developer_uid: azuruce
submission_id: sao10k-mn-12b-lyra-v4a1_v33
model_name: sao10k-mn-12b-lyra-v4a1_v33
model_group: Sao10K/MN-12B-Lyra-v4a1
status: torndown
timestamp: 2024-10-24T07:15:51+00:00
num_battles: 7378
num_wins: 3728
celo_rating: 1246.54
family_friendly_score: 0.78
family_friendly_standard_error: 0.005858327406350724
submission_type: basic
model_repo: Sao10K/MN-12B-Lyra-v4a1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: sao10k-mn-12b-lyra-v4a1_v33
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: 0.5052859853618867
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}
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-v33-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v33-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ _____ __ __ ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ /___/ ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ Version: 0.11.12 ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ https://mk1.ai ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ belonging to: ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ Chai Research Corp. ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: Downloaded to shared memory in 33.741s
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpntqhujrd, device:0
sao10k-mn-12b-lyra-v4a1-v33-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
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: quantized model in 35.304s
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 69.045s
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v33
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v33/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v33/config.json
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v33/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v33/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v33/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a1-v33-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:05<17:57, 2.99s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:46, 1.24it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:42, 3.41it/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<00:21, 15.05it/s] Loading 0: 11%|█▏ | 41/363 [00:06<00:15, 21.17it/s] Loading 0: 13%|█▎ | 47/363 [00:06<00:12, 25.02it/s] Loading 0: 14%|█▍ | 52/363 [00:07<00:11, 28.23it/s] Loading 0: 16%|█▌ | 58/363 [00:07<00:11, 25.42it/s] Loading 0: 17%|█▋ | 62/363 [00:07<00:11, 27.26it/s] Loading 0: 18%|█▊ | 67/363 [00:07<00:09, 31.43it/s] Loading 0: 20%|█▉ | 72/363 [00:07<00:08, 33.98it/s] Loading 0: 21%|██ | 77/363 [00:07<00:07, 36.68it/s] Loading 0: 23%|██▎ | 83/363 [00:07<00:07, 37.91it/s] Loading 0: 24%|██▍ | 88/363 [00:08<00:06, 39.60it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:05, 45.31it/s] Loading 0: 28%|██▊ | 100/363 [00:08<00:05, 46.45it/s] Loading 0: 29%|██▉ | 105/363 [00:08<00:06, 37.78it/s] Loading 0: 31%|███ | 112/363 [00:08<00:05, 44.45it/s] Loading 0: 32%|███▏ | 117/363 [00:08<00:05, 44.22it/s] Loading 0: 34%|███▎ | 122/363 [00:08<00:05, 45.49it/s] Loading 0: 35%|███▌ | 128/363 [00:08<00:05, 42.83it/s] Loading 0: 37%|███▋ | 133/363 [00:09<00:05, 42.28it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:04, 47.20it/s] Loading 0: 40%|████ | 146/363 [00:09<00:04, 44.44it/s] Loading 0: 42%|████▏ | 151/363 [00:09<00:05, 40.96it/s] Loading 0: 43%|████▎ | 157/363 [00:09<00:06, 33.34it/s] Loading 0: 44%|████▍ | 161/363 [00:09<00:06, 33.55it/s] Loading 0: 45%|████▌ | 165/363 [00:09<00:05, 34.42it/s] Loading 0: 47%|████▋ | 169/363 [00:10<00:05, 33.61it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:04, 39.86it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:04, 41.56it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:04, 42.47it/s] Loading 0: 52%|█████▏ | 190/363 [00:10<00:03, 43.88it/s] Loading 0: 54%|█████▎ | 195/363 [00:10<00:04, 37.20it/s] Loading 0: 56%|█████▌ | 202/363 [00:10<00:03, 44.53it/s] Loading 0: 57%|█████▋ | 207/363 [00:10<00:03, 43.73it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:03, 42.91it/s] Loading 0: 60%|█████▉ | 217/363 [00:11<00:03, 44.28it/s] Loading 0: 61%|██████ | 222/363 [00:11<00:03, 37.92it/s] Loading 0: 63%|██████▎ | 229/363 [00:11<00:03, 44.02it/s] Loading 0: 64%|██████▍ | 234/363 [00:11<00:02, 43.66it/s] Loading 0: 66%|██████▌ | 239/363 [00:11<00:02, 44.33it/s] Loading 0: 67%|██████▋ | 245/363 [00:11<00:02, 42.61it/s] Loading 0: 69%|██████▉ | 250/363 [00:11<00:02, 41.59it/s] Loading 0: 71%|███████ | 256/363 [00:12<00:03, 32.56it/s] Loading 0: 72%|███████▏ | 260/363 [00:12<00:03, 33.60it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:02, 37.92it/s] Loading 0: 75%|███████▍ | 272/363 [00:12<00:02, 37.33it/s] Loading 0: 76%|███████▌ | 276/363 [00:12<00:02, 36.00it/s] Loading 0: 78%|███████▊ | 283/363 [00:12<00:01, 43.25it/s] Loading 0: 79%|███████▉ | 288/363 [00:12<00:01, 43.24it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:01, 42.81it/s] Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 41.65it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:01, 41.26it/s] Loading 0: 85%|████████▌ | 310/363 [00:13<00:01, 44.42it/s] Loading 0: 87%|████████▋ | 315/363 [00:13<00:01, 43.92it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:00, 44.86it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:00, 43.38it/s] Loading 0: 91%|█████████ | 331/363 [00:13<00:00, 42.93it/s] Loading 0: 93%|█████████▎| 337/363 [00:14<00:00, 46.58it/s] Loading 0: 94%|█████████▍| 342/363 [00:14<00:00, 46.46it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 46.56it/s] Loading 0: 97%|█████████▋| 353/363 [00:14<00:00, 44.02it/s] Loading 0: 99%|█████████▊| 358/363 [00:14<00:00, 30.11it/s]
Job sao10k-mn-12b-lyra-v4a1-v33-mkmlizer completed after 104.55s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v33-mkmlizer
Pipeline stage MKMLizer completed in 105.39s
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-v33
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v33 to be ready
Inference service sao10k-mn-12b-lyra-v4a1-v33 ready after 130.47820210456848s
Pipeline stage MKMLDeployer completed in 131.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3721532821655273s
Received healthy response to inference request in 1.5517582893371582s
Received healthy response to inference request in 1.0594935417175293s
Received healthy response to inference request in 1.5352177619934082s
Received healthy response to inference request in 1.3383920192718506s
5 requests
0 failed requests
5th percentile: 1.1152732372283936
10th percentile: 1.1710529327392578
20th percentile: 1.2826123237609863
30th percentile: 1.345144271850586
40th percentile: 1.3586487770080566
50th percentile: 1.3721532821655273
60th percentile: 1.4373790740966796
70th percentile: 1.502604866027832
80th percentile: 1.5385258674621582
90th percentile: 1.5451420783996581
95th percentile: 1.5484501838684082
99th percentile: 1.5510966682434082
mean time: 1.3714029788970947
Pipeline stage StressChecker completed in 8.22s
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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.52s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v33 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 1541.58s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v33 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v4a1_v33 status is now torndown due to DeploymentManager action