chaiml-ca18-v1-10-dpo-b025

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-10-dpo-b025_v1

model_name: training123

model_group: ChaiML/ca18-v1-10-dpo_b0

status: torndown

timestamp: 2025-11-20T12:01:22+00:00

num_battles: 5414

num_wins: 2858

celo_rating: 1306.12

family_friendly_score: 0.5072

family_friendly_standard_error: 0.007070334645545429

submission_type: basic

model_repo: ChaiML/ca18-v1-10-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': 0.6947280594179275, 'latency_mean': 1.4392872071266174, 'latency_p50': 1.4219841957092285, 'latency_p90': 1.5964043140411377}, {'batch_size': 3, 'throughput': 1.2730042186803003, 'latency_mean': 2.3534914481639864, 'latency_p50': 2.352976679801941, 'latency_p90': 2.575752353668213}, {'batch_size': 5, 'throughput': 1.5572265316619665, 'latency_mean': 3.2048690736293795, 'latency_p50': 3.1856753826141357, 'latency_p90': 3.601490521430969}, {'batch_size': 6, 'throughput': 1.6388111463487494, 'latency_mean': 3.6441099298000337, 'latency_p50': 3.679943084716797, 'latency_p90': 4.105012655258179}, {'batch_size': 8, 'throughput': 1.7676006609276895, 'latency_mean': 4.503504575490951, 'latency_p50': 4.539067029953003, 'latency_p90': 5.093743252754211}, {'batch_size': 10, 'throughput': 1.8303314876057455, 'latency_mean': 5.426649692058564, 'latency_p50': 5.452928304672241, 'latency_p90': 6.150599789619446}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-10-dpo_b025

model_size: 13B

ranking_group: single

throughput_3p7s: 1.66

us_pacific_date: 2025-11-17

win_ratio: 0.527890653860362

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', 'You:', '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer to finish
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: Downloaded to shared memory in 46.981s
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: Checking if ChaiML/ca18-v1-10-dpo_b025 already exists in ChaiML
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc3dviuhi, device:0
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: quantized model in 27.200s
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: Processed model ChaiML/ca18-v1-10-dpo_b025 in 74.182s
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-b025-v1/nvidia
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-b025-v1/nvidia/config.json
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-b025-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-b025-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-b025-v1/nvidia/tokenizer.json
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.39it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 47.55it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 52.15it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 54.67it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 55.82it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 55.77it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 61.79it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 45.68it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 43.59it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:05, 50.82it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:05, 49.72it/s]
Loading 0:  26%|██▌       | 93/363 [00:01<00:05, 51.18it/s]
Loading 0:  28%|██▊       | 100/363 [00:01<00:05, 48.23it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 54.62it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 54.44it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:04, 52.76it/s]
Loading 0:  35%|███▌      | 128/363 [00:02<00:05, 43.76it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 48.81it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:04, 47.43it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.87it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:05, 36.57it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 41.51it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 42.46it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:05, 36.15it/s]
Loading 0:  48%|████▊     | 174/363 [00:03<00:04, 40.60it/s]
Loading 0:  49%|████▉     | 179/363 [00:03<00:04, 41.49it/s]
Loading 0:  51%|█████     | 184/363 [00:03<00:04, 43.30it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 42.53it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 42.78it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 49.13it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 46.49it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 46.73it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 51.52it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 39.13it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:03, 41.34it/s]
Loading 0:  66%|██████▌   | 239/363 [00:05<00:03, 39.89it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 48.25it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 47.53it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 48.91it/s]
Loading 0:  73%|███████▎  | 265/363 [00:05<00:01, 51.53it/s]
Loading 0:  75%|███████▍  | 271/363 [00:05<00:01, 49.49it/s]
Loading 0:  76%|███████▋  | 277/363 [00:05<00:01, 51.24it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:01, 48.22it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 44.07it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 43.34it/s]
Loading 0:  83%|████████▎ | 302/363 [00:06<00:01, 52.35it/s]
Loading 0:  85%|████████▍ | 308/363 [00:06<00:01, 27.96it/s]
Loading 0:  86%|████████▌ | 313/363 [00:07<00:01, 29.65it/s]
Loading 0:  88%|████████▊ | 320/363 [00:07<00:01, 36.47it/s]
Loading 0:  90%|████████▉ | 326/363 [00:07<00:00, 37.70it/s]
Loading 0:  91%|█████████ | 331/363 [00:07<00:00, 37.58it/s]
Loading 0:  93%|█████████▎| 337/363 [00:07<00:00, 41.95it/s]
Loading 0:  94%|█████████▍| 342/363 [00:07<00:00, 41.62it/s]
Loading 0:  96%|█████████▌| 347/363 [00:07<00:00, 43.14it/s]
Loading 0:  97%|█████████▋| 352/363 [00:07<00:00, 44.28it/s]
Loading 0:  98%|█████████▊| 357/363 [00:08<00:00, 38.67it/s]
                                                            
Job chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer completed after 134.21s with status: succeeded
Stopping job with name chaiml-ca18-v1-10-dpo-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.16s
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-v1-10-dpo-b025-v1
Waiting for inference service chaiml-ca18-v1-10-dpo-b025-v1 to be ready
Inference service chaiml-ca18-v1-10-dpo-b025-v1 ready after 160.76507353782654s
Pipeline stage MKMLDeployer completed in 163.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8025741577148438s
Received healthy response to inference request in 1.3279118537902832s
Received healthy response to inference request in 1.4951655864715576s
Received healthy response to inference request in 1.246511459350586s
Received healthy response to inference request in 1.377697229385376s
5 requests
0 failed requests
5th percentile: 1.2627915382385253
10th percentile: 1.2790716171264649
20th percentile: 1.3116317749023438
30th percentile: 1.3378689289093018
40th percentile: 1.3577830791473389
50th percentile: 1.377697229385376
60th percentile: 1.4246845722198487
70th percentile: 1.4716719150543214
80th percentile: 1.5566473007202148
90th percentile: 1.6796107292175293
95th percentile: 1.7410924434661865
99th percentile: 1.7902778148651124
mean time: 1.4499720573425292
Pipeline stage StressChecker completed in 9.67s
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 0.71s
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 0.67s
Shutdown handler de-registered
chaiml-ca18-v1-10-dpo-b025_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 2477.02s
Shutdown handler de-registered
chaiml-ca18-v1-10-dpo-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-10-dpo-b025_v1 status is now torndown due to DeploymentManager action