chaiml-ca18-v2-1-dpo

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v2-1-dpo_v1

model_name: training123

model_group: ChaiML/ca18-v2-1-dpo

status: torndown

timestamp: 2025-11-19T21:21:15+00:00

num_battles: 5258

num_wins: 2853

celo_rating: 1311.79

family_friendly_score: 0.5076

family_friendly_standard_error: 0.007070250914925157

submission_type: basic

model_repo: ChaiML/ca18-v2-1-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': 0.609157394262171, 'latency_mean': 1.6415165436267853, 'latency_p50': 1.5233986377716064, 'latency_p90': 1.687518262863159}, {'batch_size': 3, 'throughput': 1.202347506520539, 'latency_mean': 2.489515210390091, 'latency_p50': 2.493844509124756, 'latency_p90': 2.7481003046035766}, {'batch_size': 5, 'throughput': 1.4185905664923268, 'latency_mean': 3.511865462064743, 'latency_p50': 3.5300856828689575, 'latency_p90': 3.906060004234314}, {'batch_size': 6, 'throughput': 1.5110772588048533, 'latency_mean': 3.9556542837619784, 'latency_p50': 3.9482346773147583, 'latency_p90': 4.511314487457275}, {'batch_size': 8, 'throughput': 1.6054381565749158, 'latency_mean': 4.947877714633941, 'latency_p50': 4.983157992362976, 'latency_p90': 5.48830361366272}, {'batch_size': 10, 'throughput': 1.6465261823508912, 'latency_mean': 6.0434274327754975, 'latency_p50': 6.058070540428162, 'latency_p90': 6.8854073762893675}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v2-1-dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.47

us_pacific_date: 2025-11-16

win_ratio: 0.5426017497147204

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': ['User:', 'You:', '\n', '</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

Connection pool is full, discarding connection: %s. Connection pool size: %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v2-1-dpo-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-1-dpo-v1-mkmlizer to finish
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v2-1-dpo-v1-mkmlizer: Downloaded to shared memory in 23.812s
chaiml-ca18-v2-1-dpo-v1-mkmlizer: Checking if ChaiML/ca18-v2-1-dpo already exists in ChaiML
chaiml-ca18-v2-1-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppnnwotoq, device:0
chaiml-ca18-v2-1-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v2-1-dpo-v1-mkmlizer: quantized model in 25.946s
chaiml-ca18-v2-1-dpo-v1-mkmlizer: Processed model ChaiML/ca18-v2-1-dpo in 49.758s
chaiml-ca18-v2-1-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v2-1-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v2-1-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-v1/nvidia
chaiml-ca18-v2-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-v1/nvidia/special_tokens_map.json
chaiml-ca18-v2-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-v1/nvidia/config.json
chaiml-ca18-v2-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-v1/nvidia/tokenizer_config.json
chaiml-ca18-v2-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-v1/nvidia/tokenizer.json
chaiml-ca18-v2-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v2-1-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.28it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 48.01it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 52.84it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 55.03it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 56.04it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 56.84it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 62.27it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 46.70it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 45.13it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:05, 48.66it/s]
Loading 0:  25%|██▌       | 91/363 [00:01<00:05, 49.00it/s]
Loading 0:  27%|██▋       | 99/363 [00:01<00:04, 55.31it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:04, 53.03it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 56.78it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 48.39it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 55.30it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 52.94it/s]
Loading 0:  38%|███▊      | 138/363 [00:02<00:05, 44.87it/s]
Loading 0:  39%|███▉      | 143/363 [00:02<00:06, 35.94it/s]
Loading 0:  41%|████      | 148/363 [00:03<00:06, 33.64it/s]
Loading 0:  42%|████▏     | 154/363 [00:03<00:05, 36.54it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:05, 37.05it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 46.51it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 47.02it/s]
Loading 0:  49%|████▉     | 177/363 [00:03<00:03, 47.12it/s]
Loading 0:  51%|█████     | 184/363 [00:03<00:03, 52.78it/s]
Loading 0:  52%|█████▏    | 190/363 [00:03<00:03, 51.09it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 52.29it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:03, 49.01it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 56.28it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 53.41it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:03, 42.48it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 42.99it/s]
Loading 0:  65%|██████▍   | 235/363 [00:04<00:02, 44.73it/s]
Loading 0:  66%|██████▌   | 240/363 [00:04<00:02, 45.82it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 51.62it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 50.27it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 51.72it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:01, 48.71it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 55.87it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 53.09it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 53.76it/s]
Loading 0:  81%|████████  | 293/363 [00:05<00:01, 49.77it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 55.58it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 33.28it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 34.71it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 37.62it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 43.18it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 46.86it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 49.56it/s]
Loading 0:  98%|█████████▊| 356/363 [00:07<00:00, 54.74it/s]
Loading 0: 100%|█████████▉| 362/363 [00:07<00:00, 52.44it/s]
                                                            
Job chaiml-ca18-v2-1-dpo-v1-mkmlizer completed after 183.39s with status: succeeded
Stopping job with name chaiml-ca18-v2-1-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 184.07s
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-ca18-v2-1-dpo-v1
Waiting for inference service chaiml-ca18-v2-1-dpo-v1 to be ready
Inference service chaiml-ca18-v2-1-dpo-v1 ready after 170.9502022266388s
Pipeline stage MKMLDeployer completed in 171.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2174928188323975s
Received healthy response to inference request in 1.3103082180023193s
Received healthy response to inference request in 1.2503137588500977s
Received healthy response to inference request in 1.2693212032318115s
Received healthy response to inference request in 1.6063930988311768s
5 requests
0 failed requests
5th percentile: 1.2541152477264403
10th percentile: 1.2579167366027832
20th percentile: 1.2655197143554688
30th percentile: 1.2775186061859132
40th percentile: 1.2939134120941163
50th percentile: 1.3103082180023193
60th percentile: 1.4287421703338623
70th percentile: 1.5471761226654053
80th percentile: 1.728613042831421
90th percentile: 1.9730529308319094
95th percentile: 2.0952728748321534
99th percentile: 2.1930488300323487
mean time: 1.5307658195495606
Pipeline stage StressChecker completed in 9.01s
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 0.64s
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 0.66s
Shutdown handler de-registered
chaiml-ca18-v2-1-dpo_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ca18-v2-1-dpo-v1-profiler
Waiting for inference service chaiml-ca18-v2-1-dpo-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 2630.41s
Shutdown handler de-registered
chaiml-ca18-v2-1-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v2-1-dpo_v1 status is now torndown due to DeploymentManager action