chaiml-ssnew-v7-dpo-b025

developer_uid: chai_backend_admin

submission_id: chaiml-ssnew-v7-dpo-b025_v1

model_name: training123

model_group: ChaiML/ssnew-v7-dpo_b025

status: torndown

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

num_battles: 6184

num_wins: 3254

celo_rating: 1294.41

family_friendly_score: 0.5232

family_friendly_standard_error: 0.007063451847361883

submission_type: basic

model_repo: ChaiML/ssnew-v7-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': 0.34582314868724034, 'latency_mean': 2.891530694961548, 'latency_p50': 2.313215494155884, 'latency_p90': 5.1665506839752195}, {'batch_size': 3, 'throughput': 0.8306073669034504, 'latency_mean': 3.6046247613430022, 'latency_p50': 3.563674569129944, 'latency_p90': 3.9218748331069944}, {'batch_size': 5, 'throughput': 0.9956845496977179, 'latency_mean': 4.994279128313065, 'latency_p50': 4.994015336036682, 'latency_p90': 5.5573179721832275}, {'batch_size': 6, 'throughput': 1.0493137528249783, 'latency_mean': 5.674581335783005, 'latency_p50': 5.724060893058777, 'latency_p90': 6.278182649612426}, {'batch_size': 10, 'throughput': 1.1538016330105383, 'latency_mean': 8.597783848047257, 'latency_p50': 8.63788616657257, 'latency_p90': 9.551232528686523}]

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

display_name: training123

is_internal_developer: True

language_model: ChaiML/ssnew-v7-dpo_b025

model_size: 24B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2025-11-20

win_ratio: 0.5261966364812419

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>', 'User:', '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
Running pipeline stage MKMLizer
Starting job with name chaiml-ssnew-v7-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-ssnew-v7-dpo-b025-v1-mkmlizer to finish
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: Downloaded to shared memory in 67.439s
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: Checking if ChaiML/ssnew-v7-dpo_b025 already exists in ChaiML
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzqhls9zx, device:0
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: quantized model in 45.982s
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: Processed model ChaiML/ssnew-v7-dpo_b025 in 113.421s
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-b025-v1/nvidia
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-b025-v1/nvidia/config.json
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-b025-v1/nvidia/special_tokens_map.json
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-b025-v1/nvidia/tokenizer_config.json
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-b025-v1/nvidia/tokenizer.json
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-b025-v1/nvidia/flywheel_model.1.safetensors
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-dpo-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-ssnew-v7-dpo-b025-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.13it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.97it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.71it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.65it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 33.10it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 40.01it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.80it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.47it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.16it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.52it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 31.44it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.44it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.66it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.75it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 22.02it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.66it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.89it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 25.58it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.12it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:09, 29.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 30.75it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 29.48it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 24.80it/s]
Loading 0:  30%|███       | 110/363 [00:04<00:15, 16.50it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:16, 15.01it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:10, 22.30it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:11, 21.81it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 27.15it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 26.86it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.81it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.63it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.37it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 22.52it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 25.06it/s]
Loading 0:  44%|████▍     | 161/363 [00:06<00:07, 26.28it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 28.22it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 27.72it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.56it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.08it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.59it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.83it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.49it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 25.28it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.87it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.87it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:55,  1.09s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:25,  1.10it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:27,  1.77it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:07,  2.25it/s]
Loading 0:  59%|█████▉    | 214/363 [00:21<00:50,  2.98it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.26it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.44it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.57it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:13,  9.70it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.51it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.66it/s]
Loading 0:  66%|██████▋   | 241/363 [00:22<00:06, 17.88it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 22.05it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:04, 23.37it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 26.33it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.62it/s]
Loading 0:  73%|███████▎  | 266/363 [00:23<00:02, 32.81it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 19.95it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 22.73it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 24.44it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.83it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.98it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 30.25it/s]
Loading 0:  81%|████████▏ | 295/363 [00:24<00:02, 29.35it/s]
Loading 0:  82%|████████▏ | 299/363 [00:24<00:02, 30.00it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 28.14it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 25.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 26.09it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:01, 26.81it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 30.01it/s]
Loading 0:  89%|████████▊ | 322/363 [00:25<00:01, 28.93it/s]
Loading 0:  90%|█████████ | 327/363 [00:25<00:01, 31.66it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 29.96it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 30.25it/s]
Loading 0:  93%|█████████▎| 339/363 [00:26<00:00, 30.26it/s]
Loading 0:  94%|█████████▍| 343/363 [00:26<00:01, 18.31it/s]
Loading 0:  96%|█████████▌| 348/363 [00:27<00:00, 19.99it/s]
Loading 0:  98%|█████████▊| 355/363 [00:27<00:00, 26.70it/s]
Loading 0:  99%|█████████▉| 359/363 [00:27<00:00, 26.24it/s]
                                                            
Job chaiml-ssnew-v7-dpo-b025-v1-mkmlizer completed after 155.0s with status: succeeded
Stopping job with name chaiml-ssnew-v7-dpo-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.73s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ssnew-v7-dpo-b025-v1
Waiting for inference service chaiml-ssnew-v7-dpo-b025-v1 to be ready
Inference service chaiml-ssnew-v7-dpo-b025-v1 ready after 140.54337787628174s
Pipeline stage MKMLDeployer completed in 141.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3519320487976074s
Received healthy response to inference request in 2.046916961669922s
Received healthy response to inference request in 2.102731466293335s
Received healthy response to inference request in 2.0509698390960693s
Received healthy response to inference request in 1.751420021057129s
5 requests
0 failed requests
5th percentile: 1.8105194091796875
10th percentile: 1.869618797302246
20th percentile: 1.9878175735473633
30th percentile: 2.0477275371551515
40th percentile: 2.0493486881256104
50th percentile: 2.0509698390960693
60th percentile: 2.0716744899749755
70th percentile: 2.0923791408538817
80th percentile: 2.1525715827941894
90th percentile: 2.2522518157958986
95th percentile: 2.302091932296753
99th percentile: 2.3419640254974365
mean time: 2.0607940673828127
Pipeline stage StressChecker completed in 12.01s
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 0.66s
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 0.72s
Shutdown handler de-registered
chaiml-ssnew-v7-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 2921.98s
Shutdown handler de-registered
chaiml-ssnew-v7-dpo-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ssnew-v7-dpo-b025_v1 status is now torndown due to DeploymentManager action