developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-plroleplay_v1
model_name: alexcuadron-dpo-plroleplay_v1
model_group: AlexCuadron/dpo_plrolepl
status: inactive
timestamp: 2025-03-25T02:57:20+00:00
num_battles: 8228
num_wins: 4150
celo_rating: 1287.55
family_friendly_score: 0.5808
family_friendly_standard_error: 0.006978128115762852
submission_type: basic
model_repo: AlexCuadron/dpo_plroleplay
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.610220490065567, 'latency_mean': 1.6386777865886688, 'latency_p50': 1.6362522840499878, 'latency_p90': 1.809496021270752}, {'batch_size': 3, 'throughput': 1.1032638397284364, 'latency_mean': 2.7144232606887817, 'latency_p50': 2.7234119176864624, 'latency_p90': 2.990175747871399}, {'batch_size': 5, 'throughput': 1.3368729850994965, 'latency_mean': 3.712642934322357, 'latency_p50': 3.717627763748169, 'latency_p90': 4.174457216262818}, {'batch_size': 6, 'throughput': 1.4188064703730747, 'latency_mean': 4.209226797819138, 'latency_p50': 4.185109376907349, 'latency_p90': 4.7125307559967045}, {'batch_size': 8, 'throughput': 1.4707165588944322, 'latency_mean': 5.400458990335465, 'latency_p50': 5.452497482299805, 'latency_p90': 6.060416603088378}, {'batch_size': 10, 'throughput': 1.5324037773748143, 'latency_mean': 6.463369925022125, 'latency_p50': 6.4786601066589355, 'latency_p90': 7.28320767879486}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-plroleplay_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_plroleplay
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-03-24
win_ratio: 0.5043753038405445
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
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 alexcuadron-dpo-plroleplay-v1-mkmlizer
Waiting for job on alexcuadron-dpo-plroleplay-v1-mkmlizer to finish
alexcuadron-dpo-plroleplay-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║     _____            __           __                                ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║       /___/                                                         ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║                                                                     ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║                                                                     ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║                                                                     ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ║                                                                     ║
alexcuadron-dpo-plroleplay-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-plroleplay-v1-mkmlizer: Downloaded to shared memory in 44.222s
alexcuadron-dpo-plroleplay-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvlxy93ik, device:0
alexcuadron-dpo-plroleplay-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-plroleplay-v1-mkmlizer: quantized model in 42.201s
alexcuadron-dpo-plroleplay-v1-mkmlizer: Processed model AlexCuadron/dpo_plroleplay in 86.425s
alexcuadron-dpo-plroleplay-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-plroleplay-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-plroleplay-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-plroleplay-v1
alexcuadron-dpo-plroleplay-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-plroleplay-v1/config.json
alexcuadron-dpo-plroleplay-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-plroleplay-v1/special_tokens_map.json
alexcuadron-dpo-plroleplay-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-plroleplay-v1/tokenizer_config.json
