chaiml-ir-v4-3-dpo-irv1_44221

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-3-dpo-irv1_44221_v1

model_name: training123

model_group: ChaiML/ir-v4-3-dpo_irv13

status: inactive

timestamp: 2025-11-01T23:04:00+00:00

num_battles: 5112

num_wins: 2647

celo_rating: 1307.33

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-3-dpo_irv13-lr5e6b01

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': 0.3779090568880279, 'latency_mean': 2.6460428369045257, 'latency_p50': 2.6562494039535522, 'latency_p90': 2.8974939823150634}, {'batch_size': 2, 'throughput': 0.569079256196741, 'latency_mean': 3.514038466215134, 'latency_p50': 3.5204821825027466, 'latency_p90': 3.7995271921157836}, {'batch_size': 3, 'throughput': 0.7088708644596571, 'latency_mean': 4.230715661048889, 'latency_p50': 4.221306562423706, 'latency_p90': 4.688268446922303}, {'batch_size': 4, 'throughput': 0.7978133365451013, 'latency_mean': 4.988119666576385, 'latency_p50': 4.987957954406738, 'latency_p90': 5.658111119270324}, {'batch_size': 5, 'throughput': 0.8594740914135673, 'latency_mean': 5.792098504304886, 'latency_p50': 5.776260614395142, 'latency_p90': 6.5628715515136715}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-3-dpo_irv13-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-01

win_ratio: 0.5178012519561815

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>', '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-v4-3-dpo-irv1-44221-v1-mkmlizer
Waiting for job on chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer to finish
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: Downloaded to shared memory in 52.492s
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: Checking if ChaiML/ir-v4-3-dpo_irv13-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp368sslz7, device:0
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-v4-3-dpo-irv1-44221-v1-mkmlizer: quantized model in 42.629s
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: Processed model ChaiML/ir-v4-3-dpo_irv13-lr5e6b01 in 95.122s
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-44221-v1/nvidia
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-44221-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-44221-v1/nvidia/config.json
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-44221-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-44221-v1/nvidia/tokenizer.json
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-44221-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.29it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.15it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 34.68it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 34.96it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 35.35it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 40.36it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.15it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.39it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.65it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.83it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.27it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.45it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.81it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 29.13it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.67it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.48it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.80it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.37it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.53it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 26.96it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.75it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.82it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.79it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 31.40it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.27it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.59it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.79it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.01it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.51it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.46it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 25.64it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.72it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.70it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.77it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.71it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.38it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 31.49it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.89it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.52it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:16,  1.19it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.62it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:40,  3.66it/s]
Loading 0:  60%|██████    | 219/363 [00:20<00:29,  4.88it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.77it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.32it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:12, 10.77it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 14.60it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:07, 16.92it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 21.26it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 22.81it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.10it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.10it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.17it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:03, 23.55it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.38it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.34it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.60it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.34it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.84it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.78it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.85it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.93it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.71it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 30.93it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.77it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.01it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 27.58it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:01, 26.24it/s]
Loading 0:  93%|█████████▎| 338/363 [00:24<00:01, 23.43it/s]
Loading 0:  94%|█████████▍| 341/363 [00:24<00:01, 14.06it/s]
Loading 0:  96%|█████████▌| 347/363 [00:24<00:00, 19.57it/s]
Loading 0:  96%|█████████▋| 350/363 [00:25<00:00, 20.84it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 25.54it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 26.07it/s]
                                                            
Job chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer completed after 154.9s with status: succeeded
Stopping job with name chaiml-ir-v4-3-dpo-irv1-44221-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.40s
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-v4-3-dpo-irv1-44221-v1
Waiting for inference service chaiml-ir-v4-3-dpo-irv1-44221-v1 to be ready
Inference service chaiml-ir-v4-3-dpo-irv1-44221-v1 ready after 130.94811511039734s
Pipeline stage MKMLDeployer completed in 131.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5664846897125244s
Received healthy response to inference request in 2.1187095642089844s
Received healthy response to inference request in 2.3232975006103516s
Received healthy response to inference request in 2.21311616897583s
Received healthy response to inference request in 2.4297516345977783s
5 requests
0 failed requests
5th percentile: 2.1375908851623535
10th percentile: 2.1564722061157227
20th percentile: 2.194234848022461
30th percentile: 2.2351524353027346
40th percentile: 2.279224967956543
50th percentile: 2.3232975006103516
60th percentile: 2.3658791542053224
70th percentile: 2.408460807800293
80th percentile: 2.4570982456207275
90th percentile: 2.511791467666626
95th percentile: 2.539138078689575
99th percentile: 2.5610153675079346
mean time: 2.330271911621094
Pipeline stage StressChecker completed in 13.01s
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 0.68s
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 0.97s
Shutdown handler de-registered
chaiml-ir-v4-3-dpo-irv1_44221_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
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 5701.34s
Shutdown handler de-registered