developer_uid: azuruce
submission_id: toastypigeon-ms3-roseli_23049_v1
model_name: toastypigeon-ms3-roseli_23049_v1
model_group: ToastyPigeon/ms3-roselil
status: torndown
timestamp: 2025-02-25T00:29:29+00:00
num_battles: 5408
num_wins: 1619
celo_rating: 1061.91
family_friendly_score: 0.6377999999999999
family_friendly_standard_error: 0.0067972223738818486
submission_type: basic
model_repo: ToastyPigeon/ms3-roselily-instruct
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 2
max_input_tokens: 64
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4753253325426793, 'latency_mean': 2.1037544131278993, 'latency_p50': 2.099064588546753, 'latency_p90': 2.370542049407959}, {'batch_size': 5, 'throughput': 1.9573325615076693, 'latency_mean': 2.5344203400611875, 'latency_p50': 2.518148183822632, 'latency_p90': 2.8398961305618284}, {'batch_size': 10, 'throughput': 3.4355707274892917, 'latency_mean': 2.859420702457428, 'latency_p50': 2.8494564294815063, 'latency_p90': 3.182613205909729}, {'batch_size': 15, 'throughput': 4.585137698573097, 'latency_mean': 3.1611419796943663, 'latency_p50': 3.1892727613449097, 'latency_p90': 3.578469729423523}, {'batch_size': 20, 'throughput': 5.4855159948910455, 'latency_mean': 3.5365104484558105, 'latency_p50': 3.550669312477112, 'latency_p90': 4.006783604621887}, {'batch_size': 25, 'throughput': 6.228076585861448, 'latency_mean': 3.868040338754654, 'latency_p50': 3.887897253036499, 'latency_p90': 4.379904341697693}, {'batch_size': 30, 'throughput': 6.712927237286971, 'latency_mean': 4.236887378692627, 'latency_p50': 4.222720980644226, 'latency_p90': 4.866541624069214}, {'batch_size': 35, 'throughput': 7.10469877307747, 'latency_mean': 4.732863453626632, 'latency_p50': 4.784401893615723, 'latency_p90': 5.416177654266358}, {'batch_size': 40, 'throughput': 7.228041804487541, 'latency_mean': 5.265260555744171, 'latency_p50': 5.246570587158203, 'latency_p90': 6.170020508766174}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: toastypigeon-ms3-roseli_23049_v1
is_internal_developer: False
language_model: ToastyPigeon/ms3-roselily-instruct
model_size: 24B
ranking_group: single
throughput_3p7s: 6.07
us_pacific_date: 2025-02-24
win_ratio: 0.2993713017751479
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': 64, '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-v1-mkmlizer
Waiting for job on toastypigeon-ms3-roseli-23049-v1-mkmlizer to finish
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║     _____            __           __                                ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║       /___/                                                         ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║                                                                     ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  https://mk1.ai                                                     ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║                                                                     ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  belonging to:                                                      ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║                                                                     ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  Chai Research Corp.                                                ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ║                                                                     ║
toastypigeon-ms3-roseli-23049-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
toastypigeon-ms3-roseli-23049-v1-mkmlizer: Downloaded to shared memory in 87.054s
toastypigeon-ms3-roseli-23049-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6kdxu0hr, device:0
toastypigeon-ms3-roseli-23049-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
toastypigeon-ms3-roseli-23049-v1-mkmlizer: quantized model in 54.883s
toastypigeon-ms3-roseli-23049-v1-mkmlizer: Processed model ToastyPigeon/ms3-roselily-instruct in 141.938s
toastypigeon-ms3-roseli-23049-v1-mkmlizer: creating bucket guanaco-mkml-models
toastypigeon-ms3-roseli-23049-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
toastypigeon-ms3-roseli-23049-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v1
toastypigeon-ms3-roseli-23049-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v1/config.json
toastypigeon-ms3-roseli-23049-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v1/special_tokens_map.json
toastypigeon-ms3-roseli-23049-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v1/tokenizer_config.json
toastypigeon-ms3-roseli-23049-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v1/tokenizer.json
toastypigeon-ms3-roseli-23049-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v1/flywheel_model.1.safetensors
toastypigeon-ms3-roseli-23049-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/toastypigeon-ms3-roseli-23049-v1/flywheel_model.0.safetensors
toastypigeon-ms3-roseli-23049-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:39,  3.10s/it]
Loading 0:   1%|▏         | 5/363 [00:06<06:02,  1.01s/it]
Loading 0:   2%|▏         | 7/363 [00:06<03:49,  1.55it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:28,  3.96it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:06,  5.20it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:43,  7.91it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:36,  9.22it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:24, 13.55it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:22, 14.47it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:16, 19.74it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 20.12it/s]
Loading 0:  13%|█▎        | 49/363 [00:08<00:13, 22.71it/s]
Loading 0:  14%|█▍        | 52/363 [00:08<00:14, 21.07it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 25.98it/s]
Loading 0:  17%|█▋        | 61/363 [00:08<00:16, 18.17it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:12, 23.85it/s]
