sao10k-mn-12b-lyra-v4a1

developer_uid: azuruce

submission_id: sao10k-mn-12b-lyra-v4a1_v25

model_name: sao10k-mn-12b-lyra-v4a1_v25

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

status: torndown

timestamp: 2024-10-23T20:08:33+00:00

num_battles: 7127

num_wins: 3811

celo_rating: 1266.66

family_friendly_score: 0.7792

family_friendly_standard_error: 0.005865958745166897

submission_type: basic

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

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

display_name: sao10k-mn-12b-lyra-v4a1_v25

is_internal_developer: True

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

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-23

win_ratio: 0.5347270941490108

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': 8, '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-v25-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v25-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║       /___/                                                         ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: Downloaded to shared memory in 31.307s
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_nfcmn6w, device:0
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: quantized model in 35.336s
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 66.643s
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v25
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v25/config.json
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v25/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v25/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v25/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v25/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a1-v25-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:59,  2.99s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:47,  1.24it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:42,  3.42it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:03,  5.43it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  8.01it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.61it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.92it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:16, 20.08it/s]
Loading 0:  12%|█▏        | 45/363 [00:06<00:13, 23.61it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:11, 27.76it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 30.64it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:12, 24.27it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:09, 31.03it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:08, 33.36it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:08, 35.42it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 41.91it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 41.68it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 41.90it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:05, 45.46it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:05, 43.79it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 43.69it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:05, 41.55it/s]
Loading 0:  34%|███▍      | 124/363 [00:08<00:05, 40.41it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:05, 44.58it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:05, 44.78it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:04, 45.45it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:05, 42.44it/s]
Loading 0:  42%|████▏     | 151/363 [00:09<00:05, 42.12it/s]
Loading 0:  43%|████▎     | 157/363 [00:09<00:06, 32.60it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:06, 32.36it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 35.84it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 36.77it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:04, 41.33it/s]
Loading 0:  50%|████▉     | 181/363 [00:10<00:04, 42.40it/s]
Loading 0:  51%|█████     | 186/363 [00:10<00:05, 34.99it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 43.61it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 42.13it/s]
Loading 0:  56%|█████▋    | 205/363 [00:10<00:03, 40.36it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:03, 44.41it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 44.36it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 44.89it/s]
Loading 0:  63%|██████▎   | 227/363 [00:11<00:03, 42.52it/s]
Loading 0:  64%|██████▍   | 232/363 [00:11<00:03, 40.70it/s]
Loading 0:  66%|██████▌   | 239/363 [00:11<00:02, 45.85it/s]
Loading 0:  67%|██████▋   | 245/363 [00:11<00:02, 44.34it/s]
Loading 0:  69%|██████▉   | 250/363 [00:11<00:02, 42.90it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:03, 34.43it/s]
Loading 0:  72%|███████▏  | 260/363 [00:12<00:02, 35.09it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 38.05it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 39.48it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:02, 41.34it/s]
Loading 0:  77%|███████▋  | 281/363 [00:12<00:02, 40.97it/s]
Loading 0:  79%|███████▉  | 286/363 [00:12<00:01, 41.35it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:01, 44.89it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 45.20it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 45.90it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:01, 43.31it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:01, 41.65it/s]
Loading 0:  88%|████████▊ | 319/363 [00:13<00:00, 44.25it/s]
Loading 0:  89%|████████▉ | 324/363 [00:13<00:00, 44.67it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:00, 44.61it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:00, 41.90it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 40.82it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 45.34it/s]
Loading 0:  97%|█████████▋| 351/363 [00:14<00:00, 45.59it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 31.49it/s]
Loading 0:  99%|█████████▉| 361/363 [00:14<00:00, 35.26it/s]
                                                            
Job sao10k-mn-12b-lyra-v4a1-v25-mkmlizer completed after 94.35s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v25-mkmlizer
Pipeline stage MKMLizer completed in 94.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-mn-12b-lyra-v4a1-v25
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v25 to be ready
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
Inference service sao10k-mn-12b-lyra-v4a1-v25 ready after 130.49151730537415s
Pipeline stage MKMLDeployer completed in 131.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2206313610076904s
Received healthy response to inference request in 1.6278126239776611s
Received healthy response to inference request in 1.6080949306488037s
Received healthy response to inference request in 1.7451798915863037s
Received healthy response to inference request in 2.0419867038726807s
5 requests
0 failed requests
5th percentile: 1.6120384693145753
10th percentile: 1.6159820079803466
20th percentile: 1.6238690853118896
30th percentile: 1.6512860774993896
40th percentile: 1.6982329845428468
50th percentile: 1.7451798915863037
60th percentile: 1.8639026165008545
70th percentile: 1.9826253414154051
80th percentile: 2.0777156352996826
90th percentile: 2.1491734981536865
95th percentile: 2.1849024295806885
99th percentile: 2.21348557472229
mean time: 1.848741102218628
Pipeline stage StressChecker completed in 10.85s
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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.57s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v25 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 1774.47s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v25 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v4a1_v25 status is now torndown due to DeploymentManager action
run pipeline %s