chaiml-ir-v3-2-dpo-qcld

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-2-dpo-qcld_v1

model_name: training123

model_group: ChaiML/ir-v3-2-dpo_qcld

status: torndown

timestamp: 2025-11-17T11:21:27+00:00

num_battles: 6904

num_wins: 3610

celo_rating: 1297.12

family_friendly_score: 0.49560000000000004

family_friendly_standard_error: 0.007070794014818986

submission_type: basic

model_repo: ChaiML/ir-v3-2-dpo_qcld

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': 0.37795586227575634, 'latency_mean': 2.6456910276412966, 'latency_p50': 2.6389304399490356, 'latency_p90': 2.9100619077682497}, {'batch_size': 2, 'throughput': 0.5633233632436739, 'latency_mean': 3.546224261522293, 'latency_p50': 3.5386193990707397, 'latency_p90': 3.8782641887664795}, {'batch_size': 3, 'throughput': 0.6895915757996404, 'latency_mean': 4.338964780569077, 'latency_p50': 4.33689558506012, 'latency_p90': 4.835225677490234}, {'batch_size': 4, 'throughput': 0.7799943343116315, 'latency_mean': 5.117029677629471, 'latency_p50': 5.123722314834595, 'latency_p90': 5.962108707427978}, {'batch_size': 5, 'throughput': 0.8397864470531864, 'latency_mean': 5.934356656074524, 'latency_p50': 5.955924153327942, 'latency_p90': 6.712224817276001}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-2-dpo_qcld

model_size: 24B

ranking_group: single

throughput_3p7s: 0.59

us_pacific_date: 2025-11-14

win_ratio: 0.5228852838933952

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:', 'User:', '</s>', '\n'], '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-v3-2-dpo-qcld-v1-mkmlizer
Waiting for job on chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer to finish
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-qcld-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-v3-2-dpo-qcld-v1-mkmlizer: Downloaded to shared memory in 56.440s
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: Checking if ChaiML/ir-v3-2-dpo_qcld already exists in ChaiML
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcsonrq4k, device:0
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: quantized model in 42.979s
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: Processed model ChaiML/ir-v3-2-dpo_qcld in 99.419s
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-qcld-v1/nvidia
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-qcld-v1/nvidia/config.json
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-qcld-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-qcld-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-qcld-v1/nvidia/tokenizer.json
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-qcld-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-qcld-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.84it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 37.61it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 39.05it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:13, 25.72it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 36.90it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.81it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.21it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.37it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.08it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.54it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.87it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.77it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.81it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.83it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.94it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.82it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.00it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:09, 27.74it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.38it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 33.67it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 29.33it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 31.84it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 32.55it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 34.01it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 32.10it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.52it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 33.51it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.40it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 34.05it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.52it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.93it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 25.87it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.17it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.97it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.08it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.85it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.89it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.47it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.68it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.69it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.13it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.69it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:42,  3.47it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.89it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:21,  6.70it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.35it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:12, 10.27it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.03it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 17.90it/s]
Loading 0:  67%|██████▋   | 245/363 [00:20<00:05, 20.38it/s]
Loading 0:  69%|██████▊   | 249/363 [00:20<00:05, 19.69it/s]
Loading 0:  70%|██████▉   | 253/363 [00:20<00:04, 22.84it/s]
Loading 0:  71%|███████   | 257/363 [00:21<00:04, 21.41it/s]
Loading 0:  72%|███████▏  | 262/363 [00:21<00:03, 26.33it/s]
Loading 0:  74%|███████▎  | 267/363 [00:21<00:03, 25.96it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:04, 21.81it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:04, 19.09it/s]
Loading 0:  77%|███████▋  | 280/363 [00:22<00:03, 22.59it/s]
Loading 0:  78%|███████▊  | 283/363 [00:22<00:03, 22.11it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:03, 23.41it/s]
Loading 0:  80%|███████▉  | 289/363 [00:22<00:03, 22.47it/s]
Loading 0:  80%|████████  | 292/363 [00:22<00:03, 22.06it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:03, 21.03it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 24.47it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 24.63it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:02, 20.45it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 20.66it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 29.07it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 28.78it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 32.55it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 31.13it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.22it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 28.25it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 18.89it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 20.86it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.34it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 23.96it/s]
                                                            
Job chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer completed after 167.68s with status: succeeded
Stopping job with name chaiml-ir-v3-2-dpo-qcld-v1-mkmlizer
Pipeline stage MKMLizer completed in 170.70s
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-v3-2-dpo-qcld-v1
Waiting for inference service chaiml-ir-v3-2-dpo-qcld-v1 to be ready
Inference service chaiml-ir-v3-2-dpo-qcld-v1 ready after 150.54710054397583s
Pipeline stage MKMLDeployer completed in 151.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.483189582824707s
Received healthy response to inference request in 2.6319656372070312s
Received healthy response to inference request in 2.400073766708374s
Received healthy response to inference request in 2.2740731239318848s
Received healthy response to inference request in 2.279439926147461s
5 requests
0 failed requests
5th percentile: 2.275146484375
10th percentile: 2.2762198448181152
20th percentile: 2.2783665657043457
30th percentile: 2.3035666942596436
40th percentile: 2.351820230484009
50th percentile: 2.400073766708374
60th percentile: 2.433320093154907
70th percentile: 2.4665664196014405
80th percentile: 2.512944793701172
90th percentile: 2.5724552154541014
95th percentile: 2.6022104263305663
99th percentile: 2.626014595031738
mean time: 2.4137484073638915
Pipeline stage StressChecker completed in 13.44s
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 0.63s
Shutdown handler de-registered
chaiml-ir-v3-2-dpo-qcld_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 3197.90s
Shutdown handler de-registered
chaiml-ir-v3-2-dpo-qcld_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v3-2-dpo-qcld_v1 status is now torndown due to DeploymentManager action