Running pipeline stage MKMLizer
Starting job with name sao10k-mn-12b-lyra-v2a2-v1-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v2a2-v1-mkmlizer to finish
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ _____ __ __ ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ /___/ ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ Version: 0.9.11 ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ belonging to: ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: Downloaded to shared memory in 61.707s
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi7nqvv0i, device:0
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a2-v1
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a2-v1/config.json
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a2-v1/special_tokens_map.json
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a2-v1/tokenizer_config.json
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a2-v1/tokenizer.json
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a2-v1/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v2a2-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:06<18:03, 3.00s/it]
Loading 0: 2%|▏ | 6/363 [00:06<04:47, 1.24it/s]
Loading 0: 4%|▎ | 13/363 [00:06<01:42, 3.41it/s]
Loading 0: 5%|▍ | 18/363 [00:06<01:03, 5.41it/s]
Loading 0: 6%|▋ | 23/363 [00:06<00:42, 7.97it/s]
Loading 0: 8%|▊ | 29/363 [00:06<00:29, 11.42it/s]
Loading 0: 9%|▉ | 34/363 [00:06<00:22, 14.68it/s]
Loading 0: 11%|█ | 40/363 [00:06<00:16, 19.80it/s]
Loading 0: 12%|█▏ | 45/363 [00:06<00:13, 23.56it/s]
Loading 0: 14%|█▍ | 50/363 [00:07<00:11, 27.46it/s]
Loading 0: 15%|█▌ | 55/363 [00:07<00:09, 31.70it/s]
Loading 0: 17%|█▋ | 60/363 [00:07<00:14, 21.56it/s]
Loading 0: 18%|█▊ | 67/363 [00:07<00:10, 29.07it/s]
Loading 0: 20%|█▉ | 72/363 [00:07<00:09, 32.12it/s]
Loading 0: 21%|██ | 77/363 [00:07<00:08, 35.18it/s]
Loading 0: 23%|██▎ | 83/363 [00:08<00:07, 35.96it/s]
Loading 0: 24%|██▍ | 88/363 [00:08<00:07, 36.80it/s]
Loading 0: 26%|██▌ | 95/363 [00:08<00:06, 42.76it/s]
Loading 0: 28%|██▊ | 101/363 [00:08<00:06, 41.21it/s]
Loading 0: 29%|██▉ | 106/363 [00:08<00:06, 40.69it/s]
Loading 0: 31%|███ | 112/363 [00:08<00:05, 44.59it/s]
Loading 0: 32%|███▏ | 117/363 [00:08<00:05, 44.64it/s]
Loading 0: 34%|███▎ | 122/363 [00:08<00:05, 45.14it/s]
Loading 0: 35%|███▍ | 127/363 [00:09<00:05, 45.63it/s]
Loading 0: 36%|███▋ | 132/363 [00:09<00:06, 36.01it/s]
Loading 0: 38%|███▊ | 139/363 [00:09<00:05, 43.06it/s]
Loading 0: 40%|███▉ | 144/363 [00:09<00:05, 42.64it/s]
Loading 0: 41%|████ | 149/363 [00:09<00:05, 42.16it/s]
Loading 0: 43%|████▎ | 155/363 [00:09<00:05, 40.88it/s]
Loading 0: 44%|████▍ | 160/363 [00:10<00:07, 28.78it/s]
Loading 0: 46%|████▌ | 166/363 [00:10<00:05, 34.36it/s]
Loading 0: 47%|████▋ | 171/363 [00:10<00:05, 36.66it/s]
Loading 0: 48%|████▊ | 176/363 [00:10<00:04, 38.47it/s]
Loading 0: 50%|████▉ | 181/363 [00:10<00:04, 41.09it/s]
Loading 0: 51%|█████ | 186/363 [00:10<00:04, 35.46it/s]
Loading 0: 53%|█████▎ | 193/363 [00:10<00:03, 42.69it/s]
Loading 0: 55%|█████▍ | 198/363 [00:10<00:03, 42.61it/s]
Loading 0: 56%|█████▌ | 203/363 [00:11<00:03, 42.81it/s]
Loading 0: 58%|█████▊ | 209/363 [00:11<00:03, 40.96it/s]
