chaiml-ca18-v1-8-dpo

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-8-dpo_v1

model_name: training123

model_group: ChaiML/ca18-v1-8-dpo

status: torndown

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

num_battles: 6263

num_wins: 3318

celo_rating: 1305.16

family_friendly_score: 0.5028

family_friendly_standard_error: 0.0070709569366529165

submission_type: basic

model_repo: ChaiML/ca18-v1-8-dpo

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': 0.6840811904679964, 'latency_mean': 1.4617170584201813, 'latency_p50': 1.465732216835022, 'latency_p90': 1.621917724609375}, {'batch_size': 3, 'throughput': 1.2697392740483098, 'latency_mean': 2.3518687224388124, 'latency_p50': 2.3410197496414185, 'latency_p90': 2.6302392721176147}, {'batch_size': 5, 'throughput': 1.536755424469796, 'latency_mean': 3.2461792182922364, 'latency_p50': 3.268526554107666, 'latency_p90': 3.684576106071472}, {'batch_size': 6, 'throughput': 1.6217425908917216, 'latency_mean': 3.6688063621520994, 'latency_p50': 3.670621871948242, 'latency_p90': 4.260779857635498}, {'batch_size': 8, 'throughput': 1.736308625705437, 'latency_mean': 4.577305866479874, 'latency_p50': 4.625048995018005, 'latency_p90': 5.293564367294311}, {'batch_size': 10, 'throughput': 1.8108401381851513, 'latency_mean': 5.483106178045273, 'latency_p50': 5.4771116971969604, 'latency_p90': 6.337615370750427}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-8-dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.64

us_pacific_date: 2025-11-17

win_ratio: 0.5297780616318059

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-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-8-dpo-v1-mkmlizer to finish
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-8-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-8-dpo-v1-mkmlizer: Downloaded to shared memory in 59.748s
chaiml-ca18-v1-8-dpo-v1-mkmlizer: Checking if ChaiML/ca18-v1-8-dpo already exists in ChaiML
chaiml-ca18-v1-8-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcd3ktyn6, device:0
chaiml-ca18-v1-8-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-8-dpo-v1-mkmlizer: quantized model in 25.808s
chaiml-ca18-v1-8-dpo-v1-mkmlizer: Processed model ChaiML/ca18-v1-8-dpo in 85.557s
chaiml-ca18-v1-8-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-8-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-8-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-v1/nvidia
chaiml-ca18-v1-8-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-v1/nvidia/config.json
chaiml-ca18-v1-8-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-8-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-8-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-v1/nvidia/tokenizer.json
chaiml-ca18-v1-8-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-8-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-8-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.71it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 47.73it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 51.94it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 54.22it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 55.36it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 56.04it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 61.57it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 45.31it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 43.25it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:06, 46.71it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 53.34it/s]
Loading 0:  26%|██▋       | 96/363 [00:01<00:05, 52.06it/s]
Loading 0:  28%|██▊       | 102/363 [00:01<00:04, 52.79it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 55.34it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 55.19it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:04, 55.21it/s]
Loading 0:  35%|███▌      | 128/363 [00:02<00:04, 48.24it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 53.13it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:04, 51.25it/s]
Loading 0:  40%|████      | 147/363 [00:02<00:05, 37.78it/s]
Loading 0:  42%|████▏     | 153/363 [00:03<00:04, 42.15it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:05, 39.36it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 48.25it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:03, 48.33it/s]
Loading 0:  49%|████▉     | 178/363 [00:03<00:03, 49.71it/s]
Loading 0:  51%|█████     | 185/363 [00:03<00:03, 47.84it/s]
Loading 0:  53%|█████▎    | 193/363 [00:03<00:03, 55.24it/s]
Loading 0:  55%|█████▍    | 199/363 [00:03<00:03, 53.20it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 54.04it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 55.50it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 52.91it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:03, 42.29it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 42.32it/s]
Loading 0:  64%|██████▍   | 234/363 [00:04<00:02, 46.17it/s]
Loading 0:  66%|██████▌   | 239/363 [00:04<00:02, 41.80it/s]
Loading 0:  68%|██████▊   | 247/363 [00:04<00:02, 50.90it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 49.90it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 51.43it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 48.17it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 54.75it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 51.95it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 52.18it/s]
Loading 0:  81%|████████  | 293/363 [00:05<00:01, 47.47it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 53.93it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 32.55it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 34.21it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 37.21it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 42.88it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 46.86it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 49.82it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 51.75it/s]
                                                            
Job chaiml-ca18-v1-8-dpo-v1-mkmlizer completed after 155.34s with status: succeeded
Stopping job with name chaiml-ca18-v1-8-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.11s
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-v1
Waiting for inference service chaiml-ca18-v1-8-dpo-v1 to be ready
Inference service chaiml-ca18-v1-8-dpo-v1 ready after 160.89730644226074s
Pipeline stage MKMLDeployer completed in 161.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7005655765533447s
Received healthy response to inference request in 1.5679786205291748s
Received healthy response to inference request in 1.5591766834259033s
Received healthy response to inference request in 1.2751662731170654s
Received healthy response to inference request in 1.7631826400756836s
5 requests
0 failed requests
5th percentile: 1.331968355178833
10th percentile: 1.3887704372406007
20th percentile: 1.5023746013641357
30th percentile: 1.5609370708465575
40th percentile: 1.5644578456878662
50th percentile: 1.5679786205291748
60th percentile: 1.6210134029388428
70th percentile: 1.6740481853485107
80th percentile: 1.7130889892578125
90th percentile: 1.738135814666748
95th percentile: 1.7506592273712158
99th percentile: 1.76067795753479
mean time: 1.5732139587402343
Pipeline stage StressChecker completed in 9.40s
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 0.95s
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-ca18-v1-8-dpo_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 2478.01s
Shutdown handler de-registered
chaiml-ca18-v1-8-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-8-dpo_v1 status is now torndown due to DeploymentManager action