sao10k-mn-12b-lyra-v4a1

submission_id: sao10k-mn-12b-lyra-v4a1_v40

developer_uid: valentin

best_of: 4

celo_rating: 1249.23

display_name: sao10k_best_of_4

family_friendly_score: 0.577

family_friendly_standard_error: 0.006986715966747181

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': 4, '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_4

model_num_parameters: 12772070400.0

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

model_size: 13B

num_battles: 7712

num_wins: 4001

ranking_group: single

status: inactive

submission_type: basic

timestamp: 2024-10-29T10:34:56+00:00

us_pacific_date: 2024-10-29

win_ratio: 0.5188018672199171

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-v40-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v40-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║       /___/                                                         ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: Downloaded to shared memory in 35.702s
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaamyjy58, device:0
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: quantized model in 37.106s
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 72.808s
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v40
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v40/config.json
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v40/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v40/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v40/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v40/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a1-v40-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:24,  3.06s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:54,  1.21it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:45,  3.33it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:11,  4.83it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:46,  7.36it/s]
Loading 0:   7%|▋         | 26/363 [00:06<00:34,  9.77it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:22, 14.47it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:17, 18.91it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:14, 21.86it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:11, 27.20it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:10, 29.37it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:13, 22.95it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:11, 25.43it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:10, 28.82it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:09, 30.88it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:08, 33.90it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:08, 35.22it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 36.30it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:07, 35.58it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 38.21it/s]
Loading 0:  27%|██▋       | 98/363 [00:08<00:07, 35.00it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:07, 36.84it/s]
Loading 0:  29%|██▉       | 107/363 [00:08<00:07, 35.42it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 38.54it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:06, 37.37it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:05, 42.10it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:05, 43.91it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 35.04it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 42.08it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:05, 41.13it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:05, 40.24it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:05, 41.42it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:08, 24.22it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:06, 31.23it/s]
Loading 0:  47%|████▋     | 171/363 [00:10<00:05, 32.08it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:05, 33.64it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:05, 33.53it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 36.96it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:04, 38.00it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 39.79it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:04, 40.48it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:04, 33.39it/s]
Loading 0:  58%|█████▊    | 209/363 [00:11<00:04, 37.03it/s]
Loading 0:  59%|█████▉    | 214/363 [00:11<00:04, 36.63it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:03, 39.59it/s]
Loading 0:  62%|██████▏   | 225/363 [00:12<00:03, 39.92it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 40.78it/s]
Loading 0:  65%|██████▍   | 235/363 [00:12<00:03, 41.47it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 32.89it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 39.96it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 40.28it/s]
Loading 0:  71%|███████   | 257/363 [00:13<00:03, 28.40it/s]
Loading 0:  72%|███████▏  | 261/363 [00:13<00:03, 30.00it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:03, 31.26it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 32.11it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 35.81it/s]
Loading 0:  77%|███████▋  | 278/363 [00:13<00:02, 35.41it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 38.39it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:01, 39.15it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:01, 39.34it/s]
Loading 0:  82%|████████▏ | 298/363 [00:14<00:01, 40.30it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:01, 32.74it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 38.60it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 38.03it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 38.04it/s]
Loading 0:  89%|████████▉ | 323/363 [00:14<00:01, 37.03it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 39.90it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:00, 40.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 41.52it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 42.62it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 33.52it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 28.29it/s]
Loading 0:  99%|█████████▉| 359/363 [00:16<00:00, 29.10it/s]
                                                            
Job sao10k-mn-12b-lyra-v4a1-v40-mkmlizer completed after 104.35s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v40-mkmlizer
Pipeline stage MKMLizer completed in 104.90s
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-v40
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v40 to be ready
Inference service sao10k-mn-12b-lyra-v4a1-v40 ready after 110.43126249313354s
Pipeline stage MKMLDeployer completed in 111.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9369022846221924s
Received healthy response to inference request in 1.973010540008545s
Received healthy response to inference request in 1.8720993995666504s
Received healthy response to inference request in 1.9614934921264648s
Received healthy response to inference request in 1.524092674255371s
5 requests
0 failed requests
5th percentile: 1.593694019317627
10th percentile: 1.663295364379883
20th percentile: 1.8024980545043945
30th percentile: 1.8850599765777587
40th percentile: 1.9109811305999755
50th percentile: 1.9369022846221924
60th percentile: 1.9467387676239014
70th percentile: 1.9565752506256104
80th percentile: 1.963796901702881
90th percentile: 1.9684037208557128
95th percentile: 1.9707071304321289
99th percentile: 1.9725498580932617
mean time: 1.8535196781158447
Pipeline stage StressChecker completed in 10.82s
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 2.79s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v40 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 1991.93s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v40 status is now inactive due to auto deactivation removed underperforming models