chaiml-ir-v4-2-dpo-irv0_35646

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-2-dpo-irv0_35646_v1

model_name: training123

model_group: ChaiML/ir-v4-2-dpo_irv0-

status: inactive

timestamp: 2025-11-01T22:32:25+00:00

num_battles: 5644

num_wins: 2914

celo_rating: 1296.79

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-2-dpo_irv0-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': 0.3778856395606993, 'latency_mean': 2.646195763349533, 'latency_p50': 2.6493043899536133, 'latency_p90': 2.8968581199645995}, {'batch_size': 2, 'throughput': 0.5707876279303785, 'latency_mean': 3.497478233575821, 'latency_p50': 3.490586519241333, 'latency_p90': 3.8110165357589723}, {'batch_size': 3, 'throughput': 0.7065205625603679, 'latency_mean': 4.23800763964653, 'latency_p50': 4.22452437877655, 'latency_p90': 4.582818341255188}, {'batch_size': 4, 'throughput': 0.8071689163443749, 'latency_mean': 4.9375077497959134, 'latency_p50': 4.923322319984436, 'latency_p90': 5.615189051628112}, {'batch_size': 5, 'throughput': 0.8685885749084901, 'latency_mean': 5.733943871259689, 'latency_p50': 5.721996903419495, 'latency_p90': 6.5092894554138185}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-2-dpo_irv0-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-01

win_ratio: 0.5163004961020553

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

Connection pool is full, discarding connection: %s. Connection pool size: %s
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-v4-2-dpo-irv0-35646-v1-mkmlizer
Waiting for job on chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer to finish
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: Downloaded to shared memory in 65.809s
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: Checking if ChaiML/ir-v4-2-dpo_irv0-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnwgt3qpz, device:0
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: quantized model in 41.075s
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: Processed model ChaiML/ir-v4-2-dpo_irv0-lr5e6b01 in 106.884s
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-35646-v1/nvidia
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-35646-v1/nvidia/config.json
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-35646-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-35646-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-35646-v1/nvidia/tokenizer.json
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-35646-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-35646-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.30it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.71it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 40.62it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:09, 35.79it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 45.68it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:10, 29.64it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:11, 27.09it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 34.61it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 34.38it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 35.11it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 35.84it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:07, 39.03it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:10, 29.07it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:09, 29.81it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:10, 27.38it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 33.13it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:08, 32.06it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:08, 31.02it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:07, 34.35it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 33.08it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.42it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.95it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.65it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 32.61it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 34.07it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 34.53it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:06, 35.72it/s]
Loading 0:  38%|███▊      | 139/363 [00:04<00:06, 35.57it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 36.42it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 41.21it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.40it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:08, 25.61it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.00it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 32.20it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.37it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.57it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 34.39it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 31.12it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 30.15it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 27.29it/s]
Loading 0:  55%|█████▌    | 201/363 [00:18<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.13it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:52,  2.85it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:32,  4.44it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:24,  5.76it/s]
Loading 0:  62%|██████▏   | 226/363 [00:19<00:19,  7.14it/s]
Loading 0:  63%|██████▎   | 230/363 [00:19<00:15,  8.80it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.64it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.89it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 20.01it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 21.93it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 26.43it/s]
Loading 0:  71%|███████▏  | 259/363 [00:20<00:03, 27.47it/s]
Loading 0:  73%|███████▎  | 266/363 [00:20<00:02, 34.87it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 26.92it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 25.06it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 32.28it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 31.42it/s]
Loading 0:  80%|████████  | 291/363 [00:21<00:02, 34.72it/s]
Loading 0:  81%|████████▏ | 295/363 [00:21<00:02, 33.11it/s]
Loading 0:  82%|████████▏ | 299/363 [00:21<00:01, 34.05it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 31.18it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 30.19it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 27.25it/s]
Loading 0:  88%|████████▊ | 318/363 [00:22<00:01, 33.10it/s]
Loading 0:  89%|████████▊ | 322/363 [00:22<00:01, 32.10it/s]
Loading 0:  90%|█████████ | 327/363 [00:22<00:01, 35.53it/s]
Loading 0:  91%|█████████ | 331/363 [00:22<00:00, 33.40it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 34.18it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 34.84it/s]
Loading 0:  94%|█████████▍| 343/363 [00:23<00:00, 20.83it/s]
Loading 0:  96%|█████████▌| 348/363 [00:23<00:00, 22.43it/s]
Loading 0:  98%|█████████▊| 355/363 [00:23<00:00, 30.14it/s]
Loading 0:  99%|█████████▉| 359/363 [00:23<00:00, 29.80it/s]
                                                            
Job chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer completed after 155.19s with status: succeeded
Stopping job with name chaiml-ir-v4-2-dpo-irv0-35646-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.95s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v4-2-dpo-irv0-35646-v1
Waiting for inference service chaiml-ir-v4-2-dpo-irv0-35646-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-v4-2-dpo-irv0-35646-v1 ready after 130.6218285560608s
Pipeline stage MKMLDeployer completed in 131.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.493467092514038s
Received healthy response to inference request in 2.2061448097229004s
Received healthy response to inference request in 2.2142064571380615s
Received healthy response to inference request in 2.422797441482544s
Received healthy response to inference request in 2.2865891456604004s
5 requests
0 failed requests
5th percentile: 2.2077571392059325
10th percentile: 2.2093694686889647
20th percentile: 2.2125941276550294
30th percentile: 2.2286829948425293
40th percentile: 2.257636070251465
50th percentile: 2.2865891456604004
60th percentile: 2.3410724639892577
70th percentile: 2.395555782318115
80th percentile: 2.4369313716888428
90th percentile: 2.4651992321014404
95th percentile: 2.4793331623077393
99th percentile: 2.4906403064727782
mean time: 2.324640989303589
Pipeline stage StressChecker completed in 12.87s
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 0.64s
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 0.58s
Shutdown handler de-registered
chaiml-ir-v4-2-dpo-irv0_35646_v1 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 0.11s
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-v4-2-dpo-irv0-35646-v1-profiler
Waiting for inference service chaiml-ir-v4-2-dpo-irv0-35646-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5686.72s
Shutdown handler de-registered