chaiml-ca18-v1-2-dpo

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-2-dpo_v1

model_name: training123

model_group: ChaiML/ca18-v1-2-dpo

status: torndown

timestamp: 2025-11-18T11:41:23+00:00

num_battles: 5990

num_wins: 3110

celo_rating: 1300.23

family_friendly_score: 0.509

family_friendly_standard_error: 0.007069922206078367

submission_type: basic

model_repo: ChaiML/ca18-v1-2-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': 0.6874017030678488, 'latency_mean': 1.4546572291851043, 'latency_p50': 1.4462594985961914, 'latency_p90': 1.5991844177246093}, {'batch_size': 3, 'throughput': 1.278176032503812, 'latency_mean': 2.3372034096717833, 'latency_p50': 2.3468756675720215, 'latency_p90': 2.56238796710968}, {'batch_size': 5, 'throughput': 1.5877483649090085, 'latency_mean': 3.136544897556305, 'latency_p50': 3.1292076110839844, 'latency_p90': 3.627169680595398}, {'batch_size': 6, 'throughput': 1.6709173505182442, 'latency_mean': 3.5710956692695617, 'latency_p50': 3.554334878921509, 'latency_p90': 4.007657098770141}, {'batch_size': 8, 'throughput': 1.79120130285802, 'latency_mean': 4.426282141208649, 'latency_p50': 4.416437029838562, 'latency_p90': 5.016589236259461}, {'batch_size': 10, 'throughput': 1.8621828482711928, 'latency_mean': 5.318242769241333, 'latency_p50': 5.354124903678894, 'latency_p90': 6.099498844146728}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-2-dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.7

us_pacific_date: 2025-11-15

win_ratio: 0.5191986644407346

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

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-v1-2-dpo-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-2-dpo-v1-mkmlizer to finish
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-2-dpo-v1-mkmlizer: Downloaded to shared memory in 49.740s
chaiml-ca18-v1-2-dpo-v1-mkmlizer: Checking if ChaiML/ca18-v1-2-dpo already exists in ChaiML
chaiml-ca18-v1-2-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph_jnt4rt, device:0
chaiml-ca18-v1-2-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-2-dpo-v1-mkmlizer: quantized model in 26.191s
chaiml-ca18-v1-2-dpo-v1-mkmlizer: Processed model ChaiML/ca18-v1-2-dpo in 75.932s
chaiml-ca18-v1-2-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-2-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-2-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-v1/nvidia
chaiml-ca18-v1-2-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-2-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-v1/nvidia/config.json
chaiml-ca18-v1-2-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-2-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-v1/nvidia/tokenizer.json
chaiml-ca18-v1-2-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-2-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.10it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 46.55it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 50.73it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 53.03it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 53.94it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 54.98it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:05, 60.43it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 44.97it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 43.21it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:05, 50.44it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:05, 49.47it/s]
Loading 0:  26%|██▌       | 93/363 [00:01<00:05, 50.57it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:05, 48.04it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 54.94it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 54.98it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:04, 52.57it/s]
Loading 0:  36%|███▌      | 129/363 [00:02<00:04, 53.09it/s]
Loading 0:  37%|███▋      | 136/363 [00:02<00:04, 49.66it/s]
Loading 0:  39%|███▉      | 142/363 [00:02<00:05, 42.35it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 42.05it/s]
Loading 0:  42%|████▏     | 153/363 [00:03<00:04, 45.79it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:05, 39.30it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 47.11it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 47.19it/s]
Loading 0:  49%|████▉     | 177/363 [00:03<00:03, 47.74it/s]
Loading 0:  51%|█████     | 184/363 [00:03<00:03, 52.93it/s]
Loading 0:  52%|█████▏    | 190/363 [00:03<00:03, 50.62it/s]
Loading 0:  54%|█████▍    | 196/363 [00:03<00:03, 51.11it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:03, 47.99it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 54.97it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 52.69it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:03, 41.81it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 41.52it/s]
Loading 0:  64%|██████▍   | 234/363 [00:04<00:02, 45.30it/s]
Loading 0:  66%|██████▌   | 239/363 [00:04<00:03, 41.01it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 48.63it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 47.65it/s]
Loading 0:  71%|███████   | 258/363 [00:05<00:02, 47.65it/s]
Loading 0:  73%|███████▎  | 265/363 [00:05<00:01, 53.24it/s]
Loading 0:  75%|███████▍  | 271/363 [00:05<00:01, 51.20it/s]
Loading 0:  76%|███████▋  | 277/363 [00:05<00:01, 52.37it/s]
Loading 0:  78%|███████▊  | 284/363 [00:05<00:01, 49.02it/s]
Loading 0:  80%|████████  | 292/363 [00:05<00:01, 56.35it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 52.89it/s]
Loading 0:  84%|████████▎ | 304/363 [00:06<00:01, 32.12it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 35.08it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 36.24it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 38.43it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 44.41it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 47.97it/s]
Loading 0:  96%|█████████▌| 347/363 [00:07<00:00, 54.80it/s]
Loading 0:  97%|█████████▋| 353/363 [00:07<00:00, 52.55it/s]
Loading 0:  99%|█████████▉| 359/363 [00:07<00:00, 52.85it/s]
                                                            
Job chaiml-ca18-v1-2-dpo-v1-mkmlizer completed after 133.86s with status: succeeded
Stopping job with name chaiml-ca18-v1-2-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 134.44s
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-v1-2-dpo-v1
Waiting for inference service chaiml-ca18-v1-2-dpo-v1 to be ready
Inference service chaiml-ca18-v1-2-dpo-v1 ready after 170.67157316207886s
Pipeline stage MKMLDeployer completed in 171.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4531943798065186s
Received healthy response to inference request in 1.4825475215911865s
Received healthy response to inference request in 1.5745644569396973s
Received healthy response to inference request in 1.6367847919464111s
Received healthy response to inference request in 1.332547903060913s
5 requests
0 failed requests
5th percentile: 1.3625478267669677
10th percentile: 1.3925477504730224
20th percentile: 1.4525475978851319
30th percentile: 1.5009509086608888
40th percentile: 1.537757682800293
50th percentile: 1.5745644569396973
60th percentile: 1.599452590942383
70th percentile: 1.6243407249450683
80th percentile: 1.8000667095184328
90th percentile: 2.1266305446624756
95th percentile: 2.289912462234497
99th percentile: 2.420537996292114
mean time: 1.6959278106689453
Pipeline stage StressChecker completed in 9.85s
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 0.92s
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 0.69s
Shutdown handler de-registered
chaiml-ca18-v1-2-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 0.08s
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-v1-2-dpo-v1-profiler
Waiting for inference service chaiml-ca18-v1-2-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 2527.69s
Shutdown handler de-registered
chaiml-ca18-v1-2-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-2-dpo_v1 status is now torndown due to DeploymentManager action