chaiml-ssnew-v7-dpo-cos_53155

developer_uid: chai_backend_admin

submission_id: chaiml-ssnew-v7-dpo-cos_53155_v1

model_name: training123

model_group: ChaiML/ssnew-v7-dpo_cosi

status: torndown

timestamp: 2025-11-23T08:51:26+00:00

num_battles: 5791

num_wins: 3086

celo_rating: 1301.91

family_friendly_score: 0.4958

family_friendly_standard_error: 0.007070818340192315

submission_type: basic

model_repo: ChaiML/ssnew-v7-dpo_cosineb025

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': 0.4532193476865306, 'latency_mean': 2.206315973997116, 'latency_p50': 2.2035367488861084, 'latency_p90': 2.410946822166443}, {'batch_size': 3, 'throughput': 0.8391533087037347, 'latency_mean': 3.5698496222496034, 'latency_p50': 3.5829617977142334, 'latency_p90': 3.8554718017578127}, {'batch_size': 5, 'throughput': 1.0123792884184826, 'latency_mean': 4.908213937282563, 'latency_p50': 4.911847114562988, 'latency_p90': 5.503848552703857}, {'batch_size': 6, 'throughput': 1.0739366721966086, 'latency_mean': 5.5695267057418825, 'latency_p50': 5.525923490524292, 'latency_p90': 6.237461972236633}, {'batch_size': 10, 'throughput': 1.1878453127077615, 'latency_mean': 8.36296904683113, 'latency_p50': 8.419545531272888, 'latency_p90': 9.411442065238953}]

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

display_name: training123

is_internal_developer: True

language_model: ChaiML/ssnew-v7-dpo_cosineb025

model_size: 24B

ranking_group: single

throughput_3p7s: 0.86

us_pacific_date: 2025-11-20

win_ratio: 0.5328958729062339

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>', 'User:', '\n'], '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
Running pipeline stage MKMLizer
Starting job with name chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer
Waiting for job on chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer to finish
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: Downloaded to shared memory in 66.732s
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: Checking if ChaiML/ssnew-v7-dpo_cosineb025 already exists in ChaiML
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuzyftw0v, device:0
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: quantized model in 46.467s
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: Processed model ChaiML/ssnew-v7-dpo_cosineb025 in 113.199s
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-cos-53155-v1/nvidia
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-cos-53155-v1/nvidia/config.json
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-cos-53155-v1/nvidia/special_tokens_map.json
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-cos-53155-v1/nvidia/tokenizer_config.json
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-cos-53155-v1/nvidia/tokenizer.json
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-cos-53155-v1/nvidia/flywheel_model.1.safetensors
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-cos-53155-v1/nvidia/flywheel_model.0.safetensors
chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.09it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.54it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.40it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.45it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 32.56it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 39.51it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:14, 22.14it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:15, 21.37it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.76it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.38it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.48it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.36it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 30.13it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 26.91it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:12, 22.67it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 28.18it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 29.25it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 25.15it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.71it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:09, 28.90it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 30.33it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 28.94it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 24.23it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:09, 27.28it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.77it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.04it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.23it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.74it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.16it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 31.75it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 30.23it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 35.70it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 22.70it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.97it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 26.44it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 28.23it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 25.69it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:15, 12.57it/s]
Loading 0:  48%|████▊     | 175/363 [00:06<00:13, 13.79it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:12, 15.40it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:09, 18.44it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:09, 19.03it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:09, 18.96it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:08, 20.59it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.26it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:07, 22.26it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:02,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.22it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.92it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.20it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.39it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.48it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:13,  9.58it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.36it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.38it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.43it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 22.21it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:04, 23.35it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 26.84it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.56it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:02, 32.59it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 22.48it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 25.13it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 26.13it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 28.08it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 27.74it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 30.78it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 29.55it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 30.06it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 27.72it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 25.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 26.12it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 17.61it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:02, 22.20it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 21.91it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 27.77it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 27.50it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:01, 27.91it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.08it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 16.61it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 22.29it/s]
Loading 0:  96%|█████████▋| 350/363 [00:27<00:00, 22.90it/s]
Loading 0:  98%|█████████▊| 355/363 [00:27<00:00, 26.74it/s]
Loading 0:  99%|█████████▉| 359/363 [00:27<00:00, 26.53it/s]
                                                            
Job chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer completed after 154.67s with status: succeeded
Stopping job with name chaiml-ssnew-v7-dpo-cos-53155-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.26s
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-ssnew-v7-dpo-cos-53155-v1
Waiting for inference service chaiml-ssnew-v7-dpo-cos-53155-v1 to be ready
Inference service chaiml-ssnew-v7-dpo-cos-53155-v1 ready after 150.55909895896912s
Pipeline stage MKMLDeployer completed in 151.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.422109603881836s
Received healthy response to inference request in 1.9127347469329834s
Received healthy response to inference request in 2.27231502532959s
Received healthy response to inference request in 1.901029109954834s
Received healthy response to inference request in 1.6951582431793213s
5 requests
0 failed requests
5th percentile: 1.7363324165344238
10th percentile: 1.7775065898895264
20th percentile: 1.8598549365997314
30th percentile: 1.903370237350464
40th percentile: 1.9080524921417237
50th percentile: 1.9127347469329834
60th percentile: 2.056566858291626
70th percentile: 2.2003989696502684
80th percentile: 2.3022739410400392
90th percentile: 2.3621917724609376
95th percentile: 2.3921506881713865
99th percentile: 2.4161178207397462
mean time: 2.040669345855713
Pipeline stage StressChecker completed in 12.35s
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 1.10s
Shutdown handler de-registered
chaiml-ssnew-v7-dpo-cos_53155_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2716.13s
Shutdown handler de-registered
chaiml-ssnew-v7-dpo-cos_53155_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ssnew-v7-dpo-cos_53155_v1 status is now torndown due to DeploymentManager action