chaiml-ssnew-v7-1c-dpo-b025

developer_uid: chai_backend_admin

submission_id: chaiml-ssnew-v7-1c-dpo-b025_v1

model_name: training123

model_group: ChaiML/ssnew-v7-1c-dpo_b

status: torndown

timestamp: 2025-11-25T00:21:13+00:00

num_battles: 6507

num_wins: 3462

celo_rating: 1305.21

family_friendly_score: 0.5204

family_friendly_standard_error: 0.007065179969399223

submission_type: basic

model_repo: ChaiML/ssnew-v7-1c-dpo_b025

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': 0.37659139313308493, 'latency_mean': 2.655275194644928, 'latency_p50': 2.6478400230407715, 'latency_p90': 2.9199182033538817}, {'batch_size': 2, 'throughput': 0.566001356522173, 'latency_mean': 3.530978615283966, 'latency_p50': 3.538973569869995, 'latency_p90': 3.886064839363098}, {'batch_size': 3, 'throughput': 0.6942527317425653, 'latency_mean': 4.313735436201096, 'latency_p50': 4.3073039054870605, 'latency_p90': 4.764531922340393}, {'batch_size': 4, 'throughput': 0.7841340754884293, 'latency_mean': 5.086877099275589, 'latency_p50': 5.057571768760681, 'latency_p90': 5.7756720066070555}, {'batch_size': 5, 'throughput': 0.8411799929643823, 'latency_mean': 5.9297484159469604, 'latency_p50': 5.889163255691528, 'latency_p90': 6.855033922195434}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ssnew-v7-1c-dpo_b025

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-21

win_ratio: 0.5320424158598432

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', 'You:', 'User:', '</s>'], '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-v7-1c-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer to finish
Stopping job with name chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer to finish
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: Downloaded to shared memory in 109.388s
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: Checking if ChaiML/ssnew-v7-1c-dpo_b025 already exists in ChaiML
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp77u2bvrj, device:0
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: quantized model in 41.698s
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: Processed model ChaiML/ssnew-v7-1c-dpo_b025 in 151.086s
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ssnew-v7-1c-dpo-b025-v1/nvidia
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1c-dpo-b025-v1/nvidia/tokenizer.json
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-1c-dpo-b025-v1/nvidia/flywheel_model.1.safetensors
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-1c-dpo-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.82it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.66it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.33it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.94it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.50it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.30it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.53it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.98it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 34.28it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 34.90it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 35.66it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:07, 38.65it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:09, 29.39it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:09, 30.62it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:10, 27.55it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:08, 33.18it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:08, 32.01it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:08, 31.02it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.54it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.74it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.50it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 31.04it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.80it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.74it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 32.09it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.79it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 33.63it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 37.07it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.48it/s]
Loading 0:  40%|████      | 146/363 [00:04<00:06, 32.08it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 28.62it/s]
Loading 0:  42%|████▏     | 153/363 [00:04<00:08, 23.92it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.67it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.75it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.48it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.27it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 34.17it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 31.37it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 30.33it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.79it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:18,  1.17it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:58,  1.35it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:15,  2.05it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:58,  2.59it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:44,  3.35it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.74it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:21,  6.51it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.15it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:13, 10.06it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 15.78it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 17.97it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 22.36it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.73it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.15it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.35it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.33it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 26.60it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.80it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 32.13it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 31.18it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 34.22it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.41it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.81it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 29.86it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.84it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.72it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.66it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 35.30it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.81it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.97it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 34.65it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 21.26it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.85it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 30.70it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 30.07it/s]
                                                            
Job chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer completed after 205.88s with status: succeeded
Stopping job with name chaiml-ssnew-v7-1c-dpo-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 227.53s
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-v7-1c-dpo-b025-v1
Waiting for inference service chaiml-ssnew-v7-1c-dpo-b025-v1 to be ready
Inference service chaiml-ssnew-v7-1c-dpo-b025-v1 ready after 150.71676182746887s
Pipeline stage MKMLDeployer completed in 151.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4735939502716064s
Received healthy response to inference request in 2.676008701324463s
Received healthy response to inference request in 2.103323221206665s
Received healthy response to inference request in 2.0777523517608643s
Received healthy response to inference request in 2.61232328414917s
5 requests
0 failed requests
5th percentile: 2.0828665256500245
10th percentile: 2.0879806995391847
20th percentile: 2.098209047317505
30th percentile: 2.1773773670196532
40th percentile: 2.32548565864563
50th percentile: 2.4735939502716064
60th percentile: 2.5290856838226317
70th percentile: 2.5845774173736573
80th percentile: 2.6250603675842283
90th percentile: 2.6505345344543456
95th percentile: 2.6632716178894045
99th percentile: 2.673461284637451
mean time: 2.388600301742554
Pipeline stage StressChecker completed in 13.30s
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 0.78s
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 0.66s
Shutdown handler de-registered
chaiml-ssnew-v7-1c-dpo-b025_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 2971.35s
Shutdown handler de-registered
chaiml-ssnew-v7-1c-dpo-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ssnew-v7-1c-dpo-b025_v1 status is now torndown due to DeploymentManager action