alexcuadron-dpo-plroleplay-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-plroleplay-v1/tokenizer.json
alexcuadron-dpo-plroleplay-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-plroleplay-v1/flywheel_model.0.safetensors
alexcuadron-dpo-plroleplay-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<20:13,  3.36s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:25,  1.10it/s]
Loading 0:   3%|▎         | 11/363 [00:07<02:24,  2.44it/s]
Loading 0:   4%|▍         | 15/363 [00:07<01:31,  3.79it/s]
Loading 0:   6%|▌         | 20/363 [00:07<00:56,  6.08it/s]
Loading 0:   7%|▋         | 24/363 [00:07<00:42,  7.93it/s]
Loading 0:   8%|▊         | 29/363 [00:07<00:29, 11.30it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:24, 13.20it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:18, 17.14it/s]
Loading 0:  12%|█▏        | 42/363 [00:08<00:23, 13.83it/s]
Loading 0:  13%|█▎        | 47/363 [00:08<00:17, 17.81it/s]
Loading 0:  14%|█▍        | 51/363 [00:08<00:16, 18.94it/s]
Loading 0:  15%|█▌        | 56/363 [00:08<00:13, 23.23it/s]
Loading 0:  17%|█▋        | 60/363 [00:08<00:13, 23.25it/s]
Loading 0:  18%|█▊        | 65/363 [00:09<00:10, 27.41it/s]
Loading 0:  19%|█▉        | 69/363 [00:09<00:11, 26.15it/s]
Loading 0:  20%|██        | 74/363 [00:09<00:09, 30.05it/s]
Loading 0:  21%|██▏       | 78/363 [00:09<00:10, 28.03it/s]
Loading 0:  23%|██▎       | 83/363 [00:09<00:09, 30.67it/s]
Loading 0:  24%|██▍       | 87/363 [00:09<00:09, 28.18it/s]
Loading 0:  25%|██▌       | 92/363 [00:09<00:08, 31.80it/s]
Loading 0:  26%|██▋       | 96/363 [00:10<00:09, 28.71it/s]
Loading 0:  28%|██▊       | 101/363 [00:10<00:08, 32.23it/s]
Loading 0:  29%|██▉       | 105/363 [00:10<00:08, 29.26it/s]
Loading 0:  30%|███       | 110/363 [00:10<00:07, 32.34it/s]
Loading 0:  31%|███▏      | 114/363 [00:10<00:08, 29.65it/s]
Loading 0:  33%|███▎      | 119/363 [00:10<00:07, 34.16it/s]
Loading 0:  34%|███▍      | 123/363 [00:11<00:11, 21.07it/s]
Loading 0:  35%|███▌      | 128/363 [00:11<00:09, 25.66it/s]
Loading 0:  36%|███▋      | 132/363 [00:11<00:09, 25.42it/s]
Loading 0:  38%|███▊      | 137/363 [00:11<00:07, 29.94it/s]
Loading 0:  39%|███▉      | 141/363 [00:11<00:07, 28.61it/s]
Loading 0:  40%|████      | 146/363 [00:11<00:06, 33.04it/s]
Loading 0:  41%|████▏     | 150/363 [00:12<00:07, 29.39it/s]
Loading 0:  43%|████▎     | 155/363 [00:12<00:06, 33.23it/s]
Loading 0:  44%|████▍     | 159/363 [00:12<00:07, 28.93it/s]
Loading 0:  45%|████▌     | 164/363 [00:12<00:06, 31.79it/s]
Loading 0:  46%|████▋     | 168/363 [00:12<00:06, 28.40it/s]
Loading 0:  48%|████▊     | 173/363 [00:12<00:06, 31.16it/s]
Loading 0:  49%|████▉     | 177/363 [00:12<00:06, 28.33it/s]
Loading 0:  50%|█████     | 182/363 [00:13<00:05, 32.29it/s]
Loading 0:  51%|█████     | 186/363 [00:13<00:06, 29.40it/s]
Loading 0:  53%|█████▎    | 191/363 [00:13<00:05, 32.49it/s]
Loading 0:  54%|█████▎    | 195/363 [00:13<00:05, 29.48it/s]
Loading 0:  55%|█████▌    | 200/363 [00:13<00:04, 33.03it/s]
Loading 0:  56%|█████▌    | 204/363 [00:13<00:07, 20.80it/s]
Loading 0:  58%|█████▊    | 209/363 [00:14<00:06, 25.02it/s]
Loading 0:  59%|█████▊    | 213/363 [00:14<00:06, 24.07it/s]
Loading 0:  60%|██████    | 218/363 [00:14<00:05, 27.40it/s]
Loading 0:  61%|██████    | 222/363 [00:14<00:05, 25.41it/s]
Loading 0:  63%|██████▎   | 227/363 [00:14<00:04, 29.07it/s]
Loading 0:  64%|██████▎   | 231/363 [00:14<00:05, 26.12it/s]
Loading 0:  65%|██████▌   | 236/363 [00:15<00:04, 30.21it/s]
