chaiml-ir-v3-1-dpo-irv0_16815

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-1-dpo-irv0_16815_v1

model_name: training123

model_group: ChaiML/ir-v3-1-dpo_irv0f

status: inactive

timestamp: 2025-10-29T07:37:01+00:00

num_battles: 5703

num_wins: 2888

celo_rating: 1293.04

family_friendly_score: 0.4424

family_friendly_standard_error: 0.007023990888376778

submission_type: basic

model_repo: ChaiML/ir-v3-1-dpo_irv0fullpyg-lr5e6b01-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': 0.3860887624738974, 'latency_mean': 2.589980150461197, 'latency_p50': 2.594445824623108, 'latency_p90': 2.8349338293075563}, {'batch_size': 2, 'throughput': 0.5784782789412788, 'latency_mean': 3.452646692991257, 'latency_p50': 3.429213285446167, 'latency_p90': 3.7262171030044553}, {'batch_size': 3, 'throughput': 0.7196204388151107, 'latency_mean': 4.16171728849411, 'latency_p50': 4.171720623970032, 'latency_p90': 4.706162858009338}, {'batch_size': 4, 'throughput': 0.8091700019881972, 'latency_mean': 4.918779562711716, 'latency_p50': 4.899496674537659, 'latency_p90': 5.756685495376587}, {'batch_size': 5, 'throughput': 0.8836119008326278, 'latency_mean': 5.637150354385376, 'latency_p50': 5.611813306808472, 'latency_p90': 6.3276273012161255}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-1-dpo_irv0fullpyg-lr5e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-10-29

win_ratio: 0.5064001402770472

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>', 'You:', 'User:', '\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-v3-1-dpo-irv0-16815-v1-mkmlizer
Waiting for job on chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer to finish
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: Downloaded to shared memory in 63.458s
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: Checking if ChaiML/ir-v3-1-dpo_irv0fullpyg-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9hdxk3vy, device:0
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: quantized model in 42.349s
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: Processed model ChaiML/ir-v3-1-dpo_irv0fullpyg-lr5e6b01-cosine in 105.807s
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-16815-v1/nvidia
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-16815-v1/nvidia/config.json
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-16815-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-16815-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-16815-v1/nvidia/tokenizer.json
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-16815-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-16815-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.88it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 37.50it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.22it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.11it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.78it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:11, 28.04it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:14, 22.87it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:13, 22.84it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:16, 19.47it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 23.77it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:14, 20.59it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.23it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.32it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.48it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 26.37it/s]
Loading 0:  23%|██▎       | 83/363 [00:03<00:09, 28.01it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 25.80it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 25.88it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.24it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.86it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.47it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 29.98it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 30.74it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:07, 31.86it/s]
Loading 0:  34%|███▍      | 125/363 [00:04<00:07, 33.39it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.95it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.28it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.75it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.61it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 39.71it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.68it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.95it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.14it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.33it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 34.44it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.91it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 32.93it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.73it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.32it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.62it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 212/363 [00:20<00:53,  2.80it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:33,  4.37it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.70it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.00it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:09, 13.27it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:07, 15.30it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:06, 19.25it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 20.81it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 25.15it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.13it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.30it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 24.80it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.87it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.76it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.40it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.78it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.48it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 33.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 30.28it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.64it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.96it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.83it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.06it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.53it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:00, 32.87it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 33.84it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.44it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.45it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.03it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.64it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.89it/s]
                                                            
Job chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer completed after 173.99s with status: succeeded
Stopping job with name chaiml-ir-v3-1-dpo-irv0-16815-v1-mkmlizer
Pipeline stage MKMLizer completed in 174.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v3-1-dpo-irv0-16815-v1
Waiting for inference service chaiml-ir-v3-1-dpo-irv0-16815-v1 to be ready
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', '')
Inference service chaiml-ir-v3-1-dpo-irv0-16815-v1 ready after 100.59826231002808s
Pipeline stage MKMLDeployer completed in 101.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.631434440612793s
Received healthy response to inference request in 2.125465154647827s
Received healthy response to inference request in 2.3848283290863037s
Received healthy response to inference request in 2.135939598083496s
Received healthy response to inference request in 2.182844877243042s
5 requests
0 failed requests
5th percentile: 2.127560043334961
10th percentile: 2.1296549320220945
20th percentile: 2.1338447093963624
30th percentile: 2.1453206539154053
40th percentile: 2.1640827655792236
50th percentile: 2.182844877243042
60th percentile: 2.2636382579803467
70th percentile: 2.3444316387176514
80th percentile: 2.4341495513916014
90th percentile: 2.532791996002197
95th percentile: 2.5821132183074953
99th percentile: 2.6215701961517333
mean time: 2.2921024799346923
Pipeline stage StressChecker completed in 12.81s
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 0.68s
Shutdown handler de-registered
chaiml-ir-v3-1-dpo-irv0_16815_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 3041.62s
Shutdown handler de-registered
chaiml-ir-v3-1-dpo-irv0_16815_v1 status is now inactive due to auto deactivation removed underperforming models