chaiml-ir-v3-4-dpo-qcld_50792

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-4-dpo-qcld_50792_v1

model_name: training123

model_group: ChaiML/ir-v3-4-dpo_qcld-

status: torndown

timestamp: 2025-11-17T15:31:50+00:00

num_battles: 6014

num_wins: 3172

celo_rating: 1301.18

family_friendly_score: 0.5142

family_friendly_standard_error: 0.0070682156164056

submission_type: basic

model_repo: ChaiML/ir-v3-4-dpo_qcld-cosine

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': 0.37179348425603953, 'latency_mean': 2.6895695292949675, 'latency_p50': 2.684998631477356, 'latency_p90': 2.9254085779190064}, {'batch_size': 2, 'throughput': 0.5488985089169147, 'latency_mean': 3.6406293535232543, 'latency_p50': 3.6596890687942505, 'latency_p90': 3.9361576318740843}, {'batch_size': 3, 'throughput': 0.6801157648581643, 'latency_mean': 4.397033619880676, 'latency_p50': 4.3725385665893555, 'latency_p90': 4.801899933815003}, {'batch_size': 4, 'throughput': 0.7602880747130135, 'latency_mean': 5.2278524219989775, 'latency_p50': 5.192551016807556, 'latency_p90': 5.971492433547974}, {'batch_size': 5, 'throughput': 0.820269353274301, 'latency_mean': 6.076350144147873, 'latency_p50': 6.070416808128357, 'latency_p90': 6.948305416107178}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-4-dpo_qcld-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.56

us_pacific_date: 2025-11-14

win_ratio: 0.527435982707017

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', 'User:', '</s>', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-ir-v3-4-dpo-qcld-50792-v1-mkmlizer
Waiting for job on chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer to finish
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: quantized model in 42.243s
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: Processed model ChaiML/ir-v3-4-dpo_qcld-cosine in 123.827s
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-50792-v1/nvidia
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-50792-v1/nvidia/config.json
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-50792-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-50792-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-50792-v1/nvidia/tokenizer.json
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-50792-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-50792-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.79it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.41it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.30it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.93it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.15it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.70it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.81it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.99it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.62it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.28it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.58it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.90it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 32.19it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 28.14it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 31.98it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.67it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.52it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.96it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.46it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 33.75it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 29.51it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 31.65it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.48it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.32it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.08it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 34.52it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 32.95it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.31it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 34.36it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.86it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.93it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:08, 25.62it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.59it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.24it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.16it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.01it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.47it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 29.83it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 28.89it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.06it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:15,  1.19it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.08it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.40it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:30,  4.78it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.07it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.77it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:13,  9.92it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:11, 11.29it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 15.30it/s]
Loading 0:  66%|██████▌   | 240/363 [00:20<00:07, 16.41it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 22.70it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.80it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.16it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.71it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.94it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 23.68it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 22.97it/s]
Loading 0:  77%|███████▋  | 280/363 [00:22<00:03, 24.91it/s]
Loading 0:  78%|███████▊  | 284/363 [00:22<00:03, 24.06it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 31.66it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 30.85it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.16it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.47it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 30.00it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.68it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.35it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.23it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.90it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.14it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.17it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.14it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.79it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.40it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.99it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.59it/s]
                                                            
Job chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer completed after 197.4s with status: succeeded
Stopping job with name chaiml-ir-v3-4-dpo-qcld-50792-v1-mkmlizer
Pipeline stage MKMLizer completed in 198.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v3-4-dpo-qcld-50792-v1
Waiting for inference service chaiml-ir-v3-4-dpo-qcld-50792-v1 to be ready
Inference service chaiml-ir-v3-4-dpo-qcld-50792-v1 ready after 251.22760367393494s
Pipeline stage MKMLDeployer completed in 251.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4645798206329346s
Received healthy response to inference request in 2.174349308013916s
Received healthy response to inference request in 2.21435809135437s
Received healthy response to inference request in 2.807468891143799s
Received healthy response to inference request in 2.374234437942505s
5 requests
0 failed requests
5th percentile: 2.182351064682007
10th percentile: 2.1903528213500976
20th percentile: 2.206356334686279
30th percentile: 2.246333360671997
40th percentile: 2.310283899307251
50th percentile: 2.374234437942505
60th percentile: 2.410372591018677
70th percentile: 2.446510744094849
80th percentile: 2.5331576347351077
90th percentile: 2.670313262939453
95th percentile: 2.7388910770416257
99th percentile: 2.793753328323364
mean time: 2.406998109817505
Pipeline stage StressChecker completed in 14.06s
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 0.64s
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 0.66s
Shutdown handler de-registered
chaiml-ir-v3-4-dpo-qcld_50792_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3154.77s
Shutdown handler de-registered
chaiml-ir-v3-4-dpo-qcld_50792_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v3-4-dpo-qcld_50792_v1 status is now torndown due to DeploymentManager action