chaiml-ir-v3-4-dpo-qcld

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-4-dpo-qcld_v1

model_name: training123

model_group: ChaiML/ir-v3-4-dpo_qcld

status: torndown

timestamp: 2025-11-17T14:06:33+00:00

num_battles: 6212

num_wins: 3272

celo_rating: 1300.03

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v3-4-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': 0.3736315128091021, 'latency_mean': 2.6763088488578797, 'latency_p50': 2.679563522338867, 'latency_p90': 2.92672655582428}, {'batch_size': 2, 'throughput': 0.5461843215599302, 'latency_mean': 3.6561028349399565, 'latency_p50': 3.650795102119446, 'latency_p90': 4.032947731018067}, {'batch_size': 3, 'throughput': 0.6729522839067892, 'latency_mean': 4.448567165136337, 'latency_p50': 4.462081074714661, 'latency_p90': 5.0642575263977045}, {'batch_size': 4, 'throughput': 0.7624007162964478, 'latency_mean': 5.229879035949707, 'latency_p50': 5.224281430244446, 'latency_p90': 5.909636998176574}, {'batch_size': 5, 'throughput': 0.816253531207093, 'latency_mean': 6.109265882968902, 'latency_p50': 6.089614987373352, 'latency_p90': 7.043081665039062}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-4-dpo_qcld

model_size: 24B

ranking_group: single

throughput_3p7s: 0.56

us_pacific_date: 2025-11-14

win_ratio: 0.5267224726336124

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': ['</s>', '\n', 'User:', '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-v1-mkmlizer
Waiting for job on chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer to finish
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: Downloaded to shared memory in 66.831s
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: Checking if ChaiML/ir-v3-4-dpo_qcld already exists in ChaiML
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyod6bv4c, device:0
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: quantized model in 41.920s
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: Processed model ChaiML/ir-v3-4-dpo_qcld in 108.751s
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-v1/nvidia
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-v1/nvidia/config.json
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-v1/nvidia/tokenizer.json
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-4-dpo-qcld-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.98it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 40.36it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.39it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 37.39it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 40.08it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 41.94it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.83it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.65it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.47it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.32it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.16it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.45it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.69it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.99it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.81it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.87it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.90it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.46it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.45it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.16it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 33.48it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 29.56it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 31.78it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 32.24it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 34.05it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.39it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.09it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.99it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.53it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.07it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.72it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 28.00it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 25.77it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.82it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.39it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.60it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.34it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.24it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.74it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.23it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.17it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.13it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.68it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.46it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.86it/s]
Loading 0:  61%|██████    | 221/363 [00:19<00:23,  6.12it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:18,  7.38it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.68it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.47it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.73it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 18.50it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 23.02it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 23.43it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:03, 27.46it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.88it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.66it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:04, 22.65it/s]
Loading 0:  75%|███████▌  | 274/363 [00:21<00:03, 25.49it/s]
Loading 0:  77%|███████▋  | 278/363 [00:21<00:03, 27.30it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 29.58it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 28.06it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 31.73it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 29.76it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 30.94it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 28.13it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 27.52it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 22.86it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 30.32it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.44it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 32.89it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 30.50it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 31.41it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 31.57it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.44it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 20.96it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 28.26it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 27.89it/s]
                                                            
Job chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer completed after 155.56s with status: succeeded
Stopping job with name chaiml-ir-v3-4-dpo-qcld-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.12s
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-ir-v3-4-dpo-qcld-v1
Waiting for inference service chaiml-ir-v3-4-dpo-qcld-v1 to be ready
Inference service chaiml-ir-v3-4-dpo-qcld-v1 ready after 161.39195704460144s
Pipeline stage MKMLDeployer completed in 162.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.479228973388672s
Received healthy response to inference request in 2.4984912872314453s
Received healthy response to inference request in 2.3435769081115723s
Received healthy response to inference request in 2.722073554992676s
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', '')
Received healthy response to inference request in 2.1740384101867676s
5 requests
0 failed requests
5th percentile: 2.2079461097717283
10th percentile: 2.2418538093566895
20th percentile: 2.3096692085266115
30th percentile: 2.370707321166992
40th percentile: 2.424968147277832
50th percentile: 2.479228973388672
60th percentile: 2.4869338989257814
70th percentile: 2.4946388244628905
80th percentile: 2.5432077407836915
90th percentile: 2.6326406478881834
95th percentile: 2.6773571014404296
99th percentile: 2.7131302642822264
mean time: 2.4434818267822265
Pipeline stage StressChecker completed in 13.53s
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 1.30s
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_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 5684.82s
Shutdown handler de-registered
chaiml-ir-v3-4-dpo-qcld_v1 status is now torndown due to DeploymentManager action