chaiml-ir-v3-2-dpo-irv0_97632

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-2-dpo-irv0_97632_v2

model_name: training123

model_group: ChaiML/ir-v3-2-dpo_irv0f

status: torndown

timestamp: 2025-11-17T10:01:37+00:00

num_battles: 5257

num_wins: 2700

celo_rating: 1299.13

family_friendly_score: 0.42600000000000005

family_friendly_standard_error: 0.006993196693930466

submission_type: basic

model_repo: ChaiML/ir-v3-2-dpo_irv0fullpyg

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': 0.3804642400309637, 'latency_mean': 2.62826856136322, 'latency_p50': 2.612749457359314, 'latency_p90': 2.894040584564209}, {'batch_size': 2, 'throughput': 0.5728443817535036, 'latency_mean': 3.4847969591617582, 'latency_p50': 3.4651039838790894, 'latency_p90': 3.783562111854553}, {'batch_size': 3, 'throughput': 0.7061244014332233, 'latency_mean': 4.2277490067481995, 'latency_p50': 4.222489595413208, 'latency_p90': 4.857871651649475}, {'batch_size': 4, 'throughput': 0.7978962738991017, 'latency_mean': 5.001534165143966, 'latency_p50': 5.032622337341309, 'latency_p90': 5.604792857170105}, {'batch_size': 5, 'throughput': 0.8574633034503272, 'latency_mean': 5.79976758480072, 'latency_p50': 5.784130811691284, 'latency_p90': 6.717693543434143}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-2-dpo_irv0fullpyg

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-14

win_ratio: 0.5136009130682899

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': ['User:', '</s>', '\n', '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-v3-2-dpo-irv0-97632-v2-mkmlizer
Waiting for job on chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer to finish
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: Downloaded to shared memory in 51.216s
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: Checking if ChaiML/ir-v3-2-dpo_irv0fullpyg already exists in ChaiML
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqle4b8gk, device:0
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: quantized model in 43.050s
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: Processed model ChaiML/ir-v3-2-dpo_irv0fullpyg in 94.267s
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv0-97632-v2/nvidia
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv0-97632-v2/nvidia/config.json
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv0-97632-v2/nvidia/special_tokens_map.json
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv0-97632-v2/nvidia/tokenizer_config.json
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv0-97632-v2/nvidia/tokenizer.json
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv0-97632-v2/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv0-97632-v2/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.49it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 25.51it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.81it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.65it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.96it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:08, 37.94it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.21it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.93it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.52it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.73it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.27it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:09, 32.56it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.77it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.55it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 24.37it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:12, 23.18it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:16, 17.52it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:15, 17.74it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:16, 17.15it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:13, 20.63it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:14, 18.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:11, 23.22it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:11, 22.87it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.88it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 27.41it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 27.60it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.72it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.87it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.47it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.44it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:06, 35.55it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:06, 32.91it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 39.30it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.28it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.44it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 32.47it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.10it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.45it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.42it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 31.39it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.95it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.16it/s]
Loading 0:  54%|█████▎    | 195/363 [00:07<00:06, 26.34it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:06, 26.34it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<02:16,  1.19it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:57,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:14,  2.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:58,  2.61it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:40,  3.65it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:31,  4.64it/s]
Loading 0:  61%|██████    | 221/363 [00:21<00:23,  5.93it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:19,  7.18it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:12, 10.55it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:10, 12.55it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 17.15it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 19.38it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 24.08it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.87it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:03, 29.02it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:03, 28.69it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 35.56it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.60it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.21it/s]
Loading 0:  78%|███████▊  | 282/363 [00:23<00:02, 31.11it/s]
Loading 0:  79%|███████▉  | 286/363 [00:23<00:02, 30.19it/s]
Loading 0:  80%|████████  | 291/363 [00:23<00:02, 33.27it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 31.66it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 32.50it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.62it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.97it/s]
Loading 0:  86%|████████▌ | 312/363 [00:24<00:01, 26.14it/s]
Loading 0:  88%|████████▊ | 318/363 [00:24<00:01, 31.79it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 30.49it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 33.77it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 31.73it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.54it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.06it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:01, 19.82it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.23it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.45it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.43it/s]
                                                            
Job chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer completed after 165.54s with status: succeeded
Stopping job with name chaiml-ir-v3-2-dpo-irv0-97632-v2-mkmlizer
Pipeline stage MKMLizer completed in 166.67s
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-v3-2-dpo-irv0-97632-v2
Waiting for inference service chaiml-ir-v3-2-dpo-irv0-97632-v2 to be ready
Inference service chaiml-ir-v3-2-dpo-irv0-97632-v2 ready after 140.63433694839478s
Pipeline stage MKMLDeployer completed in 141.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.54199481010437s
Received healthy response to inference request in 2.4816713333129883s
Received healthy response to inference request in 2.6219844818115234s
Received healthy response to inference request in 2.3239428997039795s
Received healthy response to inference request in 2.302140474319458s
5 requests
0 failed requests
5th percentile: 2.306500959396362
10th percentile: 2.3108614444732667
20th percentile: 2.3195824146270754
30th percentile: 2.355488586425781
40th percentile: 2.4185799598693847
50th percentile: 2.4816713333129883
60th percentile: 2.505800724029541
70th percentile: 2.5299301147460938
80th percentile: 2.5579927444458006
90th percentile: 2.589988613128662
95th percentile: 2.605986547470093
99th percentile: 2.6187848949432375
mean time: 2.454346799850464
Pipeline stage StressChecker completed in 13.69s
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 0.70s
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 0.64s
Shutdown handler de-registered
chaiml-ir-v3-2-dpo-irv0_97632_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v3-2-dpo-irv0-97632-v2-profiler
Waiting for inference service chaiml-ir-v3-2-dpo-irv0-97632-v2-profiler to be ready
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 3014.80s
Shutdown handler de-registered
chaiml-ir-v3-2-dpo-irv0_97632_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v3-2-dpo-irv0_97632_v2 status is now torndown due to DeploymentManager action