chaiml-1029-quang-ir-lt_83471

developer_uid: chai_backend_admin

submission_id: chaiml-1029-quang-ir-lt_83471_v1

model_name: training123

model_group: ChaiML/1029-quang-ir-ltr

status: inactive

timestamp: 2025-10-30T03:56:55+00:00

num_battles: 6277

num_wins: 3210

celo_rating: 1291.82

family_friendly_score: 0.4638

family_friendly_standard_error: 0.007052511042174979

submission_type: basic

model_repo: ChaiML/1029-quang-ir-ltry-mix3-maxb3-10k-dpo_1e5

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': 0.38091912263706795, 'latency_mean': 2.6251321518421173, 'latency_p50': 2.6374908685684204, 'latency_p90': 2.8905166387557983}, {'batch_size': 2, 'throughput': 0.5714298427376518, 'latency_mean': 3.493771376609802, 'latency_p50': 3.4930258989334106, 'latency_p90': 3.8071805238723755}, {'batch_size': 3, 'throughput': 0.702859355499499, 'latency_mean': 4.263049312829971, 'latency_p50': 4.270023941993713, 'latency_p90': 4.64889349937439}, {'batch_size': 4, 'throughput': 0.8032077255215601, 'latency_mean': 4.966972348690033, 'latency_p50': 4.959353923797607, 'latency_p90': 5.763944458961487}, {'batch_size': 5, 'throughput': 0.862758409015441, 'latency_mean': 5.752700023651123, 'latency_p50': 5.78163754940033, 'latency_p90': 6.517677974700928}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1029-quang-ir-ltry-mix3-maxb3-10k-dpo_1e5

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-10-29

win_ratio: 0.5113907917795125

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-1029-quang-ir-lt-83471-v1-mkmlizer
Waiting for job on chaiml-1029-quang-ir-lt-83471-v1-mkmlizer to finish
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ║                                                                     ║
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: Downloaded to shared memory in 62.989s
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: Checking if ChaiML/1029-quang-ir-ltry-mix3-maxb3-10k-dpo_1e5 already exists in ChaiML
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj9qmfydi, device:0
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: quantized model in 43.214s
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: Processed model ChaiML/1029-quang-ir-ltry-mix3-maxb3-10k-dpo_1e5 in 106.204s
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-83471-v1/nvidia
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-83471-v1/nvidia/config.json
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-83471-v1/nvidia/tokenizer_config.json
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-83471-v1/nvidia/special_tokens_map.json
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-83471-v1/nvidia/tokenizer.json
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-83471-v1/nvidia/flywheel_model.1.safetensors
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1029-quang-ir-lt-83471-v1/nvidia/flywheel_model.0.safetensors
chaiml-1029-quang-ir-lt-83471-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.32it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.14it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.84it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.32it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.80it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.53it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.74it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.05it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.27it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 32.63it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 29.24it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 25.97it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.30it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:18, 15.48it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:17, 16.02it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:16, 17.79it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:15, 17.89it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.38it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:11, 24.65it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:11, 23.84it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 30.51it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 29.96it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 26.20it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 29.24it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 30.23it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 32.49it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 31.19it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.33it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.04it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.55it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:06, 33.38it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 40.13it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.13it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.35it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.56it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.44it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 34.62it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.89it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.63it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.91it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.02it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.17it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 212/363 [00:20<00:53,  2.80it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:33,  4.37it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.70it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.02it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.63it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:09, 13.37it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:07, 15.48it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:06, 19.43it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 21.27it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 25.60it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.39it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.44it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:04, 20.07it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:04, 20.34it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 27.08it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:03, 25.16it/s]
Loading 0:  80%|███████▉  | 290/363 [00:22<00:02, 26.58it/s]
Loading 0:  81%|████████  | 294/363 [00:23<00:02, 24.94it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 25.57it/s]
Loading 0:  83%|████████▎ | 303/363 [00:23<00:02, 28.30it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:03, 18.47it/s]
Loading 0:  86%|████████▌ | 311/363 [00:24<00:02, 19.21it/s]
Loading 0:  88%|████████▊ | 318/363 [00:24<00:01, 26.73it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 27.26it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 31.08it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 26.59it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:01, 24.31it/s]
Loading 0:  93%|█████████▎| 338/363 [00:24<00:01, 22.63it/s]
Loading 0:  94%|█████████▍| 341/363 [00:25<00:01, 15.35it/s]
Loading 0:  96%|█████████▌| 347/363 [00:25<00:00, 21.06it/s]
Loading 0:  96%|█████████▋| 350/363 [00:25<00:00, 22.23it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 27.05it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 27.42it/s]
Loading 0: 100%|██████████| 363/363 [00:25<00:00, 30.09it/s]
                                                            
Job chaiml-1029-quang-ir-lt-83471-v1-mkmlizer completed after 185.26s with status: succeeded
Stopping job with name chaiml-1029-quang-ir-lt-83471-v1-mkmlizer
Pipeline stage MKMLizer completed in 185.83s
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-83471-v1
Waiting for inference service chaiml-1029-quang-ir-lt-83471-v1 to be ready
Inference service chaiml-1029-quang-ir-lt-83471-v1 ready after 110.68137955665588s
Pipeline stage MKMLDeployer completed in 111.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5002801418304443s
Received healthy response to inference request in 2.1311862468719482s
Received healthy response to inference request in 2.3397223949432373s
Received healthy response to inference request in 2.0858230590820312s
Received healthy response to inference request in 2.205721378326416s
5 requests
0 failed requests
5th percentile: 2.0948956966400147
10th percentile: 2.1039683341979982
20th percentile: 2.1221136093139648
30th percentile: 2.1460932731628417
40th percentile: 2.175907325744629
50th percentile: 2.205721378326416
60th percentile: 2.2593217849731446
70th percentile: 2.3129221916198732
80th percentile: 2.3718339443206786
90th percentile: 2.4360570430755617
95th percentile: 2.468168592453003
99th percentile: 2.4938578319549563
mean time: 2.2525466442108155
Pipeline stage StressChecker completed in 12.52s
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 0.65s
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 0.68s
Shutdown handler de-registered
chaiml-1029-quang-ir-lt_83471_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 0.11s
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-1029-quang-ir-lt-83471-v1-profiler
Waiting for inference service chaiml-1029-quang-ir-lt-83471-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 3048.14s
Shutdown handler de-registered
chaiml-1029-quang-ir-lt_83471_v1 status is now inactive due to auto deactivation removed underperforming models