sao10k-mn-12b-lyra-v4a1

submission_id: sao10k-mn-12b-lyra-v4a1_v39
developer_uid: valentin
best_of: 2
celo_rating: 1235.17
display_name: sao10k_best_of_1_best_of_2
family_friendly_score: 0.5791999999999999
family_friendly_standard_error: 0.006981795757539746
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': 2, '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_best_of_2
model_num_parameters: 12772070400.0
model_repo: Sao10K/MN-12B-Lyra-v4a1
model_size: 13B
num_battles: 7920
num_wins: 3939
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-10-29T10:34:26+00:00
us_pacific_date: 2024-10-29
win_ratio: 0.4973484848484849
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-v39-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v39-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║       /___/                                                         ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: Downloaded to shared memory in 39.477s
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuobk1jva, device:0
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: quantized model in 37.485s
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 76.962s
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v39
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v39/config.json
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v39/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v39/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v39/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v39-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v39/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a1-v39-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<04:51,  1.23it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:08,  2.74it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.28it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  7.98it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 10.95it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:22, 14.43it/s]
Loading 0:  10%|█         | 37/363 [00:06<00:17, 18.42it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:16, 19.94it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:11, 26.96it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:10, 29.65it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:13, 23.35it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:11, 25.73it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:10, 28.11it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:09, 29.50it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 33.83it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 34.08it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 36.36it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:07, 35.55it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 37.56it/s]
Loading 0:  27%|██▋       | 98/363 [00:08<00:07, 36.76it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 39.64it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:06, 39.87it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:06, 39.64it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 41.36it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:06, 34.49it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:05, 41.34it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:05, 41.32it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 41.49it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 42.12it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 33.81it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:07, 29.10it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:06, 29.87it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:06, 32.54it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 32.67it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:05, 35.78it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:05, 35.91it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 38.30it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:04, 37.26it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 39.54it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:04, 38.23it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 36.68it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 35.45it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 37.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:11<00:04, 36.13it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:03, 38.50it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:03, 36.80it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 39.16it/s]
Loading 0:  64%|██████▍   | 233/363 [00:12<00:03, 37.23it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 39.48it/s]
Loading 0:  67%|██████▋   | 242/363 [00:12<00:03, 37.52it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 39.46it/s]
Loading 0:  69%|██████▉   | 251/363 [00:12<00:02, 37.61it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:03, 26.87it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:03, 27.88it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:03, 31.80it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 32.27it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 35.58it/s]
Loading 0:  77%|███████▋  | 278/363 [00:13<00:02, 35.28it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 37.62it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 35.45it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:01, 37.62it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:01, 36.33it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 38.78it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 37.31it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 39.57it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:01, 37.52it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 39.71it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 39.67it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 39.28it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 37.23it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 39.33it/s]
Loading 0:  94%|█████████▍| 341/363 [00:15<00:00, 37.53it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 39.48it/s]
Loading 0:  96%|█████████▋| 350/363 [00:15<00:00, 37.45it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 27.50it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:00, 28.64it/s]
                                                            
Job sao10k-mn-12b-lyra-v4a1-v39-mkmlizer completed after 104.4s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v39-mkmlizer
Pipeline stage MKMLizer completed in 104.95s
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-v39
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v39 to be ready
Inference service sao10k-mn-12b-lyra-v4a1-v39 ready after 120.42457175254822s
Pipeline stage MKMLDeployer completed in 121.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.21079421043396s
Received healthy response to inference request in 1.1660094261169434s
Received healthy response to inference request in 1.3805432319641113s
Received healthy response to inference request in 1.0996341705322266s
Received healthy response to inference request in 0.9580879211425781s
5 requests
0 failed requests
5th percentile: 0.9863971710205078
10th percentile: 1.0147064208984375
20th percentile: 1.071324920654297
30th percentile: 1.1129092216491698
40th percentile: 1.1394593238830566
50th percentile: 1.1660094261169434
60th percentile: 1.2518229484558105
70th percentile: 1.3376364707946777
80th percentile: 1.5465934276580813
90th percentile: 1.8786938190460205
95th percentile: 2.0447440147399902
99th percentile: 2.177584171295166
mean time: 1.363013792037964
Pipeline stage StressChecker completed in 8.39s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.98s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v39 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 1922.65s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v39 status is now inactive due to auto deactivation removed underperforming models