developer_uid: azuruce
submission_id: toastypigeon-ms3-roseli_23049_v2
model_name: toastypigeon-ms3-roseli_23049_v2
model_group: ToastyPigeon/ms3-roselil
status: torndown
timestamp: 2025-02-25T09:02:24+00:00
num_battles: 5301
num_wins: 2306
celo_rating: 1220.88
family_friendly_score: 0.5992
family_friendly_standard_error: 0.0069305030120475385
submission_type: basic
model_repo: ToastyPigeon/ms3-roselily-instruct
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 2
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.39066566100990835, 'latency_mean': 2.559636036157608, 'latency_p50': 2.574917793273926, 'latency_p90': 2.8372220754623414}, {'batch_size': 3, 'throughput': 0.8401977882561006, 'latency_mean': 3.5498364758491516, 'latency_p50': 3.545299530029297, 'latency_p90': 3.9073002338409424}, {'batch_size': 5, 'throughput': 1.1488070531531054, 'latency_mean': 4.339503247737884, 'latency_p50': 4.321630835533142, 'latency_p90': 4.797294354438781}, {'batch_size': 6, 'throughput': 1.229595694909406, 'latency_mean': 4.836704173088074, 'latency_p50': 4.830425262451172, 'latency_p90': 5.521731519699097}, {'batch_size': 8, 'throughput': 1.4048715121744126, 'latency_mean': 5.6431710350513455, 'latency_p50': 5.6872254610061646, 'latency_p90': 6.386003923416138}, {'batch_size': 10, 'throughput': 1.50778057423921, 'latency_mean': 6.559322007894516, 'latency_p50': 6.578828454017639, 'latency_p90': 7.427061223983765}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: toastypigeon-ms3-roseli_23049_v2
is_internal_developer: False
language_model: ToastyPigeon/ms3-roselily-instruct
model_size: 24B
ranking_group: single
throughput_3p7s: 0.91
us_pacific_date: 2025-02-25
win_ratio: 0.43501226183738917
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 2, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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 toastypigeon-ms3-roseli-23049-v2-mkmlizer
Waiting for job on toastypigeon-ms3-roseli-23049-v2-mkmlizer to finish
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║     _____            __           __                                ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║       /___/                                                         ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║                                                                     ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  https://mk1.ai                                                     ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║                                                                     ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  belonging to:                                                      ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║                                                                     ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  Chai Research Corp.                                                ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ║                                                                     ║
toastypigeon-ms3-roseli-23049-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
toastypigeon-ms3-roseli-23049-v2-mkmlizer: Downloaded to shared memory in 72.285s
toastypigeon-ms3-roseli-23049-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpredfxnkh, device:0
toastypigeon-ms3-roseli-23049-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
toastypigeon-ms3-roseli-23049-v2-mkmlizer: quantized model in 58.043s
toastypigeon-ms3-roseli-23049-v2-mkmlizer: Processed model ToastyPigeon/ms3-roselily-instruct in 130.330s
toastypigeon-ms3-roseli-23049-v2-mkmlizer: creating bucket guanaco-mkml-models
toastypigeon-ms3-roseli-23049-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
toastypigeon-ms3-roseli-23049-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v2
toastypigeon-ms3-roseli-23049-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v2/config.json
toastypigeon-ms3-roseli-23049-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v2/special_tokens_map.json
