sao10k-mn-12b-lyra-v4a1

developer_uid: azuruce

submission_id: sao10k-mn-12b-lyra-v4a1_v17

model_name: sao10k-mn-12b-lyra-v4a1_v17

model_group: Sao10K/MN-12B-Lyra-v4a1

status: torndown

timestamp: 2024-10-23T05:50:46+00:00

num_battles: 7591

num_wins: 3485

celo_rating: 1214.7

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/MN-12B-Lyra-v4a1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 64

display_name: sao10k-mn-12b-lyra-v4a1_v17

is_internal_developer: True

language_model: Sao10K/MN-12B-Lyra-v4a1

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-22

win_ratio: 0.4590962982479252

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': 1, '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-v17-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v17-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║       /___/                                                         ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: Downloaded to shared memory in 48.869s
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpah2b6d0b, device:0
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: quantized model in 36.053s
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 84.922s
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v17
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v17/config.json
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v17/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v17/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v17/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v17/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a1-v17-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:08,  3.02s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:50,  1.23it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:07,  2.76it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:20,  4.32it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:39,  8.58it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:27, 11.93it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 15.17it/s]
Loading 0:  11%|█▏        | 41/363 [00:06<00:15, 21.08it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:12, 24.72it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 27.67it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:12, 24.47it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:11, 26.57it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:09, 31.67it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:08, 33.78it/s]
Loading 0:  22%|██▏       | 79/363 [00:08<00:07, 35.73it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 41.52it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 40.72it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 39.63it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:05, 43.86it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:05, 43.20it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 43.66it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:05, 41.63it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:05, 39.99it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:05, 43.96it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:05, 43.45it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 43.32it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:05, 41.48it/s]
Loading 0:  42%|████▏     | 151/363 [00:09<00:05, 40.34it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:06, 29.72it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:06, 30.82it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 34.32it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 34.69it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 38.28it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 39.45it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 40.38it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:04, 39.45it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:04, 39.45it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:03, 43.40it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:03, 43.51it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 43.92it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 41.93it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 39.06it/s]
Loading 0:  63%|██████▎   | 229/363 [00:11<00:03, 43.19it/s]
Loading 0:  64%|██████▍   | 234/363 [00:11<00:02, 43.55it/s]
Loading 0:  66%|██████▌   | 239/363 [00:11<00:02, 41.68it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 40.75it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 40.67it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:03, 31.35it/s]
Loading 0:  72%|███████▏  | 260/363 [00:12<00:03, 32.58it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 36.28it/s]
Loading 0:  74%|███████▍  | 269/363 [00:12<00:02, 36.29it/s]
Loading 0:  75%|███████▌  | 274/363 [00:12<00:02, 39.47it/s]
Loading 0:  77%|███████▋  | 279/363 [00:13<00:02, 38.99it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:01, 39.82it/s]
Loading 0:  80%|███████▉  | 290/363 [00:13<00:01, 39.44it/s]
Loading 0:  81%|████████▏ | 295/363 [00:13<00:01, 39.43it/s]
Loading 0:  83%|████████▎ | 301/363 [00:13<00:01, 44.21it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:01, 44.22it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 44.10it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 45.60it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:01, 37.70it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 43.46it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 42.60it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 41.93it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 43.70it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 36.28it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 29.62it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:00, 30.13it/s]
                                                            
Job sao10k-mn-12b-lyra-v4a1-v17-mkmlizer completed after 104.43s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v17-mkmlizer
Pipeline stage MKMLizer completed in 105.08s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-mn-12b-lyra-v4a1-v17
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v17 to be ready
Inference service sao10k-mn-12b-lyra-v4a1-v17 ready after 140.51461029052734s
Pipeline stage MKMLDeployer completed in 141.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5417637825012207s
Received healthy response to inference request in 0.592766284942627s
Received healthy response to inference request in 0.819354772567749s
Received healthy response to inference request in 1.3245689868927002s
Received healthy response to inference request in 0.5268290042877197s
5 requests
0 failed requests
5th percentile: 0.5400164604187012
10th percentile: 0.5532039165496826
20th percentile: 0.5795788288116455
30th percentile: 0.6380839824676514
40th percentile: 0.7287193775177002
50th percentile: 0.819354772567749
60th percentile: 1.0214404582977294
70th percentile: 1.2235261440277099
80th percentile: 1.3680079460144043
90th percentile: 1.4548858642578124
95th percentile: 1.4983248233795166
99th percentile: 1.5330759906768798
mean time: 0.9610565662384033
Pipeline stage StressChecker completed in 6.56s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 4.34s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v17 status is now deployed due to DeploymentManager action
sao10k-mn-12b-lyra-v4a1_v17 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v4a1_v17 status is now torndown due to DeploymentManager action