chaiml-1029-quang-ir-lt_69424

developer_uid: chai_backend_admin

submission_id: chaiml-1029-quang-ir-lt_69424_v1

model_name: training123

model_group: ChaiML/1029-quang-ir-ltr

status: inactive

timestamp: 2025-10-29T22:22:59+00:00

num_battles: 5613

num_wins: 2834

celo_rating: 1293.55

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1029-quang-ir-ltry-mix3-maxb3-10k

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': 0.37801792539591056, 'latency_mean': 2.6452589404582976, 'latency_p50': 2.64948308467865, 'latency_p90': 2.8780730247497557}, {'batch_size': 2, 'throughput': 0.5697566863271794, 'latency_mean': 3.500819721221924, 'latency_p50': 3.483996868133545, 'latency_p90': 3.8150503396987916}, {'batch_size': 3, 'throughput': 0.702819196081072, 'latency_mean': 4.25690354347229, 'latency_p50': 4.26134991645813, 'latency_p90': 4.754468011856079}, {'batch_size': 4, 'throughput': 0.7949998934722388, 'latency_mean': 5.016837646961212, 'latency_p50': 5.010170817375183, 'latency_p90': 5.726299595832825}, {'batch_size': 5, 'throughput': 0.8577086701284639, 'latency_mean': 5.805936306715012, 'latency_p50': 5.784236431121826, 'latency_p90': 6.5805198669433596}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1029-quang-ir-ltry-mix3-maxb3-10k

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-10-29

win_ratio: 0.504899340815963

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>', '\n', '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-1029-quang-ir-lt-69424-v1-mkmlizer
Waiting for job on chaiml-1029-quang-ir-lt-69424-v1-mkmlizer to finish
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: Downloaded to shared memory in 68.489s
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: Checking if ChaiML/1029-quang-ir-ltry-mix3-maxb3-10k already exists in ChaiML
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnrlisgh8, device:0
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: quantized model in 43.384s
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: Processed model ChaiML/1029-quang-ir-ltry-mix3-maxb3-10k in 111.873s
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-69424-v1/nvidia
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-69424-v1/nvidia/tokenizer.json
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-69424-v1/nvidia/flywheel_model.1.safetensors
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-69424-v1/nvidia/flywheel_model.0.safetensors
chaiml-1029-quang-ir-lt-69424-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.75it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.44it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.86it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.60it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 35.48it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 40.32it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.28it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.43it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.45it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 28.19it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 31.65it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.12it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 30.40it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 27.27it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:12, 23.15it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.26it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.30it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 26.44it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 25.54it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 32.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 30.35it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 25.90it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 28.59it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.25it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.82it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.46it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 33.03it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.55it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 33.86it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 30.87it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 36.99it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.25it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.48it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.12it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 29.79it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 32.79it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.07it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 30.54it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 27.87it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:06, 25.37it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.21it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:11,  1.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:56,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:15,  2.06it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:58,  2.59it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:45,  3.28it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:31,  4.57it/s]
Loading 0:  61%|██████    | 221/363 [00:21<00:25,  5.63it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:20,  6.80it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:13,  9.96it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:11, 11.75it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 16.06it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.06it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 22.62it/s]
Loading 0:  69%|██████▉   | 250/363 [00:22<00:04, 23.26it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:03, 27.57it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:03, 27.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 33.78it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:04, 22.82it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 22.34it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:03, 26.42it/s]
Loading 0:  78%|███████▊  | 284/363 [00:23<00:03, 23.16it/s]
Loading 0:  80%|███████▉  | 289/363 [00:23<00:02, 27.33it/s]
Loading 0:  81%|████████  | 293/363 [00:23<00:02, 24.65it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 30.06it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 27.53it/s]
Loading 0:  85%|████████▍ | 308/363 [00:24<00:02, 27.17it/s]
Loading 0:  86%|████████▌ | 311/363 [00:24<00:02, 22.97it/s]
Loading 0:  88%|████████▊ | 318/363 [00:24<00:01, 30.50it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 28.86it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 32.11it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 30.02it/s]
Loading 0:  92%|█████████▏| 335/363 [00:25<00:00, 30.90it/s]
Loading 0:  93%|█████████▎| 339/363 [00:25<00:00, 31.24it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:01, 19.01it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 20.74it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 27.90it/s]
Loading 0:  99%|█████████▉| 359/363 [00:26<00:00, 27.18it/s]
                                                            
Job chaiml-1029-quang-ir-lt-69424-v1-mkmlizer completed after 186.4s with status: succeeded
Stopping job with name chaiml-1029-quang-ir-lt-69424-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.95s
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-1029-quang-ir-lt-69424-v1
Waiting for inference service chaiml-1029-quang-ir-lt-69424-v1 to be ready
Inference service chaiml-1029-quang-ir-lt-69424-v1 ready after 110.95069122314453s
Pipeline stage MKMLDeployer completed in 111.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.336394786834717s
Received healthy response to inference request in 2.8541555404663086s
Received healthy response to inference request in 2.5606396198272705s
Received healthy response to inference request in 2.1624178886413574s
Received healthy response to inference request in 2.6040050983428955s
5 requests
0 failed requests
5th percentile: 2.1972132682800294
10th percentile: 2.2320086479187013
20th percentile: 2.301599407196045
30th percentile: 2.3812437534332274
40th percentile: 2.470941686630249
50th percentile: 2.5606396198272705
60th percentile: 2.5779858112335203
70th percentile: 2.5953320026397706
80th percentile: 2.654035186767578
90th percentile: 2.754095363616943
95th percentile: 2.804125452041626
99th percentile: 2.8441495227813722
mean time: 2.50352258682251
Pipeline stage StressChecker completed in 13.95s
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 0.73s
Shutdown handler de-registered
chaiml-1029-quang-ir-lt_69424_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5461.52s
Shutdown handler de-registered
chaiml-1029-quang-ir-lt_69424_v1 status is now protected due to ABTestQueueItem