sao10k-mn-12b-lyra-v4a1

developer_uid: azuruce

submission_id: sao10k-mn-12b-lyra-v4a1_v27

model_name: sao10k-mn-12b-lyra-v4a1_v27

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

status: torndown

timestamp: 2024-10-24T07:06:41+00:00

num_battles: 6936

num_wins: 3130

celo_rating: 1208.27

family_friendly_score: 0.7862

family_friendly_standard_error: 0.005798095549402407

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_v27

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: 0.45126874279123413

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-v27-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v27-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║       /___/                                                         ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: Downloaded to shared memory in 36.462s
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu_04ouph, device:0
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: quantized model in 36.307s
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 72.769s
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v27
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v27/config.json
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v27/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v27/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v27/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v27/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a1-v27-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<20:27,  3.40s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:25,  1.10it/s]
Loading 0:   3%|▎         | 12/363 [00:07<02:07,  2.76it/s]
Loading 0:   4%|▍         | 16/363 [00:07<01:23,  4.17it/s]
Loading 0:   6%|▋         | 23/363 [00:07<00:44,  7.57it/s]
Loading 0:   8%|▊         | 29/363 [00:07<00:30, 10.79it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:23, 13.92it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:16, 19.65it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:13, 23.21it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 26.37it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:12, 24.60it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:11, 26.62it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:09, 30.86it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:08, 33.45it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 36.34it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:07, 36.65it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:07, 37.75it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:06, 42.72it/s]
Loading 0:  27%|██▋       | 99/363 [00:09<00:06, 42.90it/s]
Loading 0:  29%|██▊       | 104/363 [00:09<00:05, 43.36it/s]
Loading 0:  30%|███       | 109/363 [00:09<00:05, 44.93it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:06, 37.08it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:05, 44.53it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:05, 43.77it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:05, 43.80it/s]
Loading 0:  37%|███▋      | 136/363 [00:10<00:05, 45.38it/s]
Loading 0:  39%|███▉      | 141/363 [00:10<00:05, 37.42it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:04, 43.51it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:04, 43.35it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:06, 30.71it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:05, 34.29it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:06, 31.27it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:04, 38.28it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:04, 39.33it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:04, 40.27it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:04, 42.20it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:04, 35.93it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:03, 43.07it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:03, 43.12it/s]
Loading 0:  58%|█████▊    | 212/363 [00:12<00:03, 42.92it/s]
Loading 0:  60%|█████▉    | 217/363 [00:12<00:03, 44.67it/s]
Loading 0:  61%|██████    | 222/363 [00:12<00:03, 37.40it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 44.19it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:02, 44.17it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 43.62it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 41.74it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 41.24it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:03, 32.96it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:03, 33.88it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 38.11it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 40.74it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 35.18it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:01, 42.88it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:01, 43.42it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:01, 43.35it/s]
Loading 0:  82%|████████▏ | 299/363 [00:14<00:01, 41.36it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:01, 40.77it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 44.95it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 44.51it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:00, 44.94it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:00, 42.51it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:00, 41.67it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 45.92it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 45.74it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 45.45it/s]
Loading 0:  97%|█████████▋| 353/363 [00:15<00:00, 43.09it/s]
Loading 0:  99%|█████████▊| 358/363 [00:15<00:00, 31.03it/s]
                                                            
Job sao10k-mn-12b-lyra-v4a1-v27-mkmlizer completed after 94.64s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v27-mkmlizer
Pipeline stage MKMLizer completed in 95.23s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-mn-12b-lyra-v4a1-v27
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v27 to be ready
Inference service sao10k-mn-12b-lyra-v4a1-v27 ready after 130.45321488380432s
Pipeline stage MKMLDeployer completed in 131.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4509093761444092s
Received healthy response to inference request in 1.414302110671997s
Received healthy response to inference request in 1.0100677013397217s
Received healthy response to inference request in 1.4618275165557861s
Received healthy response to inference request in 1.9317467212677002s
5 requests
0 failed requests
5th percentile: 1.0909145832061768
10th percentile: 1.1717614650726318
20th percentile: 1.333455228805542
30th percentile: 1.4216235637664796
40th percentile: 1.4362664699554444
50th percentile: 1.4509093761444092
60th percentile: 1.4552766323089599
70th percentile: 1.4596438884735108
80th percentile: 1.5558113574981691
90th percentile: 1.7437790393829347
95th percentile: 1.8377628803253172
99th percentile: 1.9129499530792236
mean time: 1.453770685195923
Pipeline stage StressChecker completed in 9.02s
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 5.57s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v27 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 1371.97s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v27 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v4a1_v27 status is now torndown due to DeploymentManager action