developer_uid: azuruce
submission_id: sao10k-mn-12b-lyra-v4a1_v37
model_name: sao10k-mn-12b-lyra-v4a1_v37
model_group: Sao10K/MN-12B-Lyra-v4a1
status: torndown
timestamp: 2024-10-24T07:24:23+00:00
num_battles: 6443
num_wins: 3548
celo_rating: 1279.94
family_friendly_score: 0.7767999999999999
family_friendly_standard_error: 0.005888663006150038
submission_type: basic
model_repo: Sao10K/MN-12B-Lyra-v4a1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: sao10k-mn-12b-lyra-v4a1_v37
is_internal_developer: True
language_model: Sao10K/MN-12B-Lyra-v4a1
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-24
win_ratio: 0.5506751513270216
generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '[/INST]', '<|im_end|>', '</s>'], 'max_input_tokens': 512, 'best_of': 16, '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 sao10k-mn-12b-lyra-v4a1-v37-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v37-mkmlizer to finish
Failed to get response for submission bbchicago-nana-nemo-12b-v1-0_v8: ('http://bbchicago-nana-nemo-12b-v1-0-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║       /___/                                                         ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: Downloaded to shared memory in 33.907s
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprxdg_wdn, device:0
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: quantized model in 35.359s
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 69.266s
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v37
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v37/config.json
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v37/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v37/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v37/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v37/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a1-v37-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:50,  2.96s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:44,  1.26it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:41,  3.45it/s]
Loading 0:   5%|▌         | 19/363 [00:06<00:58,  5.91it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:41,  8.17it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:26, 12.70it/s]
Loading 0:  10%|▉         | 36/363 [00:06<00:20, 16.18it/s]
Loading 0:  12%|█▏        | 42/363 [00:06<00:16, 19.71it/s]
Loading 0:  14%|█▍        | 50/363 [00:06<00:11, 27.29it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 29.98it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:11, 25.48it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:09, 30.72it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:08, 33.53it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 36.00it/s]
Loading 0:  23%|██▎       | 82/363 [00:07<00:07, 38.67it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 34.88it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 42.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 42.13it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 43.41it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 42.39it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:05, 41.83it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:05, 45.86it/s]
Loading 0:  35%|███▍      | 126/363 [00:08<00:05, 45.67it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:05, 43.93it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 45.20it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:05, 38.16it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:04, 45.76it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:04, 46.09it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:06, 32.09it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:05, 33.67it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:05, 35.99it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 39.30it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 33.58it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 41.32it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:04, 41.99it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 42.75it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:03, 44.28it/s]
Loading 0:  56%|█████▌    | 204/363 [00:10<00:04, 37.46it/s]
Loading 0:  58%|█████▊    | 211/363 [00:10<00:03, 44.92it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 45.53it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 44.90it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 45.34it/s]
Loading 0:  64%|██████▎   | 231/363 [00:11<00:03, 37.61it/s]
Loading 0:  66%|██████▌   | 238/363 [00:11<00:02, 45.24it/s]
Loading 0:  67%|██████▋   | 243/363 [00:11<00:02, 45.25it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:02, 45.21it/s]
Loading 0:  70%|██████▉   | 254/363 [00:11<00:02, 43.59it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:03, 30.73it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 36.28it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 38.54it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:02, 40.03it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:01, 42.11it/s]
Loading 0:  79%|███████▊  | 285/363 [00:12<00:02, 34.70it/s]
Loading 0:  80%|████████  | 292/363 [00:12<00:01, 42.41it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 43.29it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 43.30it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:01, 41.74it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:01, 41.46it/s]
Loading 0:  88%|████████▊ | 319/363 [00:13<00:00, 46.02it/s]
Loading 0:  89%|████████▉ | 324/363 [00:13<00:00, 45.72it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:00, 42.20it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 43.99it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:00, 37.64it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 44.42it/s]
Loading 0:  97%|█████████▋| 351/363 [00:14<00:00, 44.14it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 31.48it/s]
Loading 0:  99%|█████████▉| 361/363 [00:14<00:00, 35.08it/s]
                                                            

Job sao10k-mn-12b-lyra-v4a1-v37-mkmlizer completed after 104.71s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v37-mkmlizer
Pipeline stage MKMLizer completed in 105.57s
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 sao10k-mn-12b-lyra-v4a1-v37
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v37 to be ready
Inference service sao10k-mn-12b-lyra-v4a1-v37 ready after 120.45255780220032s
Pipeline stage MKMLDeployer completed in 120.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.719010591506958s
Received healthy response to inference request in 1.8063905239105225s
Received healthy response to inference request in 1.6527483463287354s
Received healthy response to inference request in 1.782834768295288s
Received healthy response to inference request in 1.6462790966033936s
5 requests
0 failed requests
5th percentile: 1.6475729465484619
10th percentile: 1.6488667964935302
20th percentile: 1.651454496383667
30th percentile: 1.678765630722046
40th percentile: 1.730800199508667
50th percentile: 1.782834768295288
60th percentile: 1.7922570705413818
70th percentile: 1.8016793727874756
80th percentile: 1.9889145374298098
90th percentile: 2.3539625644683837
95th percentile: 2.5364865779876706
99th percentile: 2.6825057888031005
mean time: 1.9214526653289794
Pipeline stage StressChecker completed in 10.98s
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 2.23s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v37 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 1969.66s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v37 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v4a1_v37 status is now torndown due to DeploymentManager action