toastypigeon-ms3-roseli-23049-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v2/tokenizer_config.json
toastypigeon-ms3-roseli-23049-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v2/tokenizer.json
toastypigeon-ms3-roseli-23049-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v2/flywheel_model.1.safetensors
toastypigeon-ms3-roseli-23049-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v2/flywheel_model.0.safetensors
toastypigeon-ms3-roseli-23049-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<19:23,  3.22s/it]
Loading 0:   1%|▏         | 5/363 [00:06<06:17,  1.05s/it]
Loading 0:   2%|▏         | 7/363 [00:06<03:58,  1.49it/s]
Loading 0:   3%|▎         | 11/363 [00:06<01:55,  3.04it/s]
Loading 0:   4%|▍         | 14/363 [00:06<01:18,  4.46it/s]
Loading 0:   5%|▍         | 17/363 [00:07<00:56,  6.11it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:41,  8.14it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:35,  9.43it/s]
Loading 0:   8%|▊         | 29/363 [00:07<00:26, 12.58it/s]
Loading 0:   9%|▉         | 32/363 [00:07<00:22, 14.52it/s]
Loading 0:  10%|▉         | 35/363 [00:08<00:20, 16.13it/s]
Loading 0:  11%|█         | 40/363 [00:08<00:15, 20.26it/s]
Loading 0:  12%|█▏        | 43/363 [00:08<00:16, 19.90it/s]
Loading 0:  13%|█▎        | 49/363 [00:08<00:12, 25.90it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:12, 25.35it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 27.69it/s]
Loading 0:  17%|█▋        | 62/363 [00:09<00:15, 19.76it/s]
Loading 0:  18%|█▊        | 67/363 [00:09<00:12, 23.47it/s]
Loading 0:  19%|█▉        | 70/363 [00:09<00:13, 21.73it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 26.15it/s]
Loading 0:  22%|██▏       | 79/363 [00:09<00:12, 22.12it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 28.47it/s]
Loading 0:  25%|██▍       | 89/363 [00:10<00:09, 27.82it/s]
Loading 0:  26%|██▌       | 94/363 [00:10<00:08, 31.44it/s]
Loading 0:  27%|██▋       | 98/363 [00:10<00:12, 21.93it/s]
Loading 0:  28%|██▊       | 101/363 [00:10<00:11, 22.84it/s]
Loading 0:  29%|██▊       | 104/363 [00:10<00:11, 22.87it/s]
Loading 0:  29%|██▉       | 107/363 [00:10<00:11, 22.31it/s]
Loading 0:  30%|███       | 110/363 [00:10<00:10, 23.88it/s]
Loading 0:  31%|███       | 113/363 [00:11<00:10, 23.88it/s]
Loading 0:  32%|███▏      | 116/363 [00:11<00:10, 24.19it/s]
Loading 0:  33%|███▎      | 121/363 [00:11<00:08, 28.54it/s]
Loading 0:  34%|███▍      | 124/363 [00:11<00:11, 21.28it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:09, 25.88it/s]
Loading 0:  37%|███▋      | 133/363 [00:11<00:10, 21.98it/s]
Loading 0:  38%|███▊      | 137/363 [00:12<00:08, 25.19it/s]
Loading 0:  39%|███▊      | 140/363 [00:12<00:11, 18.91it/s]
Loading 0:  39%|███▉      | 143/363 [00:12<00:11, 18.51it/s]
Loading 0:  40%|████      | 146/363 [00:12<00:10, 20.24it/s]
Loading 0:  41%|████▏     | 150/363 [00:12<00:10, 19.59it/s]
Loading 0:  43%|████▎     | 155/363 [00:12<00:08, 25.18it/s]
Loading 0:  44%|████▎     | 158/363 [00:13<00:08, 25.14it/s]
Loading 0:  44%|████▍     | 161/363 [00:13<00:08, 24.71it/s]
Loading 0:  46%|████▌     | 166/363 [00:13<00:07, 27.17it/s]
Loading 0:  47%|████▋     | 169/363 [00:13<00:08, 22.82it/s]
Loading 0:  48%|████▊     | 175/363 [00:13<00:06, 27.98it/s]
Loading 0:  49%|████▉     | 178/363 [00:14<00:10, 17.65it/s]
Loading 0:  51%|█████     | 184/363 [00:14<00:07, 22.63it/s]
Loading 0:  52%|█████▏    | 187/363 [00:29<03:27,  1.18s/it]
Loading 0:  53%|█████▎    | 191/363 [00:29<02:24,  1.19it/s]
Loading 0:  53%|█████▎    | 194/363 [00:30<01:51,  1.52it/s]
Loading 0:  54%|█████▍    | 197/363 [00:30<01:23,  1.98it/s]
Loading 0:  56%|█████▌    | 202/363 [00:30<00:52,  3.08it/s]
Loading 0:  56%|█████▋    | 205/363 [00:30<00:41,  3.84it/s]
Loading 0:  58%|█████▊    | 211/363 [00:30<00:24,  6.12it/s]
Loading 0:  59%|█████▉    | 214/363 [00:31<00:23,  6.45it/s]
Loading 0:  61%|██████    | 220/363 [00:31<00:14,  9.67it/s]
Loading 0:  61%|██████▏   | 223/363 [00:31<00:13, 10.69it/s]
