chaiml-1108-quang-ir-mi_78509

developer_uid: chai_backend_admin

submission_id: chaiml-1108-quang-ir-mi_78509_v1

model_name: training123

model_group: ChaiML/1108-quang-ir-mix

status: torndown

timestamp: 2025-11-11T17:51:30+00:00

num_battles: 5308

num_wins: 2631

celo_rating: 1296.81

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_mult25k_0164641ep_5e6cs

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': 0.38749915503429094, 'latency_mean': 2.580546160936356, 'latency_p50': 2.5875335931777954, 'latency_p90': 2.849405813217163}, {'batch_size': 2, 'throughput': 0.5782662162218456, 'latency_mean': 3.456367172002792, 'latency_p50': 3.4499658346176147, 'latency_p90': 3.746471571922302}, {'batch_size': 3, 'throughput': 0.7181892939680726, 'latency_mean': 4.159419583082199, 'latency_p50': 4.154499650001526, 'latency_p90': 4.577806520462036}, {'batch_size': 4, 'throughput': 0.8166131354614015, 'latency_mean': 4.888811008930206, 'latency_p50': 4.8780670166015625, 'latency_p90': 5.612896728515625}, {'batch_size': 5, 'throughput': 0.877957413042036, 'latency_mean': 5.6716567838191985, 'latency_p50': 5.6554800271987915, 'latency_p90': 6.464645099639893}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_mult25k_0164641ep_5e6cs

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-11-08

win_ratio: 0.4956669178598342

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': ['You:', '####', '</s>', '\n'], '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-1108-quang-ir-mi-78509-v1-mkmlizer
Waiting for job on chaiml-1108-quang-ir-mi-78509-v1-mkmlizer to finish
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ║                                                                     ║
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: Downloaded to shared memory in 57.023s
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: Checking if ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_mult25k_0164641ep_5e6cs already exists in ChaiML
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppmtl9_41, device:0
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: quantized model in 42.236s
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: Processed model ChaiML/1108-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_mult25k_0164641ep_5e6cs in 99.260s
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-78509-v1/nvidia
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-78509-v1/nvidia/config.json
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-78509-v1/nvidia/special_tokens_map.json
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-78509-v1/nvidia/tokenizer_config.json
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-78509-v1/nvidia/tokenizer.json
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-78509-v1/nvidia/flywheel_model.1.safetensors
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1108-quang-ir-mi-78509-v1/nvidia/flywheel_model.0.safetensors
chaiml-1108-quang-ir-mi-78509-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.22it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 37.90it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.30it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.64it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.18it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.00it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.52it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.50it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.74it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.05it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.08it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.71it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.61it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.19it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.67it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 27.79it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.41it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.79it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.56it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.87it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.33it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.03it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.00it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.44it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.06it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 32.99it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.22it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.76it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.21it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.89it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.47it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.55it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.38it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.70it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.27it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 34.07it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 31.58it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 30.36it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 27.21it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 215/363 [00:19<00:39,  3.71it/s]
Loading 0:  60%|██████    | 219/363 [00:19<00:29,  4.95it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.88it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.50it/s]
Loading 0:  64%|██████▍   | 233/363 [00:20<00:11, 11.54it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.90it/s]
Loading 0:  66%|██████▌   | 240/363 [00:20<00:08, 14.56it/s]
Loading 0:  67%|██████▋   | 244/363 [00:20<00:06, 17.73it/s]
Loading 0:  68%|██████▊   | 247/363 [00:20<00:05, 19.65it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 20.97it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 26.24it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.54it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.21it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:04, 23.01it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.03it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.20it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.33it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.63it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.72it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.54it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 29.95it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 29.23it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.23it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.04it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.07it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.20it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.92it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.84it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.35it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.26it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.82it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.12it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.51it/s]
                                                            
Job chaiml-1108-quang-ir-mi-78509-v1-mkmlizer completed after 145.97s with status: succeeded
Stopping job with name chaiml-1108-quang-ir-mi-78509-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.71s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1108-quang-ir-mi-78509-v1
Waiting for inference service chaiml-1108-quang-ir-mi-78509-v1 to be ready
Inference service chaiml-1108-quang-ir-mi-78509-v1 ready after 191.28553080558777s
Pipeline stage MKMLDeployer completed in 191.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0470709800720215s
Received healthy response to inference request in 2.580737352371216s
Received healthy response to inference request in 2.3223018646240234s
Received healthy response to inference request in 3.0098724365234375s
Received healthy response to inference request in 2.343647003173828s
5 requests
0 failed requests
5th percentile: 2.3265708923339843
10th percentile: 2.330839920043945
20th percentile: 2.3393779754638673
30th percentile: 2.391065073013306
40th percentile: 2.485901212692261
50th percentile: 2.580737352371216
60th percentile: 2.7523913860321043
70th percentile: 2.9240454196929933
80th percentile: 3.0173121452331544
90th percentile: 3.0321915626525877
95th percentile: 3.0396312713623046
99th percentile: 3.045583038330078
mean time: 2.6607259273529054
Pipeline stage StressChecker completed in 14.68s
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 0.57s
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 0.61s
Shutdown handler de-registered
chaiml-1108-quang-ir-mi_78509_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 0.10s
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-1108-quang-ir-mi-78509-v1-profiler
Waiting for inference service chaiml-1108-quang-ir-mi-78509-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 5724.92s
Shutdown handler de-registered
chaiml-1108-quang-ir-mi_78509_v1 status is now torndown due to DeploymentManager action