chaiml-ca18-v2-2-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v2-2-dpo-cosine_v1

model_name: training123

model_group: ChaiML/ca18-v2-2-dpo_cos

status: torndown

timestamp: 2025-11-20T06:41:14+00:00

num_battles: 5753

num_wins: 2964

celo_rating: 1295.35

family_friendly_score: 0.5167999999999999

family_friendly_standard_error: 0.00706707520831638

submission_type: basic

model_repo: ChaiML/ca18-v2-2-dpo_cosine

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': 0.69264174609667, 'latency_mean': 1.443651226758957, 'latency_p50': 1.4294171333312988, 'latency_p90': 1.597239875793457}, {'batch_size': 3, 'throughput': 1.295804106241828, 'latency_mean': 2.3106835544109345, 'latency_p50': 2.321794271469116, 'latency_p90': 2.520481991767883}, {'batch_size': 5, 'throughput': 1.5814308858824415, 'latency_mean': 3.147336460351944, 'latency_p50': 3.128615140914917, 'latency_p90': 3.62013041973114}, {'batch_size': 6, 'throughput': 1.6824820787278716, 'latency_mean': 3.546750417947769, 'latency_p50': 3.548954725265503, 'latency_p90': 4.0648222923278805}, {'batch_size': 8, 'throughput': 1.8033362815859173, 'latency_mean': 4.403381549119949, 'latency_p50': 4.403987765312195, 'latency_p90': 4.974159455299377}, {'batch_size': 10, 'throughput': 1.8634760576043472, 'latency_mean': 5.327753564119339, 'latency_p50': 5.307724833488464, 'latency_p90': 6.047622299194336}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v2-2-dpo_cosine

model_size: 13B

ranking_group: single

throughput_3p7s: 1.72

us_pacific_date: 2025-11-16

win_ratio: 0.5152094559360334

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>', 'You:', 'User:'], '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-v2-2-dpo-cosine-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer to finish
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: quantized model in 27.233s
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: Processed model ChaiML/ca18-v2-2-dpo_cosine in 86.414s
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-cosine-v1/nvidia
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-cosine-v1/nvidia/config.json
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.45it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 53.86it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.82it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.24it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.38it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.14it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 45.88it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:06, 47.17it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:05, 54.83it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 39.84it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 43.27it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.56it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 43.03it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 48.43it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.02it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 44.30it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 52.64it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 46.97it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 43.09it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 45.90it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 43.51it/s]
Loading 0:  38%|███▊      | 137/363 [00:02<00:05, 43.19it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.29it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.57it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.27it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.30it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 40.00it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 40.10it/s]
Loading 0:  47%|████▋     | 171/363 [00:03<00:04, 42.46it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 32.93it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.35it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 40.99it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 40.42it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 41.97it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:04, 37.27it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 45.69it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 44.11it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.14it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 35.70it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 35.60it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 42.42it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 41.89it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:03, 36.22it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 45.32it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 41.49it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 40.37it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 44.78it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 44.58it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:01, 39.78it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 48.11it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 44.69it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 45.71it/s]
Loading 0:  85%|████████▍ | 308/363 [00:07<00:02, 26.54it/s]
Loading 0:  86%|████████▌ | 312/363 [00:07<00:01, 27.61it/s]
Loading 0:  88%|████████▊ | 321/363 [00:07<00:01, 35.45it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:00, 39.73it/s]
Loading 0:  93%|█████████▎| 339/363 [00:08<00:00, 43.48it/s]
Loading 0:  96%|█████████▌| 347/363 [00:08<00:00, 50.09it/s]
Loading 0:  97%|█████████▋| 353/363 [00:08<00:00, 45.66it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 44.81it/s]
                                                            
Job chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer completed after 154.8s with status: succeeded
Stopping job with name chaiml-ca18-v2-2-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.29s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v2-2-dpo-cosine-v1
Waiting for inference service chaiml-ca18-v2-2-dpo-cosine-v1 to be ready
Inference service chaiml-ca18-v2-2-dpo-cosine-v1 ready after 160.71259713172913s
Pipeline stage MKMLDeployer completed in 161.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6791386604309082s
Received healthy response to inference request in 2.351667642593384s
Received healthy response to inference request in 1.2958910465240479s
Received healthy response to inference request in 1.6294164657592773s
Received healthy response to inference request in 1.1995007991790771s
5 requests
0 failed requests
5th percentile: 1.2187788486480713
10th percentile: 1.2380568981170654
20th percentile: 1.2766129970550537
30th percentile: 1.3625961303710938
40th percentile: 1.4960062980651856
50th percentile: 1.6294164657592773
60th percentile: 1.6493053436279297
70th percentile: 1.669194221496582
80th percentile: 1.8136444568634034
90th percentile: 2.0826560497283935
95th percentile: 2.2171618461608884
99th percentile: 2.3247664833068846
mean time: 1.631122922897339
Pipeline stage StressChecker completed in 9.35s
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 0.65s
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 0.63s
Shutdown handler de-registered
chaiml-ca18-v2-2-dpo-cosine_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-v2-2-dpo-cosine-v1-profiler
Waiting for inference service chaiml-ca18-v2-2-dpo-cosine-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 2627.71s
Shutdown handler de-registered
chaiml-ca18-v2-2-dpo-cosine_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v2-2-dpo-cosine_v1 status is now torndown due to DeploymentManager action