chaiml-ir-v3-1-dpo-irv1_80635

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-1-dpo-irv1_80635_v1

model_name: training123

model_group: ChaiML/ir-v3-1-dpo_irv13

status: inactive

timestamp: 2025-10-29T02:11:07+00:00

num_battles: 6374

num_wins: 3314

celo_rating: 1299.17

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v3-1-dpo_irv13-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': 0.3821839895235416, 'latency_mean': 2.6164286243915558, 'latency_p50': 2.6318949460983276, 'latency_p90': 2.884813928604126}, {'batch_size': 2, 'throughput': 0.5760796653234568, 'latency_mean': 3.467172530889511, 'latency_p50': 3.4685763120651245, 'latency_p90': 3.7682977676391602}, {'batch_size': 3, 'throughput': 0.7137009166001099, 'latency_mean': 4.187714673280716, 'latency_p50': 4.182128667831421, 'latency_p90': 4.725768351554871}, {'batch_size': 4, 'throughput': 0.8151320136355444, 'latency_mean': 4.891787782907486, 'latency_p50': 4.866853833198547, 'latency_p90': 5.459507298469544}, {'batch_size': 5, 'throughput': 0.8715761743327316, 'latency_mean': 5.716469757556915, 'latency_p50': 5.723289370536804, 'latency_p90': 6.52577543258667}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-1-dpo_irv13-lr5e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-10-28

win_ratio: 0.519924694069658

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-v3-1-dpo-irv1-80635-v1-mkmlizer
Waiting for job on chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer to finish
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: Downloaded to shared memory in 75.932s
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: Checking if ChaiML/ir-v3-1-dpo_irv13-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpybn3la2m, device:0
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: quantized model in 41.979s
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: Processed model ChaiML/ir-v3-1-dpo_irv13-lr5e6b01-cosine in 117.912s
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv1-80635-v1/nvidia
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv1-80635-v1/nvidia/config.json
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv1-80635-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv1-80635-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv1-80635-v1/nvidia/tokenizer.json
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv1-80635-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv1-80635-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:18, 19.72it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.58it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.37it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.89it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 39.45it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 41.96it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.80it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.27it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.07it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.32it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.03it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.98it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:08, 35.36it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 29.02it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.81it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.95it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.50it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 27.89it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:09, 27.45it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.88it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.95it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.93it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.40it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.39it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.10it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.62it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.06it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.43it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.69it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.44it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.09it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.03it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.32it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.51it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.61it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.70it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.10it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.96it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 29.35it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.92it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.97it/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 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 215/363 [00:19<00:39,  3.71it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:30,  4.72it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.04it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.27it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.66it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.60it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.23it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 19.50it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:04, 24.42it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 25.63it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 30.02it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 29.41it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 36.71it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.49it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.35it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 31.57it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.31it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.66it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.07it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.11it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.38it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 29.38it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.72it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.42it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.51it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.11it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.88it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.79it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.38it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.29it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.91it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.13it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.87it/s]
                                                            
Job chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer completed after 194.7s with status: succeeded
Stopping job with name chaiml-ir-v3-1-dpo-irv1-80635-v1-mkmlizer
Pipeline stage MKMLizer completed in 195.27s
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-v3-1-dpo-irv1-80635-v1
Waiting for inference service chaiml-ir-v3-1-dpo-irv1-80635-v1 to be ready
Inference service chaiml-ir-v3-1-dpo-irv1-80635-v1 ready after 100.56844019889832s
Pipeline stage MKMLDeployer completed in 101.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4885506629943848s
Received healthy response to inference request in 2.2966532707214355s
Received healthy response to inference request in 2.435908317565918s
Received healthy response to inference request in 2.221997022628784s
Received healthy response to inference request in 2.2980473041534424s
5 requests
0 failed requests
5th percentile: 2.2369282722473143
10th percentile: 2.251859521865845
20th percentile: 2.2817220211029055
30th percentile: 2.296932077407837
40th percentile: 2.2974896907806395
50th percentile: 2.2980473041534424
60th percentile: 2.3531917095184327
70th percentile: 2.408336114883423
80th percentile: 2.4464367866516112
90th percentile: 2.4674937248229982
95th percentile: 2.4780221939086915
99th percentile: 2.486444969177246
mean time: 2.348231315612793
Pipeline stage StressChecker completed in 13.23s
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 0.75s
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 0.70s
Shutdown handler de-registered
chaiml-ir-v3-1-dpo-irv1_80635_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 5662.50s
Shutdown handler de-registered