chaiml-ssnew-v7-1a-dpo

developer_uid: chai_backend_admin

submission_id: chaiml-ssnew-v7-1a-dpo_v1

model_name: training123

model_group: ChaiML/ssnew-v7-1a-dpo

status: torndown

timestamp: 2025-11-23T23:21:27+00:00

num_battles: 6007

num_wins: 3122

celo_rating: 1303.83

family_friendly_score: 0.5584

family_friendly_standard_error: 0.007022669577874214

submission_type: basic

model_repo: ChaiML/ssnew-v7-1a-dpo

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': 0.35260203659700573, 'latency_mean': 2.8359367072582247, 'latency_p50': 2.2961169481277466, 'latency_p90': 4.50282392501831}, {'batch_size': 2, 'throughput': 0.6715542763944887, 'latency_mean': 2.966629775762558, 'latency_p50': 2.990616202354431, 'latency_p90': 3.2927441596984863}, {'batch_size': 3, 'throughput': 0.8224959743024601, 'latency_mean': 3.6379914152622224, 'latency_p50': 3.6498360633850098, 'latency_p90': 3.996606421470642}, {'batch_size': 4, 'throughput': 0.9144911335151159, 'latency_mean': 4.3588390946388245, 'latency_p50': 4.36420214176178, 'latency_p90': 4.858424663543701}, {'batch_size': 5, 'throughput': 0.9781553478125272, 'latency_mean': 5.082133169174194, 'latency_p50': 5.051427483558655, 'latency_p90': 5.7102761507034305}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ssnew-v7-1a-dpo

model_size: 24B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2025-11-20

win_ratio: 0.5197269851839521

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:', '\n', '</s>', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '####\n{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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage MKMLizer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Starting job with name chaiml-ssnew-v7-1a-dpo-v1-mkmlizer
Waiting for job on chaiml-ssnew-v7-1a-dpo-v1-mkmlizer to finish
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: Downloaded to shared memory in 71.213s
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: Checking if ChaiML/ssnew-v7-1a-dpo already exists in ChaiML
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_us3_gtu, device:0
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: quantized model in 47.244s
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: Processed model ChaiML/ssnew-v7-1a-dpo in 118.458s
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-v1/nvidia/flywheel_model.1.safetensors
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-ssnew-v7-1a-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.17it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.67it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 34.86it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.02it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 32.34it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 38.79it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.51it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.60it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.12it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 28.16it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 30.86it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.78it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.58it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 26.71it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:12, 22.41it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.76it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.57it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 24.45it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:11, 23.74it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:12, 22.48it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.74it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 24.83it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:18, 14.16it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:19, 12.85it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:17, 14.33it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:11, 20.91it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:11, 20.54it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:09, 25.66it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 25.24it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.32it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.91it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.63it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:08, 24.97it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 20.20it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.69it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.60it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.26it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.56it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.14it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:06, 28.07it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 28.69it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 27.07it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.66it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 25.30it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.32it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 25.32it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:28,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.92it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.16it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:26,  5.32it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.42it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.47it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.19it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.15it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.07it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.72it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 22.54it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 26.08it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.60it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:03, 31.33it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 21.56it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 24.16it/s]
Loading 0:  77%|███████▋  | 278/363 [00:25<00:03, 25.27it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:02, 27.12it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 26.45it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.11it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.35it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.93it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.53it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.64it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.66it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 25.29it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.55it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.53it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.75it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 29.29it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.68it/s]
Loading 0:  93%|█████████▎| 339/363 [00:27<00:00, 30.16it/s]
Loading 0:  94%|█████████▍| 343/363 [00:27<00:01, 18.15it/s]
Loading 0:  96%|█████████▌| 348/363 [00:27<00:00, 19.47it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 25.97it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 25.69it/s]
                                                            
Job chaiml-ssnew-v7-1a-dpo-v1-mkmlizer completed after 160.05s with status: succeeded
Stopping job with name chaiml-ssnew-v7-1a-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 161.11s
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-ssnew-v7-1a-dpo-v1
Waiting for inference service chaiml-ssnew-v7-1a-dpo-v1 to be ready
Inference service chaiml-ssnew-v7-1a-dpo-v1 ready after 150.82255792617798s
Pipeline stage MKMLDeployer completed in 151.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1312637329101562s
Received healthy response to inference request in 1.9611074924468994s
Received healthy response to inference request in 1.7350594997406006s
Received healthy response to inference request in 1.8617966175079346s
Received healthy response to inference request in 1.6856064796447754s
5 requests
0 failed requests
5th percentile: 1.6954970836639405
10th percentile: 1.7053876876831056
20th percentile: 1.7251688957214355
30th percentile: 1.7604069232940673
40th percentile: 1.811101770401001
50th percentile: 1.8617966175079346
60th percentile: 1.9015209674835205
70th percentile: 1.9412453174591064
80th percentile: 1.9951387405395509
90th percentile: 2.0632012367248533
95th percentile: 2.097232484817505
99th percentile: 2.124457483291626
mean time: 1.8749667644500732
Pipeline stage StressChecker completed in 10.55s
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 0.64s
Shutdown handler de-registered
chaiml-ssnew-v7-1a-dpo_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 0.09s
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-ssnew-v7-1a-dpo-v1-profiler
Waiting for inference service chaiml-ssnew-v7-1a-dpo-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3003.11s
Shutdown handler de-registered
chaiml-ssnew-v7-1a-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ssnew-v7-1a-dpo_v1 status is now torndown due to DeploymentManager action