.03it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.22it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 24.93it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.98it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.97it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.95it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.28it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.98it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.73it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.94it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.10it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.64it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.62it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.06it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.35it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.89it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 33.00it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.40it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.27it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.94it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.35it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.04it/s]
                                                            

Job chaiml-1030-quang-ir-lt-35485-v1-mkmlizer completed after 178.15s with status: succeeded
Stopping job with name chaiml-1030-quang-ir-lt-35485-v1-mkmlizer
Pipeline stage MKMLizer completed in 178.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1030-quang-ir-lt-35485-v1
Waiting for inference service chaiml-1030-quang-ir-lt-35485-v1 to be ready
Inference service chaiml-1030-quang-ir-lt-35485-v1 ready after 120.8865978717804s
Pipeline stage MKMLDeployer completed in 122.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7047905921936035s
Received healthy response to inference request in 2.3080332279205322s
Received healthy response to inference request in 2.685657501220703s
Received healthy response to inference request in 2.183950424194336s
Received healthy response to inference request in 2.370539665222168s
5 requests
0 failed requests
5th percentile: 2.208766984939575
10th percentile: 2.2335835456848145
20th percentile: 2.283216667175293
30th percentile: 2.320534515380859
40th percentile: 2.3455370903015136
50th percentile: 2.370539665222168
60th percentile: 2.496586799621582
70th percentile: 2.622633934020996
80th percentile: 2.689484119415283
90th percentile: 2.6971373558044434
95th percentile: 2.7009639739990234
99th percentile: 2.7040252685546875
mean time: 2.4505942821502686
Pipeline stage StressChecker completed in 13.75s
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 1.02s
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 0.85s
Shutdown handler de-registered
chaiml-1030-quang-ir-lt_35485_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 0.12s
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-1030-quang-ir-lt-35485-v1-profiler
Waiting for inference service chaiml-1030-quang-ir-lt-35485-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 5076.75s
Shutdown handler de-registered