Loading 0:  20%|█▉        | 71/363 [00:09<00:12, 23.36it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 26.82it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:10, 25.87it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 29.86it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:09, 28.19it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:08, 31.44it/s]
Loading 0:  27%|██▋       | 98/363 [00:10<00:12, 21.65it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:10, 24.20it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 22.61it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 27.70it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:09, 27.15it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:07, 30.62it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:08, 29.08it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:07, 31.30it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:07, 29.43it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:09, 24.39it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:09, 22.52it/s]
Loading 0:  41%|████      | 148/363 [00:11<00:07, 27.93it/s]
Loading 0:  42%|████▏     | 152/363 [00:11<00:07, 26.84it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:06, 29.62it/s]
Loading 0:  44%|████▍     | 161/363 [00:12<00:07, 27.47it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 29.40it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:06, 28.40it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:05, 31.93it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:08, 22.16it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:06, 26.06it/s]
Loading 0:  52%|█████▏    | 188/363 [00:28<03:02,  1.04s/it]
Loading 0:  53%|█████▎    | 192/363 [00:28<02:09,  1.32it/s]
Loading 0:  54%|█████▍    | 196/363 [00:28<01:34,  1.76it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:58,  2.76it/s]
Loading 0:  57%|█████▋    | 206/363 [00:28<00:43,  3.61it/s]
Loading 0:  58%|█████▊    | 211/363 [00:29<00:30,  5.06it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:25,  5.89it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:17,  8.09it/s]
Loading 0:  61%|██████▏   | 223/363 [00:29<00:15,  9.14it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:10, 13.05it/s]
Loading 0:  64%|██████▍   | 232/363 [00:30<00:09, 13.82it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:06, 18.45it/s]
Loading 0:  67%|██████▋   | 242/363 [00:30<00:06, 19.56it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:05, 23.09it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:04, 23.33it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:05, 20.84it/s]
Loading 0:  71%|███████▏  | 259/363 [00:31<00:05, 20.12it/s]
Loading 0:  73%|███████▎  | 265/363 [00:31<00:03, 24.99it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:03, 23.82it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 29.34it/s]
Loading 0:  77%|███████▋  | 278/363 [00:31<00:02, 28.87it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:02, 32.22it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:02, 30.07it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:02, 31.88it/s]
Loading 0:  82%|████████▏ | 296/363 [00:32<00:03, 21.23it/s]
Loading 0:  83%|████████▎ | 301/363 [00:32<00:02, 24.26it/s]
Loading 0:  84%|████████▎ | 304/363 [00:32<00:02, 22.52it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:01, 27.66it/s]
Loading 0:  87%|████████▋ | 314/363 [00:33<00:01, 26.28it/s]
Loading 0:  88%|████████▊ | 319/363 [00:33<00:01, 28.33it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:01, 27.05it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 30.04it/s]
Loading 0:  91%|█████████▏| 332/363 [00:33<00:01, 22.03it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 25.73it/s]
Loading 0:  94%|█████████▎| 340/363 [00:34<00:00, 24.12it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 29.82it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:00, 28.56it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:00, 30.86it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 29.36it/s]
                                                            

Job toastypigeon-ms3-roseli-23049-v1-mkmlizer completed after 189.24s with status: succeeded
Stopping job with name toastypigeon-ms3-roseli-23049-v1-mkmlizer
Pipeline stage MKMLizer completed in 189.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service toastypigeon-ms3-roseli-23049-v1
Waiting for inference service toastypigeon-ms3-roseli-23049-v1 to be ready
Inference service toastypigeon-ms3-roseli-23049-v1 ready after 240.81969094276428s
Pipeline stage MKMLDeployer completed in 241.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.084635019302368s
Received healthy response to inference request in 1.2582213878631592s
Received healthy response to inference request in 1.66064453125s
Received healthy response to inference request in 1.9724736213684082s
Received healthy response to inference request in 0.5271708965301514s
5 requests
0 failed requests
5th percentile: 0.673380994796753
10th percentile: 0.8195910930633545
20th percentile: 1.1120112895965577
30th percentile: 1.3387060165405273
40th percentile: 1.4996752738952637
50th percentile: 1.66064453125
60th percentile: 1.7853761672973634
70th percentile: 1.9101078033447265
80th percentile: 1.9949059009552002
90th percentile: 2.0397704601287843
95th percentile: 2.062202739715576
99th percentile: 2.0801485633850096
mean time: 1.5006290912628173
Pipeline stage StressChecker completed in 8.88s
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 0.65s
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 0.65s
Shutdown handler de-registered
toastypigeon-ms3-roseli_23049_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 1853.08s
Shutdown handler de-registered
toastypigeon-ms3-roseli_23049_v1 status is now inactive due to auto deactivation removed underperforming models
toastypigeon-ms3-roseli_23049_v1 status is now torndown due to DeploymentManager action