Loading 0: 59%|█████▉ | 214/363 [00:11<00:03, 40.18it/s]
Loading 0: 61%|██████ | 220/363 [00:11<00:03, 43.87it/s]
Loading 0: 62%|██████▏ | 225/363 [00:11<00:03, 43.63it/s]
Loading 0: 63%|██████▎ | 230/363 [00:11<00:03, 43.62it/s]
Loading 0: 65%|██████▍ | 235/363 [00:11<00:02, 44.36it/s]
Loading 0: 66%|██████▌ | 240/363 [00:11<00:03, 36.77it/s]
Loading 0: 68%|██████▊ | 247/363 [00:12<00:02, 43.80it/s]
Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 43.22it/s]
Loading 0: 71%|███████ | 257/363 [00:12<00:03, 29.39it/s]
Loading 0: 72%|███████▏ | 262/363 [00:12<00:03, 33.20it/s]
Loading 0: 74%|███████▎ | 267/363 [00:12<00:03, 30.49it/s]
Loading 0: 75%|███████▌ | 274/363 [00:12<00:02, 37.29it/s]
Loading 0: 77%|███████▋ | 279/363 [00:13<00:02, 38.20it/s]
Loading 0: 78%|███████▊ | 284/363 [00:13<00:02, 38.97it/s]
Loading 0: 80%|███████▉ | 289/363 [00:13<00:01, 41.44it/s]
Loading 0: 81%|████████ | 294/363 [00:13<00:01, 34.96it/s]
Loading 0: 83%|████████▎ | 301/363 [00:13<00:01, 41.32it/s]
Loading 0: 84%|████████▍ | 306/363 [00:13<00:01, 41.51it/s]
Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 40.02it/s]
Loading 0: 87%|████████▋ | 316/363 [00:13<00:01, 40.83it/s]
Loading 0: 88%|████████▊ | 321/363 [00:14<00:01, 33.83it/s]
Loading 0: 90%|█████████ | 328/363 [00:14<00:00, 39.97it/s]
Loading 0: 92%|█████████▏| 333/363 [00:14<00:00, 40.73it/s]
Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 41.13it/s]
Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 43.13it/s]
Loading 0: 96%|█████████▌| 348/363 [00:14<00:00, 36.09it/s]
Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 31.39it/s]
Loading 0: 99%|█████████▉| 359/363 [00:15<00:00, 32.26it/s]
Job sao10k-mn-12b-lyra-v2a2-v1-mkmlizer completed after 126.34s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v2a2-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-mn-12b-lyra-v2a2-v1
Waiting for inference service sao10k-mn-12b-lyra-v2a2-v1 to be ready
Inference service sao10k-mn-12b-lyra-v2a2-v1 ready after 252.0442328453064s
Pipeline stage ISVCDeployer completed in 253.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1066339015960693s
Received healthy response to inference request in 2.069040060043335s
Received healthy response to inference request in 1.6971404552459717s
Received healthy response to inference request in 1.8993711471557617s
Received healthy response to inference request in 1.6814262866973877s
5 requests
0 failed requests
5th percentile: 1.6845691204071045
10th percentile: 1.6877119541168213
20th percentile: 1.6939976215362549
30th percentile: 1.7375865936279298
40th percentile: 1.8184788703918457
50th percentile: 1.8993711471557617
60th percentile: 1.967238712310791
70th percentile: 2.0351062774658204
80th percentile: 2.076558828353882
90th percentile: 2.0915963649749756
95th percentile: 2.0991151332855225
99th percentile: 2.10513014793396
mean time: 1.8907223701477052
Pipeline stage StressChecker completed in 10.11s
sao10k-mn-12b-lyra-v2a2_v1 status is now deployed due to DeploymentManager action
sao10k-mn-12b-lyra-v2a2_v1 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v2a2_v1 status is now torndown due to DeploymentManager action