sao10k-mn-12b-lyra-v4a1

submission_id: sao10k-mn-12b-lyra-v4a1_v38

developer_uid: valentin

best_of: 1

celo_rating: 1211.02

display_name: sao10k_best_of_1

family_friendly_score: 0.589

family_friendly_standard_error: 0.006958146304871722

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}

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}

is_internal_developer: True

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

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

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

model_name: sao10k_best_of_1

model_num_parameters: 12772070400.0

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

model_size: 13B

num_battles: 7799

num_wins: 3577

ranking_group: single

status: inactive

submission_type: basic

timestamp: 2024-10-29T10:34:24+00:00

us_pacific_date: 2024-10-29

win_ratio: 0.45864854468521604

Download Preference Data

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-v38-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v38-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║       /___/                                                         ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: Downloaded to shared memory in 42.026s
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_5_oozis, device:0
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: quantized model in 37.378s
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 79.404s
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v38
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v38/config.json
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v38/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v38/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v38/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v38/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a1-v38-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:09,  3.02s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:50,  1.23it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:07,  2.75it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.29it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  8.01it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 10.98it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:22, 14.41it/s]
Loading 0:  10%|█         | 37/363 [00:06<00:17, 18.34it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:16, 19.59it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:11, 26.31it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:10, 28.84it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:13, 22.55it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:12, 24.83it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:10, 27.32it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:10, 28.57it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 32.93it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 33.19it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 36.92it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 37.79it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 38.92it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:06, 40.51it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:07, 33.66it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 40.77it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:06, 39.56it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:05, 40.38it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:05, 41.51it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 33.98it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 40.70it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:05, 40.44it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:05, 40.21it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:05, 41.29it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:07, 25.84it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:06, 32.66it/s]
Loading 0:  47%|████▋     | 171/363 [00:10<00:05, 34.28it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:05, 36.04it/s]
Loading 0:  50%|████▉     | 181/363 [00:10<00:04, 37.28it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:05, 31.68it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 38.01it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:04, 38.45it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:04, 38.61it/s]
Loading 0:  57%|█████▋    | 208/363 [00:11<00:03, 40.23it/s]
Loading 0:  59%|█████▊    | 213/363 [00:11<00:04, 33.52it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:03, 39.29it/s]
Loading 0:  62%|██████▏   | 225/363 [00:12<00:03, 39.24it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 38.79it/s]
Loading 0:  65%|██████▍   | 235/363 [00:12<00:03, 39.53it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 33.26it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 40.02it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 39.83it/s]
Loading 0:  71%|███████   | 257/363 [00:13<00:03, 28.61it/s]
Loading 0:  72%|███████▏  | 261/363 [00:13<00:03, 30.19it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:03, 31.28it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 31.66it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 34.92it/s]
Loading 0:  77%|███████▋  | 278/363 [00:13<00:02, 34.71it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 37.21it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 36.37it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:01, 38.69it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:01, 37.16it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 38.23it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 37.08it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 38.52it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:01, 37.12it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 39.31it/s]
Loading 0:  89%|████████▉ | 323/363 [00:14<00:01, 37.98it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 39.65it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 38.09it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 40.31it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 40.31it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 39.72it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 38.71it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 26.12it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:00, 28.23it/s]
                                                            
Job sao10k-mn-12b-lyra-v4a1-v38-mkmlizer completed after 104.0s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v38-mkmlizer
Pipeline stage MKMLizer completed in 104.61s
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-v38
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v38 to be ready
Inference service sao10k-mn-12b-lyra-v4a1-v38 ready after 120.41308784484863s
Pipeline stage MKMLDeployer completed in 121.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.1066713333129883s
Received healthy response to inference request in 1.4484198093414307s
Received healthy response to inference request in 1.2976737022399902s
Received healthy response to inference request in 1.4299595355987549s
Received healthy response to inference request in 2.0306150913238525s
5 requests
0 failed requests
5th percentile: 1.1448718070983888
10th percentile: 1.183072280883789
20th percentile: 1.2594732284545898
30th percentile: 1.3241308689117433
40th percentile: 1.377045202255249
50th percentile: 1.4299595355987549
60th percentile: 1.4373436450958252
70th percentile: 1.4447277545928956
80th percentile: 1.5648588657379152
90th percentile: 1.7977369785308839
95th percentile: 1.914176034927368
99th percentile: 2.0073272800445556
mean time: 1.4626678943634033
Pipeline stage StressChecker completed in 8.93s
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 2.32s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v38 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 1756.10s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v38 status is now inactive due to auto deactivation removed underperforming models