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-v2a1-v13-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v2a1-v13-mkmlizer to finish
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: Downloaded to shared memory in 26.004s
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfwl7yq33, device:0
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: quantized model in 37.361s
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v2a1 in 63.366s
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v13
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v13/special_tokens_map.json
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v13/config.json
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v13/tokenizer_config.json
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v13/tokenizer.json
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v13/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v2a1-v13-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:06<18:36, 3.09s/it]
Loading 0: 2%|▏ | 6/363 [00:06<04:57, 1.20it/s]
Loading 0: 4%|▎ | 13/363 [00:06<01:46, 3.30it/s]
Loading 0: 5%|▍ | 17/363 [00:06<01:11, 4.82it/s]
Loading 0: 6%|▋ | 23/363 [00:06<00:43, 7.88it/s]
Loading 0: 8%|▊ | 29/363 [00:06<00:29, 11.36it/s]
Loading 0: 9%|▉ | 34/363 [00:06<00:22, 14.41it/s]
Loading 0: 11%|█ | 40/363 [00:07<00:16, 19.34it/s]
Loading 0: 12%|█▏ | 45/363 [00:07<00:14, 22.52it/s]
Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 25.87it/s]
Loading 0: 15%|█▌ | 55/363 [00:07<00:10, 29.22it/s]
Loading 0: 17%|█▋ | 60/363 [00:07<00:15, 19.83it/s]
Loading 0: 18%|█▊ | 67/363 [00:08<00:11, 26.53it/s]
Loading 0: 20%|█▉ | 72/363 [00:08<00:09, 29.28it/s]
Loading 0: 21%|██ | 77/363 [00:08<00:08, 32.39it/s]
Loading 0: 23%|██▎ | 82/363 [00:08<00:07, 35.21it/s]
Loading 0: 24%|██▍ | 87/363 [00:08<00:08, 31.66it/s]
Loading 0: 26%|██▌ | 94/363 [00:08<00:06, 39.24it/s]
Loading 0: 27%|██▋ | 99/363 [00:08<00:06, 39.75it/s]
Loading 0: 29%|██▊ | 104/363 [00:08<00:06, 40.18it/s]
Loading 0: 30%|███ | 110/363 [00:09<00:06, 40.78it/s]
Loading 0: 32%|███▏ | 115/363 [00:09<00:06, 39.17it/s]
Loading 0: 33%|███▎ | 121/363 [00:09<00:05, 43.22it/s]
Loading 0: 35%|███▍ | 126/363 [00:09<00:05, 42.07it/s]
Loading 0: 36%|███▌ | 131/363 [00:09<00:05, 40.56it/s]
Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 39.92it/s]
Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 38.86it/s]
Loading 0: 41%|████ | 148/363 [00:09<00:04, 43.12it/s]
Loading 0: 42%|████▏ | 153/363 [00:10<00:04, 43.39it/s]
Loading 0: 44%|████▎ | 158/363 [00:10<00:07, 28.38it/s]
Loading 0: 45%|████▍ | 162/363 [00:10<00:06, 30.05it/s]
Loading 0: 46%|████▌ | 167/363 [00:10<00:05, 33.18it/s]
Loading 0: 48%|████▊ | 173/363 [00:10<00:05, 35.00it/s]
Loading 0: 49%|████▉ | 177/363 [00:10<00:05, 33.65it/s]
Loading 0: 51%|█████ | 184/363 [00:11<00:04, 41.63it/s]
Loading 0: 52%|█████▏ | 189/363 [00:11<00:04, 41.99it/s]
Loading 0: 53%|█████▎ | 194/363 [00:11<00:03, 43.03it/s]
Loading 0: 55%|█████▌ | 200/363 [00:11<00:03, 41.97it/s]
Loading 0: 56%|█████▋ | 205/363 [00:11<00:04, 38.34it/s]
Loading 0: 58%|█████▊ | 211/363 [00:11<00:03, 42.35it/s]
Loading 0: 60%|█████▉ | 216/363 [00:11<00:03, 42.18it/s]
Loading 0: 61%|██████ | 221/363 [00:11<00:03, 42.87it/s]
Loading 0: 62%|██████▏ | 226/363 [00:12<00:03, 44.14it/s]
Loading 0: 64%|██████▎ | 231/363 [00:12<00:03, 37.35it/s]
