chaiml-ir-v4-2-dpo-irv1_30892

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-2-dpo-irv1_30892_v1

model_name: training123

model_group: ChaiML/ir-v4-2-dpo_irv13

status: inactive

timestamp: 2025-11-01T21:56:22+00:00

num_battles: 5944

num_wins: 2998

celo_rating: 1294.24

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-2-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': 0.37865474783545966, 'latency_mean': 2.640800484418869, 'latency_p50': 2.6539812088012695, 'latency_p90': 2.8766098976135255}, {'batch_size': 2, 'throughput': 0.5724434116861623, 'latency_mean': 3.481738305091858, 'latency_p50': 3.4603954553604126, 'latency_p90': 3.816725921630859}, {'batch_size': 3, 'throughput': 0.7048963225266375, 'latency_mean': 4.24945298075676, 'latency_p50': 4.266130328178406, 'latency_p90': 4.60586404800415}, {'batch_size': 4, 'throughput': 0.8038933639909983, 'latency_mean': 4.967277846336365, 'latency_p50': 4.965519905090332, 'latency_p90': 5.551560163497924}, {'batch_size': 5, 'throughput': 0.8609697427577357, 'latency_mean': 5.793359055519104, 'latency_p50': 5.817753076553345, 'latency_p90': 6.5191436290740965}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-2-dpo_irv13-lr5e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-01

win_ratio: 0.5043741588156124

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-v4-2-dpo-irv1-30892-v1-mkmlizer
Waiting for job on chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer to finish
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-prm-v0-2-pair-ll_56078_v1: HTTPConnectionPool(host='chaiml-prm-v0-2-pair-ll-56078-v1-predictor.creator-studio.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: Downloaded to shared memory in 57.680s
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: Checking if ChaiML/ir-v4-2-dpo_irv13-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeyjv2o3d, device:0
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: quantized model in 42.966s
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: Processed model ChaiML/ir-v4-2-dpo_irv13-lr5e6b01-cosine in 100.647s
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv1-30892-v1/nvidia
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv1-30892-v1/nvidia/config.json
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv1-30892-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv1-30892-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv1-30892-v1/nvidia/tokenizer.json
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv1-30892-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv1-30892-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.79it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.32it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.08it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.47it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.52it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.71it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.67it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.75it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 31.05it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.38it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.34it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.58it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.96it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.78it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.51it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.81it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.34it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 27.01it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.28it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.48it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.31it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.54it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.01it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.82it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.89it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.76it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.83it/s]
Loading 0:  37%|███▋      | 136/363 [00:04<00:08, 26.47it/s]
Loading 0:  39%|███▊      | 140/363 [00:04<00:09, 24.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 24.80it/s]
Loading 0:  41%|████▏     | 150/363 [00:05<00:08, 25.00it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:11, 18.46it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:10, 20.13it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:10, 20.34it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 27.09it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:08, 23.86it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.14it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:08, 22.34it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.98it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:07, 25.10it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.83it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 22.68it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.43it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.81it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.09it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.30it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:12, 10.62it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:10, 12.48it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 17.00it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 19.20it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.85it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.82it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.08it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.78it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 35.50it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.36it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.88it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.78it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.15it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.41it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 29.25it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 28.91it/s]
Loading 0:  83%|████████▎ | 303/363 [00:23<00:01, 30.51it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:02, 21.32it/s]
Loading 0:  85%|████████▌ | 310/363 [00:23<00:02, 22.81it/s]
Loading 0:  86%|████████▌ | 313/363 [00:23<00:02, 23.41it/s]
Loading 0:  88%|████████▊ | 318/363 [00:24<00:01, 28.26it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 27.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 31.73it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 30.56it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 31.84it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.67it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:01, 19.78it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.11it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.46it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.34it/s]
                                                            
Job chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer completed after 176.11s with status: succeeded
Stopping job with name chaiml-ir-v4-2-dpo-irv1-30892-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.62s
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-v4-2-dpo-irv1-30892-v1
Waiting for inference service chaiml-ir-v4-2-dpo-irv1-30892-v1 to be ready
Inference service chaiml-ir-v4-2-dpo-irv1-30892-v1 ready after 211.15092158317566s
Pipeline stage MKMLDeployer completed in 211.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0377085208892822s
Received healthy response to inference request in 2.421679973602295s
Received healthy response to inference request in 2.7000486850738525s
Received healthy response to inference request in 2.2647056579589844s
Received healthy response to inference request in 2.6324565410614014s
5 requests
0 failed requests
5th percentile: 2.2961005210876464
10th percentile: 2.3274953842163084
20th percentile: 2.390285110473633
30th percentile: 2.463835287094116
40th percentile: 2.5481459140777587
50th percentile: 2.6324565410614014
60th percentile: 2.659493398666382
70th percentile: 2.686530256271362
80th percentile: 2.7675806522369384
90th percentile: 2.9026445865631105
95th percentile: 2.9701765537261964
99th percentile: 3.024202127456665
mean time: 2.611319875717163
Pipeline stage StressChecker completed in 14.65s
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 0.61s
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 0.63s
Shutdown handler de-registered
chaiml-ir-v4-2-dpo-irv1_30892_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 5179.18s
Shutdown handler de-registered