chaiml-ir-v3-2-dpo-irv1_92454

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-2-dpo-irv1_92454_v1

model_name: training123

model_group: ChaiML/ir-v3-2-dpo_irv13

status: torndown

timestamp: 2025-11-17T22:21:30+00:00

num_battles: 6018

num_wins: 3188

celo_rating: 1309.5

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v3-2-dpo_irv13-cosine-lr15

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': 0.2704662163164172, 'latency_mean': 3.6972225630283355, 'latency_p50': 2.8786780834198, 'latency_p90': 6.236266088485718}, {'batch_size': 2, 'throughput': 0.5455678753177488, 'latency_mean': 3.659510484933853, 'latency_p50': 3.6527379751205444, 'latency_p90': 3.9441408634185793}, {'batch_size': 3, 'throughput': 0.6659809201118072, 'latency_mean': 4.494366241693497, 'latency_p50': 4.486314058303833, 'latency_p90': 5.061958312988281}, {'batch_size': 4, 'throughput': 0.7644347222264382, 'latency_mean': 5.220679101943969, 'latency_p50': 5.209006309509277, 'latency_p90': 5.985614871978759}, {'batch_size': 5, 'throughput': 0.8241144763019411, 'latency_mean': 6.038246134519577, 'latency_p50': 6.08678674697876, 'latency_p90': 6.858133339881897}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-2-dpo_irv13-cosine-lr15

model_size: 24B

ranking_group: single

throughput_3p7s: 0.55

us_pacific_date: 2025-11-14

win_ratio: 0.5297441010302426

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>', 'You:', 'User:'], '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-irv1-92454-v1-mkmlizer
Waiting for job on chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer to finish
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: Downloaded to shared memory in 68.223s
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: Checking if ChaiML/ir-v3-2-dpo_irv13-cosine-lr15 already exists in ChaiML
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjocl27kc, device:0
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: quantized model in 41.526s
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: Processed model ChaiML/ir-v3-2-dpo_irv13-cosine-lr15 in 109.749s
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv1-92454-v1/nvidia
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv1-92454-v1/nvidia/config.json
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv1-92454-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv1-92454-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv1-92454-v1/nvidia/tokenizer.json
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv1-92454-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv1-92454-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.18it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 37.85it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.94it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.93it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.15it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 29.84it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 26.81it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.14it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.94it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.68it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.94it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.13it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.88it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.69it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.54it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.10it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.71it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 28.26it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 33.51it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.99it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 31.55it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 32.01it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 33.01it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 34.15it/s]
Loading 0:  36%|███▌      | 130/363 [00:04<00:06, 34.53it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:06, 35.08it/s]
Loading 0:  38%|███▊      | 139/363 [00:04<00:06, 35.24it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 35.98it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.71it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.95it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 26.16it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.50it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 32.54it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.74it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.98it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 34.67it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 32.41it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 31.48it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 27.61it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.44it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.84it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:21,  6.68it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.43it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:12, 10.35it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.16it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 18.20it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 22.54it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 23.90it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:03, 28.19it/s]
Loading 0:  71%|███████▏  | 259/363 [00:20<00:03, 28.13it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.25it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.71it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.36it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 31.49it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 30.61it/s]
Loading 0:  80%|████████  | 291/363 [00:21<00:02, 33.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.35it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.34it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 29.21it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:02, 25.32it/s]
Loading 0:  86%|████████▌ | 311/363 [00:22<00:02, 22.28it/s]
Loading 0:  88%|████████▊ | 318/363 [00:22<00:01, 29.49it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 28.93it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 32.62it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.31it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.45it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.46it/s]
Loading 0:  94%|█████████▍| 343/363 [00:23<00:00, 20.45it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.31it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 30.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.27it/s]
                                                            
Job chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer completed after 157.75s with status: succeeded
Stopping job with name chaiml-ir-v3-2-dpo-irv1-92454-v1-mkmlizer
Pipeline stage MKMLizer completed in 158.29s
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-irv1-92454-v1
Waiting for inference service chaiml-ir-v3-2-dpo-irv1-92454-v1 to be ready
Inference service chaiml-ir-v3-2-dpo-irv1-92454-v1 ready after 151.37072587013245s
Pipeline stage MKMLDeployer completed in 151.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.926873207092285s
Received healthy response to inference request in 2.1953823566436768s
Received healthy response to inference request in 2.4956281185150146s
Received healthy response to inference request in 2.1641619205474854s
Received healthy response to inference request in 3.075345754623413s
5 requests
0 failed requests
5th percentile: 2.1704060077667235
10th percentile: 2.1766500949859617
20th percentile: 2.1891382694244386
30th percentile: 2.2554315090179444
40th percentile: 2.3755298137664793
50th percentile: 2.4956281185150146
60th percentile: 2.6681261539459227
70th percentile: 2.840624189376831
80th percentile: 2.956567716598511
90th percentile: 3.015956735610962
95th percentile: 3.0456512451171873
99th percentile: 3.069406852722168
mean time: 2.571478271484375
Pipeline stage StressChecker completed in 13.98s
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 0.63s
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 0.51s
Shutdown handler de-registered
chaiml-ir-v3-2-dpo-irv1_92454_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 6043.51s
Shutdown handler de-registered
chaiml-ir-v3-2-dpo-irv1_92454_v1 status is now torndown due to DeploymentManager action