Loading 0: 66%|██████▌ | 238/363 [00:12<00:02, 44.91it/s]
Loading 0: 67%|██████▋ | 243/363 [00:12<00:02, 44.82it/s]
Loading 0: 68%|██████▊ | 248/363 [00:12<00:02, 43.77it/s]
Loading 0: 70%|██████▉ | 254/363 [00:12<00:02, 40.45it/s]
Loading 0: 71%|███████▏ | 259/363 [00:13<00:03, 26.47it/s]
Loading 0: 73%|███████▎ | 265/363 [00:13<00:03, 31.72it/s]
Loading 0: 74%|███████▍ | 269/363 [00:13<00:02, 31.79it/s]
Loading 0: 75%|███████▌ | 274/363 [00:13<00:02, 34.74it/s]
Loading 0: 77%|███████▋ | 278/363 [00:13<00:02, 34.07it/s]
Loading 0: 78%|███████▊ | 283/363 [00:13<00:02, 37.26it/s]
Loading 0: 79%|███████▉ | 288/363 [00:13<00:02, 37.40it/s]
Loading 0: 81%|████████ | 293/363 [00:13<00:01, 39.36it/s]
Loading 0: 82%|████████▏ | 299/363 [00:14<00:01, 39.77it/s]
Loading 0: 84%|████████▎ | 304/363 [00:14<00:01, 39.45it/s]
Loading 0: 85%|████████▌ | 310/363 [00:14<00:01, 42.14it/s]
Loading 0: 87%|████████▋ | 315/363 [00:14<00:01, 42.60it/s]
Loading 0: 88%|████████▊ | 320/363 [00:14<00:00, 43.53it/s]
Loading 0: 90%|████████▉ | 325/363 [00:14<00:00, 44.25it/s]
Loading 0: 91%|█████████ | 330/363 [00:14<00:00, 38.00it/s]
Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 45.76it/s]
Loading 0: 94%|█████████▍| 343/363 [00:15<00:00, 46.52it/s]
Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 36.65it/s]
Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 29.81it/s]
Loading 0: 99%|█████████▉| 359/363 [00:15<00:00, 30.42it/s]
Job sao10k-mn-12b-lyra-v2a1-v13-mkmlizer completed after 93.17s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v2a1-v13-mkmlizer
Pipeline stage MKMLizer completed in 93.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-mn-12b-lyra-v2a1-v13
Waiting for inference service sao10k-mn-12b-lyra-v2a1-v13 to be ready
Inference service sao10k-mn-12b-lyra-v2a1-v13 ready after 160.83285546302795s
Pipeline stage MKMLDeployer completed in 161.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1582558155059814s
Received healthy response to inference request in 1.9333233833312988s
Received healthy response to inference request in 1.5505383014678955s
Received healthy response to inference request in 1.6661186218261719s
Received healthy response to inference request in 1.7772748470306396s
5 requests
0 failed requests
5th percentile: 1.5736543655395507
10th percentile: 1.596770429611206
20th percentile: 1.6430025577545166
30th percentile: 1.6883498668670653
40th percentile: 1.7328123569488525
50th percentile: 1.7772748470306396
60th percentile: 1.8396942615509033
70th percentile: 1.902113676071167
80th percentile: 1.9783098697662354
90th percentile: 2.0682828426361084
95th percentile: 2.113269329071045
99th percentile: 2.149258518218994
mean time: 1.8171021938323975
Pipeline stage StressChecker completed in 10.18s
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 0.65s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.62s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v2a1_v13 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-mn-12b-lyra-v2a1-v13-profiler
Waiting for inference service sao10k-mn-12b-lyra-v2a1-v13-profiler to be ready
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 3069.29s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v2a1_v13 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v2a1_v13 status is now torndown due to DeploymentManager action