Loading 0:  66%|██████▌   | 240/363 [00:15<00:04, 28.15it/s]
Loading 0:  67%|██████▋   | 245/363 [00:15<00:03, 31.92it/s]
Loading 0:  69%|██████▊   | 249/363 [00:15<00:03, 29.01it/s]
Loading 0:  70%|██████▉   | 254/363 [00:15<00:03, 32.79it/s]
Loading 0:  71%|███████   | 258/363 [00:15<00:03, 29.55it/s]
Loading 0:  72%|███████▏  | 263/363 [00:15<00:03, 32.31it/s]
Loading 0:  74%|███████▎  | 267/363 [00:16<00:03, 29.11it/s]
Loading 0:  75%|███████▍  | 272/363 [00:16<00:02, 32.51it/s]
Loading 0:  76%|███████▌  | 276/363 [00:16<00:02, 29.32it/s]
Loading 0:  77%|███████▋  | 281/363 [00:16<00:02, 32.23it/s]
Loading 0:  79%|███████▊  | 285/363 [00:16<00:03, 20.92it/s]
Loading 0:  80%|███████▉  | 290/363 [00:16<00:02, 25.13it/s]
Loading 0:  81%|████████  | 294/363 [00:17<00:02, 24.82it/s]
Loading 0:  82%|████████▏ | 299/363 [00:17<00:02, 29.12it/s]
Loading 0:  83%|████████▎ | 303/363 [00:17<00:02, 27.47it/s]
Loading 0:  85%|████████▍ | 308/363 [00:17<00:01, 31.36it/s]
Loading 0:  86%|████████▌ | 312/363 [00:17<00:01, 28.75it/s]
Loading 0:  87%|████████▋ | 317/363 [00:17<00:01, 32.51it/s]
Loading 0:  88%|████████▊ | 321/363 [00:17<00:01, 29.10it/s]
Loading 0:  90%|████████▉ | 326/363 [00:18<00:01, 32.94it/s]
Loading 0:  91%|█████████ | 330/363 [00:18<00:01, 29.85it/s]
Loading 0:  92%|█████████▏| 335/363 [00:18<00:00, 31.30it/s]
Loading 0:  93%|█████████▎| 339/363 [00:18<00:00, 28.32it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:00, 32.76it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:00, 30.34it/s]
Loading 0:  98%|█████████▊| 355/363 [00:18<00:00, 36.67it/s]
Loading 0:  99%|█████████▉| 359/363 [00:19<00:00, 34.79it/s]
                                                            

Job alexcuadron-dpo-plroleplay-v1-mkmlizer completed after 245.29s with status: succeeded
Stopping job with name alexcuadron-dpo-plroleplay-v1-mkmlizer
Pipeline stage MKMLizer completed in 245.76s
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 alexcuadron-dpo-plroleplay-v1
Waiting for inference service alexcuadron-dpo-plroleplay-v1 to be ready
Inference service alexcuadron-dpo-plroleplay-v1 ready after 100.4381091594696s
Pipeline stage MKMLDeployer completed in 100.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3001880645751953s
Received healthy response to inference request in 1.6896138191223145s
Received healthy response to inference request in 1.6177363395690918s
Received healthy response to inference request in 1.5483968257904053s
Received healthy response to inference request in 1.4930105209350586s
5 requests
0 failed requests
5th percentile: 1.504087781906128
10th percentile: 1.5151650428771972
20th percentile: 1.5373195648193358
30th percentile: 1.5622647285461426
40th percentile: 1.590000534057617
50th percentile: 1.6177363395690918
60th percentile: 1.646487331390381
70th percentile: 1.6752383232116699
80th percentile: 1.8117286682128908
90th percentile: 2.055958366394043
95th percentile: 2.178073215484619
99th percentile: 2.27576509475708
mean time: 1.7297891139984132
Pipeline stage StressChecker completed in 9.93s
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 0.69s
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 0.78s
Shutdown handler de-registered
alexcuadron-dpo-plroleplay_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 alexcuadron-dpo-plroleplay-v1-profiler
Waiting for inference service alexcuadron-dpo-plroleplay-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4304.51s
Shutdown handler de-registered
alexcuadron-dpo-plroleplay_v1 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1