chaiml-ca18-v2-2-dpo-b025

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v2-2-dpo-b025_v1

model_name: training123

model_group: ChaiML/ca18-v2-2-dpo_b02

status: torndown

timestamp: 2025-11-20T06:41:15+00:00

num_battles: 5846

num_wins: 3114

celo_rating: 1305.36

family_friendly_score: 0.521

family_friendly_standard_error: 0.007064828377250222

submission_type: basic

model_repo: ChaiML/ca18-v2-2-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': 0.691090531011021, 'latency_mean': 1.446892750263214, 'latency_p50': 1.449567198753357, 'latency_p90': 1.5849666357040406}, {'batch_size': 3, 'throughput': 1.2971320673307978, 'latency_mean': 2.3066346824169157, 'latency_p50': 2.3167954683303833, 'latency_p90': 2.516017436981201}, {'batch_size': 5, 'throughput': 1.6007183918675447, 'latency_mean': 3.119004522562027, 'latency_p50': 3.0962207317352295, 'latency_p90': 3.588374614715576}, {'batch_size': 6, 'throughput': 1.6938870142294047, 'latency_mean': 3.522815934419632, 'latency_p50': 3.5234897136688232, 'latency_p90': 4.0061691999435425}, {'batch_size': 8, 'throughput': 1.8149303017753302, 'latency_mean': 4.3687737798690796, 'latency_p50': 4.34538471698761, 'latency_p90': 4.975018239021301}, {'batch_size': 10, 'throughput': 1.8821895332043823, 'latency_mean': 5.272488516569138, 'latency_p50': 5.26110577583313, 'latency_p90': 6.039287781715393}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v2-2-dpo_b025

model_size: 13B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2025-11-16

win_ratio: 0.5326719124187479

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', 'User:', 'You:', '</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
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
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
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
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer to finish
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: Downloaded to shared memory in 42.051s
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: Checking if ChaiML/ca18-v2-2-dpo_b025 already exists in ChaiML
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_7m78i16, device:0
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: quantized model in 26.215s
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: Processed model ChaiML/ca18-v2-2-dpo_b025 in 68.267s
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-b025-v1/nvidia/special_tokens_map.json
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-b025-v1/nvidia/config.json
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-b025-v1/nvidia/tokenizer_config.json
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-b025-v1/nvidia/tokenizer.json
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.80it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 47.71it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 51.91it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 54.17it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 56.03it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 56.71it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 62.55it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 46.62it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 44.72it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:05, 48.01it/s]
Loading 0:  25%|██▌       | 91/363 [00:01<00:05, 49.68it/s]
Loading 0:  28%|██▊       | 100/363 [00:01<00:05, 51.44it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 57.26it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 57.19it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:04, 57.84it/s]
Loading 0:  35%|███▌      | 128/363 [00:02<00:04, 51.72it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 55.71it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:04, 52.91it/s]
Loading 0:  40%|████      | 147/363 [00:02<00:05, 40.41it/s]
Loading 0:  42%|████▏     | 154/363 [00:03<00:04, 42.38it/s]
Loading 0:  44%|████▍     | 159/363 [00:03<00:04, 43.74it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:03, 49.37it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:03, 48.91it/s]
Loading 0:  49%|████▉     | 178/363 [00:03<00:03, 50.45it/s]
Loading 0:  51%|█████     | 184/363 [00:03<00:03, 52.33it/s]
Loading 0:  52%|█████▏    | 190/363 [00:03<00:03, 49.63it/s]
Loading 0:  54%|█████▍    | 196/363 [00:03<00:03, 51.38it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:03, 48.85it/s]
Loading 0:  58%|█████▊    | 209/363 [00:04<00:03, 44.99it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:03, 45.08it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 49.26it/s]
Loading 0:  63%|██████▎   | 227/363 [00:04<00:03, 38.68it/s]
Loading 0:  64%|██████▍   | 232/363 [00:04<00:03, 39.96it/s]
Loading 0:  66%|██████▌   | 239/363 [00:04<00:03, 41.12it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 49.62it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 48.89it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 50.46it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 46.77it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 53.93it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 52.05it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 53.60it/s]
Loading 0:  80%|████████  | 292/363 [00:05<00:01, 55.26it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 38.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:06<00:02, 25.97it/s]
Loading 0:  85%|████████▍ | 308/363 [00:06<00:02, 26.69it/s]
Loading 0:  86%|████████▌ | 312/363 [00:06<00:01, 27.84it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 36.28it/s]
Loading 0:  90%|█████████ | 328/363 [00:07<00:00, 41.06it/s]
Loading 0:  92%|█████████▏| 335/363 [00:07<00:00, 43.76it/s]
Loading 0:  94%|█████████▎| 340/363 [00:07<00:00, 40.87it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 43.59it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 47.51it/s]
                                                            
Job chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer completed after 133.83s with status: succeeded
Stopping job with name chaiml-ca18-v2-2-dpo-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 134.39s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v2-2-dpo-b025-v1
Waiting for inference service chaiml-ca18-v2-2-dpo-b025-v1 to be ready
Inference service chaiml-ca18-v2-2-dpo-b025-v1 ready after 160.66621947288513s
Pipeline stage MKMLDeployer completed in 161.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.665109395980835s
Received healthy response to inference request in 1.2558090686798096s
Received healthy response to inference request in 1.4840843677520752s
Received healthy response to inference request in 1.2999072074890137s
Received healthy response to inference request in 1.317624807357788s
5 requests
0 failed requests
5th percentile: 1.2646286964416504
10th percentile: 1.2734483242034913
20th percentile: 1.2910875797271728
30th percentile: 1.3034507274627685
40th percentile: 1.3105377674102783
50th percentile: 1.317624807357788
60th percentile: 1.3842086315155029
70th percentile: 1.4507924556732177
80th percentile: 1.520289373397827
90th percentile: 1.5926993846893311
95th percentile: 1.628904390335083
99th percentile: 1.6578683948516846
mean time: 1.4045069694519043
Pipeline stage StressChecker completed in 8.59s
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 0.91s
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-v2-2-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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ca18-v2-2-dpo-b025-v1-profiler
Waiting for inference service chaiml-ca18-v2-2-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 2641.30s
Shutdown handler de-registered
chaiml-ca18-v2-2-dpo-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v2-2-dpo-b025_v1 status is now torndown due to DeploymentManager action