Loading 0:  63%|██████▎   | 229/363 [00:31<00:09, 14.83it/s]
Loading 0:  64%|██████▍   | 232/363 [00:31<00:08, 15.09it/s]
Loading 0:  66%|██████▌   | 238/363 [00:32<00:06, 19.78it/s]
Loading 0:  66%|██████▋   | 241/363 [00:32<00:06, 19.05it/s]
Loading 0:  68%|██████▊   | 247/363 [00:32<00:04, 23.59it/s]
Loading 0:  69%|██████▉   | 250/363 [00:32<00:05, 21.69it/s]
Loading 0:  71%|███████   | 256/363 [00:32<00:05, 20.56it/s]
Loading 0:  71%|███████▏  | 259/363 [00:33<00:05, 19.28it/s]
Loading 0:  72%|███████▏  | 263/363 [00:33<00:04, 22.48it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:04, 23.20it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:04, 23.11it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:03, 24.48it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:03, 25.19it/s]
Loading 0:  77%|███████▋  | 278/363 [00:33<00:03, 24.13it/s]
Loading 0:  77%|███████▋  | 281/363 [00:33<00:03, 25.32it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 25.34it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:03, 24.13it/s]
Loading 0:  80%|████████  | 292/363 [00:34<00:02, 27.05it/s]
Loading 0:  81%|████████▏ | 295/363 [00:34<00:03, 17.46it/s]
Loading 0:  83%|████████▎ | 301/363 [00:34<00:02, 22.57it/s]
Loading 0:  84%|████████▎ | 304/363 [00:35<00:02, 20.94it/s]
Loading 0:  85%|████████▌ | 310/363 [00:35<00:01, 26.53it/s]
Loading 0:  86%|████████▌ | 313/363 [00:35<00:02, 24.15it/s]
Loading 0:  88%|████████▊ | 319/363 [00:35<00:01, 29.04it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:01, 27.80it/s]
Loading 0:  90%|█████████ | 328/363 [00:35<00:01, 30.63it/s]
Loading 0:  91%|█████████▏| 332/363 [00:36<00:01, 20.14it/s]
Loading 0:  93%|█████████▎| 337/363 [00:36<00:01, 23.09it/s]
Loading 0:  94%|█████████▎| 340/363 [00:36<00:01, 21.00it/s]
Loading 0:  95%|█████████▌| 346/363 [00:36<00:00, 25.12it/s]
Loading 0:  96%|█████████▌| 349/363 [00:36<00:00, 21.66it/s]
Loading 0:  97%|█████████▋| 353/363 [00:36<00:00, 24.33it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 23.95it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 22.91it/s]
Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 24.26it/s]
                                                            

Job toastypigeon-ms3-roseli-23049-v2-mkmlizer completed after 154.84s with status: succeeded
Stopping job with name toastypigeon-ms3-roseli-23049-v2-mkmlizer
Pipeline stage MKMLizer completed in 155.32s
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 toastypigeon-ms3-roseli-23049-v2
Waiting for inference service toastypigeon-ms3-roseli-23049-v2 to be ready
Inference service toastypigeon-ms3-roseli-23049-v2 ready after 260.89753580093384s
Pipeline stage MKMLDeployer completed in 261.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4427881240844727s
Received healthy response to inference request in 1.106597900390625s
Received healthy response to inference request in 2.2635579109191895s
Received healthy response to inference request in 1.427053689956665s
Received healthy response to inference request in 2.347626209259033s
5 requests
0 failed requests
5th percentile: 1.170689058303833
10th percentile: 1.234780216217041
20th percentile: 1.362962532043457
30th percentile: 1.4302005767822266
40th percentile: 1.4364943504333496
50th percentile: 1.4427881240844727
60th percentile: 1.7710960388183592
70th percentile: 2.0994039535522457
80th percentile: 2.280371570587158
90th percentile: 2.313998889923096
95th percentile: 2.3308125495910645
99th percentile: 2.3442634773254394
mean time: 1.717524766921997
Pipeline stage StressChecker completed in 10.01s
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 0.67s
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
toastypigeon-ms3-roseli_23049_v2 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 2630.75s
Shutdown handler de-registered
toastypigeon-ms3-roseli_23049_v2 status is now inactive due to auto deactivation removed underperforming models
toastypigeon-ms3-roseli_23049_v2 status is now torndown due to DeploymentManager action