rinen0721-dpo-0130-cp3000

developer_uid: rirv938

submission_id: rinen0721-dpo-0130-cp3000_v15

model_name: rinen0721-dpo-0130-cp3000_v15

model_group: rinen0721/dpo-0130-cp300

status: torndown

timestamp: 2025-04-29T03:46:06+00:00

num_battles: 5708

num_wins: 2774

celo_rating: 1288.46

family_friendly_score: 0.5492

family_friendly_standard_error: 0.007036751523252757

submission_type: basic

model_repo: rinen0721/dpo-0130-cp3000

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6088319171482378, 'latency_mean': 1.6424225616455077, 'latency_p50': 1.6510121822357178, 'latency_p90': 1.7958864212036132}, {'batch_size': 3, 'throughput': 1.1117019334749139, 'latency_mean': 2.6911898922920225, 'latency_p50': 2.699934959411621, 'latency_p90': 2.9654770374298094}, {'batch_size': 5, 'throughput': 1.3211750839329905, 'latency_mean': 3.7632772648334503, 'latency_p50': 3.7835536003112793, 'latency_p90': 4.201381826400757}, {'batch_size': 6, 'throughput': 1.3996045249218187, 'latency_mean': 4.265650444030761, 'latency_p50': 4.2921870946884155, 'latency_p90': 4.799689602851868}, {'batch_size': 8, 'throughput': 1.4638479665697273, 'latency_mean': 5.42123712182045, 'latency_p50': 5.466843605041504, 'latency_p90': 6.019889616966248}, {'batch_size': 10, 'throughput': 1.5077788858446373, 'latency_mean': 6.580357993841171, 'latency_p50': 6.653648257255554, 'latency_p90': 7.423518228530884}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rinen0721-dpo-0130-cp3000_v15

is_internal_developer: True

language_model: rinen0721/dpo-0130-cp3000

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-04-28

win_ratio: 0.48598458304134545

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', 'User:', 'You:', '<|eot_id|>', '####', '\n', '</s>', 'Bot:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 rinen0721-dpo-0130-cp3000-v15-mkmlizer
Waiting for job on rinen0721-dpo-0130-cp3000-v15-mkmlizer to finish
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║     _____            __           __                                ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║       /___/                                                         ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║                                                                     ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  Version: 0.12.8                                                    ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║                                                                     ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  belonging to:                                                      ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║                                                                     ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ║                                                                     ║
rinen0721-dpo-0130-cp3000-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-dpo-0130-cp3000-v15-mkmlizer: Downloaded to shared memory in 86.029s
rinen0721-dpo-0130-cp3000-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph9dqe7hq, device:0
rinen0721-dpo-0130-cp3000-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-dpo-0130-cp3000-v15-mkmlizer: quantized model in 42.684s
rinen0721-dpo-0130-cp3000-v15-mkmlizer: Processed model rinen0721/dpo-0130-cp3000 in 128.714s
rinen0721-dpo-0130-cp3000-v15-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-dpo-0130-cp3000-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-dpo-0130-cp3000-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-dpo-0130-cp3000-v15
rinen0721-dpo-0130-cp3000-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-dpo-0130-cp3000-v15/config.json
rinen0721-dpo-0130-cp3000-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-dpo-0130-cp3000-v15/special_tokens_map.json
rinen0721-dpo-0130-cp3000-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-dpo-0130-cp3000-v15/tokenizer_config.json
rinen0721-dpo-0130-cp3000-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-dpo-0130-cp3000-v15/tokenizer.json
rinen0721-dpo-0130-cp3000-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-dpo-0130-cp3000-v15/flywheel_model.0.safetensors
rinen0721-dpo-0130-cp3000-v15-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.33it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.50it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.02it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.68it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:16, 21.01it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 18.91it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.46it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.09it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.23it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:12, 26.61it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.28it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 27.68it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.99it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.96it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.09it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:11, 25.60it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:11, 25.41it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 23.93it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.01it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.20it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.39it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 26.04it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:10, 24.01it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.14it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 26.15it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.75it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 28.73it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 25.64it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:07, 30.42it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:08, 26.56it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 30.35it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 24.87it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.60it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 21.44it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:07, 26.53it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 24.70it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.84it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.89it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.79it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.30it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 23.08it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.89it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 26.22it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 23.76it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:05, 28.58it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 25.63it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:04, 31.62it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:04, 30.06it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.33it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.24it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.09it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 21.79it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:04, 26.84it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 24.58it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 29.34it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 26.23it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.07it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.14it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 22.99it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 20.89it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.02it/s]
Loading 0:  76%|███████▌  | 276/363 [00:10<00:03, 25.38it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.66it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.48it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 30.53it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.95it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 28.71it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.47it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.37it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 22.40it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 29.08it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 28.30it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.34it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.55it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.61it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.26it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.63it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.81it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.94it/s]
                                                            
Job rinen0721-dpo-0130-cp3000-v15-mkmlizer completed after 156.23s with status: succeeded
Stopping job with name rinen0721-dpo-0130-cp3000-v15-mkmlizer
Pipeline stage MKMLizer completed in 156.71s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-dpo-0130-cp3000-v15
Waiting for inference service rinen0721-dpo-0130-cp3000-v15 to be ready
Inference service rinen0721-dpo-0130-cp3000-v15 ready after 140.5464997291565s
Pipeline stage MKMLDeployer completed in 141.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5485265254974365s
Received healthy response to inference request in 1.5833146572113037s
Received healthy response to inference request in 1.6208245754241943s
Received healthy response to inference request in 1.709399700164795s
Received healthy response to inference request in 1.5345861911773682s
5 requests
0 failed requests
5th percentile: 1.5443318843841554
10th percentile: 1.5540775775909423
20th percentile: 1.5735689640045165
30th percentile: 1.5908166408538817
40th percentile: 1.605820608139038
50th percentile: 1.6208245754241943
60th percentile: 1.6562546253204347
70th percentile: 1.6916846752166748
80th percentile: 1.8772250652313234
90th percentile: 2.21287579536438
95th percentile: 2.380701160430908
99th percentile: 2.5149614524841306
mean time: 1.7993303298950196
Pipeline stage StressChecker completed in 10.52s
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 0.64s
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
rinen0721-dpo-0130-cp3000_v15 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 rinen0721-dpo-0130-cp3000-v15-profiler
Waiting for inference service rinen0721-dpo-0130-cp3000-v15-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 3041.47s
Shutdown handler de-registered
rinen0721-dpo-0130-cp3000_v15 status is now inactive due to auto deactivation removed underperforming models
rinen0721-dpo-0130-cp3000_v15 status is now torndown due to DeploymentManager action