chaiml-ca18-v1-8-dpo-b025

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-8-dpo-b025_v1

model_name: training123

model_group: ChaiML/ca18-v1-8-dpo_b02

status: torndown

timestamp: 2025-11-20T21:41:17+00:00

num_battles: 6221

num_wins: 3252

celo_rating: 1301.41

family_friendly_score: 0.5064

family_friendly_standard_error: 0.007070488526261817

submission_type: basic

model_repo: ChaiML/ca18-v1-8-dpo_b025

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6966542306843605, 'latency_mean': 1.4353130555152893, 'latency_p50': 1.428025245666504, 'latency_p90': 1.5721786260604858}, {'batch_size': 3, 'throughput': 1.3077829320493437, 'latency_mean': 2.287064747810364, 'latency_p50': 2.2912691831588745, 'latency_p90': 2.621155786514282}, {'batch_size': 5, 'throughput': 1.5987436021062091, 'latency_mean': 3.1080182898044586, 'latency_p50': 3.104647397994995, 'latency_p90': 3.5761511087417603}, {'batch_size': 6, 'throughput': 1.7045583715486667, 'latency_mean': 3.502167131900787, 'latency_p50': 3.5348525047302246, 'latency_p90': 3.9646254062652586}, {'batch_size': 8, 'throughput': 1.8339869535540503, 'latency_mean': 4.343294287919998, 'latency_p50': 4.339271426200867, 'latency_p90': 4.942861318588257}, {'batch_size': 10, 'throughput': 1.9067927990965803, 'latency_mean': 5.2085820174217226, 'latency_p50': 5.210731506347656, 'latency_p90': 5.914727735519409}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-8-dpo_b025

model_size: 13B

ranking_group: single

throughput_3p7s: 1.75

us_pacific_date: 2025-11-17

win_ratio: 0.522745539302363

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:', '\n', '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': '{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-ca18-v1-8-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer to finish
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: Downloaded to shared memory in 49.299s
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: Checking if ChaiML/ca18-v1-8-dpo_b025 already exists in ChaiML
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp07nuyp2z, device:0
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: quantized model in 26.687s
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: Processed model ChaiML/ca18-v1-8-dpo_b025 in 75.987s
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-b025-v1/nvidia
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-b025-v1/nvidia/config.json
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-b025-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-b025-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-b025-v1/nvidia/tokenizer.json
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.99it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 47.45it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 52.10it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 54.84it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 55.53it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 56.12it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 61.77it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 45.52it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:07, 37.46it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:06, 42.05it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:06, 40.49it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 26.68it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:07, 33.17it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:07, 36.48it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 42.49it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 40.42it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 48.61it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 40.46it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 41.85it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 36.17it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 37.43it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 40.16it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:05, 39.36it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 48.58it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:03, 48.31it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:03, 48.64it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 51.44it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 49.92it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 51.61it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:03, 47.99it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 55.51it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 51.81it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 42.34it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 41.98it/s]
Loading 0:  64%|██████▍   | 234/363 [00:05<00:02, 45.81it/s]
Loading 0:  66%|██████▌   | 239/363 [00:05<00:03, 40.14it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 48.86it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 48.15it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 50.31it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 47.63it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 55.03it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 50.71it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 50.19it/s]
Loading 0:  81%|████████  | 293/363 [00:06<00:01, 47.70it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 54.20it/s]
Loading 0:  85%|████████▌ | 309/363 [00:07<00:01, 32.94it/s]
Loading 0:  87%|████████▋ | 314/363 [00:07<00:01, 34.62it/s]
Loading 0:  88%|████████▊ | 321/363 [00:07<00:01, 37.38it/s]
Loading 0:  91%|█████████ | 330/363 [00:07<00:00, 42.95it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 46.80it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 48.96it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 49.28it/s]
                                                            
Job chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer completed after 155.45s with status: succeeded
Stopping job with name chaiml-ca18-v1-8-dpo-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v1-8-dpo-b025-v1
Waiting for inference service chaiml-ca18-v1-8-dpo-b025-v1 to be ready
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-ca18-v1-8-dpo-b025-v1 ready after 160.97330331802368s
Pipeline stage MKMLDeployer completed in 161.53s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6833701133728027s
Received healthy response to inference request in 1.342832326889038s
Received healthy response to inference request in 1.40549635887146s
Received healthy response to inference request in 1.3495557308197021s
Received healthy response to inference request in 1.5531139373779297s
5 requests
0 failed requests
5th percentile: 1.344177007675171
10th percentile: 1.3455216884613037
20th percentile: 1.3482110500335693
30th percentile: 1.3607438564300538
40th percentile: 1.3831201076507569
50th percentile: 1.40549635887146
60th percentile: 1.464543390274048
70th percentile: 1.5235904216766356
80th percentile: 1.5791651725769043
90th percentile: 1.6312676429748536
95th percentile: 1.6573188781738282
99th percentile: 1.6781598663330077
mean time: 1.4668736934661866
Pipeline stage StressChecker completed in 8.57s
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 0.67s
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 0.82s
Shutdown handler de-registered
chaiml-ca18-v1-8-dpo-b025_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ca18-v1-8-dpo-b025-v1-profiler
Waiting for inference service chaiml-ca18-v1-8-dpo-b025-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 2900.72s
Shutdown handler de-registered
chaiml-ca18-v1-8-dpo-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-8-dpo-b025_v1 status is now torndown due to DeploymentManager action