chaiml-ir-v3-1-dpo-irv0_42950

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-1-dpo-irv0_42950_v1

model_name: training123

model_group: ChaiML/ir-v3-1-dpo_irv0f

status: inactive

timestamp: 2025-10-29T06:34:12+00:00

num_battles: 6375

num_wins: 3309

celo_rating: 1292.36

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v3-1-dpo_irv0fullpyg-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': 0.37970009841400193, 'latency_mean': 2.633562239408493, 'latency_p50': 2.6424450874328613, 'latency_p90': 2.882118344306946}, {'batch_size': 2, 'throughput': 0.5675413607364262, 'latency_mean': 3.516150051355362, 'latency_p50': 3.519120454788208, 'latency_p90': 3.7913152933120724}, {'batch_size': 3, 'throughput': 0.7035783546153226, 'latency_mean': 4.251811219453812, 'latency_p50': 4.258603930473328, 'latency_p90': 4.582901906967163}, {'batch_size': 4, 'throughput': 0.8048501119929931, 'latency_mean': 4.957531728744507, 'latency_p50': 4.912980914115906, 'latency_p90': 5.484233832359314}, {'batch_size': 5, 'throughput': 0.8618342679262918, 'latency_mean': 5.7816220414638515, 'latency_p50': 5.794553756713867, 'latency_p90': 6.5835750818252565}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

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

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-10-28

win_ratio: 0.5190588235294118

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': ['You:', '</s>', '\n', '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-v3-1-dpo-irv0-42950-v1-mkmlizer
Waiting for job on chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer to finish
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: Downloaded to shared memory in 73.942s
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: Checking if ChaiML/ir-v3-1-dpo_irv0fullpyg-lr5e6b01 already exists in ChaiML
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphi47l3wk, device:0
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: quantized model in 42.024s
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: Processed model ChaiML/ir-v3-1-dpo_irv0fullpyg-lr5e6b01 in 115.966s
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-42950-v1/nvidia
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-42950-v1/nvidia/config.json
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-42950-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-42950-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-42950-v1/nvidia/tokenizer.json
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-42950-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-1-dpo-irv0-42950-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.83it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 40.32it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 39.13it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.15it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.53it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 27.80it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.73it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.81it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.77it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.44it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.94it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.07it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.34it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.93it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.14it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.65it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.07it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.37it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.83it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.99it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.86it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.23it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.13it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 31.97it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.90it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.39it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.60it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.83it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.66it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.22it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 26.86it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.17it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.32it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.32it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.39it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.32it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.18it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 29.82it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.24it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.50it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:53,  2.80it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:33,  4.37it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.71it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.03it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.68it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.42it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.51it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:06, 19.50it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 21.29it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 25.62it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.47it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.64it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 24.29it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.29it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.36it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.01it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.35it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.00it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 30.09it/s]
Loading 0:  83%|████████▎ | 303/363 [00:22<00:01, 32.03it/s]
Loading 0:  85%|████████▍ | 307/363 [00:22<00:02, 21.27it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 20.59it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 28.21it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 28.34it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 32.03it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 30.99it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.20it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.36it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.02it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.64it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.04it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.52it/s]
                                                            
Job chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer completed after 184.41s with status: succeeded
Stopping job with name chaiml-ir-v3-1-dpo-irv0-42950-v1-mkmlizer
Pipeline stage MKMLizer completed in 184.95s
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-irv0-42950-v1
Waiting for inference service chaiml-ir-v3-1-dpo-irv0-42950-v1 to be ready
Inference service chaiml-ir-v3-1-dpo-irv0-42950-v1 ready after 100.27957224845886s
Pipeline stage MKMLDeployer completed in 100.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4771056175231934s
Received healthy response to inference request in 2.13753604888916s
Received healthy response to inference request in 2.987380266189575s
Received healthy response to inference request in 2.234335422515869s
Received healthy response to inference request in 2.1322102546691895s
5 requests
0 failed requests
5th percentile: 2.1332754135131835
10th percentile: 2.1343405723571776
20th percentile: 2.136470890045166
30th percentile: 2.1568959236145018
40th percentile: 2.1956156730651855
50th percentile: 2.234335422515869
60th percentile: 2.331443500518799
70th percentile: 2.4285515785217284
80th percentile: 2.57916054725647
90th percentile: 2.7832704067230223
95th percentile: 2.8853253364562987
99th percentile: 2.9669692802429197
mean time: 2.3937135219573973
Pipeline stage StressChecker completed in 13.61s
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 0.69s
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-v3-1-dpo-irv0_42950_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 5691.57s
Shutdown handler de-registered