developer_uid: chai_backend_admin
submission_id: chaiml-ca18-v1-4-dpo-b025_v1
model_name: training123
model_group: ChaiML/ca18-v1-4-dpo_b02
status: torndown
timestamp: 2025-11-19T09:01:34+00:00
num_battles: 5534
num_wins: 2906
celo_rating: 1296.92
family_friendly_score: 0.5114000000000001
family_friendly_standard_error: 0.007069229661002675
submission_type: basic
model_repo: ChaiML/ca18-v1-4-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': 0.6872958632722642, 'latency_mean': 1.4548818528652192, 'latency_p50': 1.4539741277694702, 'latency_p90': 1.6062172412872315}, {'batch_size': 3, 'throughput': 1.2822918481876309, 'latency_mean': 2.338296310901642, 'latency_p50': 2.3581106662750244, 'latency_p90': 2.552457404136658}, {'batch_size': 5, 'throughput': 1.5634283202076098, 'latency_mean': 3.1805532598495483, 'latency_p50': 3.1708874702453613, 'latency_p90': 3.577805495262146}, {'batch_size': 6, 'throughput': 1.6537776808355602, 'latency_mean': 3.6068755555152894, 'latency_p50': 3.601743459701538, 'latency_p90': 4.060696935653686}, {'batch_size': 8, 'throughput': 1.7732382373528166, 'latency_mean': 4.47043964266777, 'latency_p50': 4.519677400588989, 'latency_p90': 5.046415758132935}, {'batch_size': 10, 'throughput': 1.851235557759654, 'latency_mean': 5.34194628238678, 'latency_p50': 5.394827961921692, 'latency_p90': 6.044394040107727}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ca18-v1-4-dpo_b025
model_size: 13B
ranking_group: single
throughput_3p7s: 1.68
us_pacific_date: 2025-11-16
win_ratio: 0.5251174557282255
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': ['You:', '</s>', '\n', '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-v1-4-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer to finish
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: Downloaded to shared memory in 62.207s
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: Checking if ChaiML/ca18-v1-4-dpo_b025 already exists in ChaiML
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpccquuxdz, device:0
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: quantized model in 25.912s
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: Processed model ChaiML/ca18-v1-4-dpo_b025 in 88.119s
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-4-dpo-b025-v1/nvidia
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-4-dpo-b025-v1/nvidia/config.json
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-4-dpo-b025-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-4-dpo-b025-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-4-dpo-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.69it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 48.96it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 53.43it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 55.10it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 56.47it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 56.00it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 61.83it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 46.44it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 44.64it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:05, 47.89it/s]
Loading 0:  24%|██▍       | 88/363 [00:01<00:05, 46.67it/s]
Loading 0:  26%|██▌       | 93/363 [00:01<00:05, 46.03it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:05, 45.55it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 53.27it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 53.67it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:04, 51.82it/s]
Loading 0:  36%|███▌      | 129/363 [00:02<00:04, 52.57it/s]
Loading 0:  37%|███▋      | 136/363 [00:02<00:04, 49.69it/s]
Loading 0:  39%|███▉      | 142/363 [00:02<00:05, 43.36it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 42.84it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:04, 44.01it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:04, 42.16it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:03, 50.89it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:03, 49.45it/s]
Loading 0:  49%|████▉     | 178/363 [00:03<00:03, 50.82it/s]
Loading 0:  51%|█████     | 185/363 [00:03<00:03, 48.83it/s]
Loading 0:  53%|█████▎    | 193/363 [00:03<00:03, 56.18it/s]
Loading 0:  55%|█████▍    | 199/363 [00:03<00:03, 53.89it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 54.35it/s]
Loading 0:  58%|█████▊    | 212/363 [00:04<00:02, 50.62it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 56.44it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 42.60it/s]
Loading 0:  64%|██████▍   | 234/363 [00:04<00:02, 45.93it/s]
Loading 0:  66%|██████▌   | 240/363 [00:04<00:02, 44.18it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:02, 45.78it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 53.07it/s]
Loading 0:  72%|███████▏  | 262/363 [00:05<00:01, 51.61it/s]
Loading 0:  74%|███████▍  | 268/363 [00:05<00:01, 52.80it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 54.62it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 51.30it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 52.08it/s]
Loading 0:  81%|████████  | 293/363 [00:05<00:01, 48.69it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 54.83it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 32.94it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 34.71it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 37.59it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 43.68it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 47.86it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 50.41it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 52.61it/s]
                                                            

Job chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer completed after 124.46s with status: succeeded
Stopping job with name chaiml-ca18-v1-4-dpo-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.06s
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-v1-4-dpo-b025-v1
Waiting for inference service chaiml-ca18-v1-4-dpo-b025-v1 to be ready
Inference service chaiml-ca18-v1-4-dpo-b025-v1 ready after 170.97476148605347s
Pipeline stage MKMLDeployer completed in 171.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6340000629425049s
Received healthy response to inference request in 1.3213763236999512s
Received healthy response to inference request in 1.3362905979156494s
Received healthy response to inference request in 1.5085358619689941s
Received healthy response to inference request in 1.5292365550994873s
5 requests
0 failed requests
5th percentile: 1.3243591785430908
10th percentile: 1.3273420333862305
20th percentile: 1.3333077430725098
30th percentile: 1.3707396507263183
40th percentile: 1.4396377563476563
50th percentile: 1.5085358619689941
60th percentile: 1.5168161392211914
70th percentile: 1.5250964164733887
80th percentile: 1.5501892566680908
90th percentile: 1.5920946598052979
95th percentile: 1.6130473613739014
99th percentile: 1.629809522628784
mean time: 1.4658878803253175
Pipeline stage StressChecker completed in 8.69s
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 0.63s
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 0.60s
Shutdown handler de-registered
chaiml-ca18-v1-4-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 2506.12s
Shutdown handler de-registered
chaiml-ca18-v1-4-dpo-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-4-dpo-b025_v1 status is now torndown due to DeploymentManager action