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 chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer
Waiting for job on chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer to finish
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: Downloaded to shared memory in 46.181s
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4khe69xp, device:0
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: quantized model in 36.129s
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: Processed model ChaiML/qwen14b-dpoexp5-qwendatav1-dpo10k in 82.310s
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/config.json
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/added_tokens.json
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/special_tokens_map.json
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/tokenizer_config.json
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/merges.txt
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/vocab.json
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/tokenizer.json
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/flywheel_model.1.safetensors
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v2/flywheel_model.0.safetensors
chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer:
Loading 0: 0%| | 0/579 [00:00<?, ?it/s]
Loading 0: 3%|▎ | 15/579 [00:00<00:04, 135.90it/s]
Loading 0: 5%|▌ | 29/579 [00:00<00:04, 120.60it/s]
Loading 0: 8%|▊ | 47/579 [00:00<00:03, 144.84it/s]
Loading 0: 11%|█ | 63/579 [00:00<00:03, 147.70it/s]
Loading 0: 14%|█▍ | 81/579 [00:00<00:05, 91.94it/s]
Loading 0: 16%|█▌ | 94/579 [00:00<00:04, 99.22it/s]
Loading 0: 18%|█▊ | 107/579 [00:00<00:04, 105.34it/s]
Loading 0: 21%|██ | 120/579 [00:01<00:04, 110.99it/s]
Loading 0: 24%|██▍ | 138/579 [00:01<00:03, 128.95it/s]
Loading 0: 27%|██▋ | 154/579 [00:01<00:03, 135.43it/s]
Loading 0: 29%|██▉ | 169/579 [00:01<00:03, 129.60it/s]
Loading 0: 32%|███▏ | 186/579 [00:01<00:02, 138.83it/s]
Loading 0: 35%|███▍ | 201/579 [00:01<00:04, 86.15it/s]
Loading 0: 38%|███▊ | 219/579 [00:01<00:03, 102.48it/s]
Loading 0: 40%|████ | 233/579 [00:02<00:03, 106.89it/s]
Loading 0: 44%|████▍ | 255/579 [00:02<00:02, 127.89it/s]
Loading 0: 47%|████▋ | 270/579 [00:02<00:02, 126.54it/s]
Loading 0: 50%|████▉ | 287/579 [00:02<00:02, 136.87it/s]
Loading 0: 52%|█████▏ | 302/579 [00:02<00:02, 100.11it/s]
Loading 0: 54%|█████▍ | 315/579 [00:02<00:02, 105.86it/s]
Loading 0: 57%|█████▋ | 328/579 [00:02<00:02, 110.18it/s]
Loading 0: 59%|█████▉ | 341/579 [00:02<00:02, 113.97it/s]
Loading 0: 63%|██████▎ | 362/579 [00:03<00:01, 138.62it/s]
Loading 0: 65%|██████▌ | 377/579 [00:03<00:01, 127.03it/s]
Loading 0: 69%|██████▊ | 397/579 [00:03<00:01, 145.32it/s]
Loading 0: 71%|███████▏ | 413/579 [00:03<00:01, 91.28it/s]
Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 111.55it/s]
Loading 0: 78%|███████▊ | 450/579 [00:03<00:01, 114.04it/s]
Loading 0: 81%|████████ | 469/579 [00:03<00:00, 130.73it/s]
Loading 0: 84%|████████▍ | 485/579 [00:04<00:00, 124.76it/s]
Loading 0: 87%|████████▋ | 505/579 [00:04<00:00, 142.42it/s]
Loading 0: 88%|████████▊ | 512/579 [00:25<00:00, 142.42it/s]
Loading 0: 89%|████████▊ | 513/579 [00:25<00:27, 2.36it/s]
Loading 0: 90%|████████▉ | 521/579 [00:25<00:20, 2.87it/s]
Loading 0: 92%|█████████▏| 535/579 [00:25<00:10, 4.16it/s]
Loading 0: 96%|█████████▌| 554/579 [00:25<00:03, 6.63it/s]
Loading 0: 98%|█████████▊| 570/579 [00:25<00:00, 9.41it/s]
Job chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer completed after 114.46s with status: succeeded
Stopping job with name chaiml-qwen14b-dpoexp5-42651-v2-mkmlizer
Pipeline stage MKMLizer completed in 114.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen14b-dpoexp5-42651-v2
Waiting for inference service chaiml-qwen14b-dpoexp5-42651-v2 to be ready
Inference service chaiml-qwen14b-dpoexp5-42651-v2 ready after 100.39220666885376s
Pipeline stage MKMLDeployer completed in 101.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3584678173065186s
Received healthy response to inference request in 2.1434974670410156s
Received healthy response to inference request in 2.492135763168335s
Received healthy response to inference request in 2.171950340270996s
Received healthy response to inference request in 2.0290236473083496s
5 requests
0 failed requests
5th percentile: 2.0519184112548827
10th percentile: 2.074813175201416
20th percentile: 2.1206027030944825
30th percentile: 2.1491880416870117
40th percentile: 2.160569190979004
50th percentile: 2.171950340270996
60th percentile: 2.246557331085205
70th percentile: 2.3211643218994142
80th percentile: 2.385201406478882
90th percentile: 2.4386685848236085
95th percentile: 2.4654021739959715
99th percentile: 2.4867890453338624
mean time: 2.239015007019043
Pipeline stage StressChecker completed in 12.46s
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 0.67s
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 0.68s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp5-_42651_v2 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4148.42s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp5-_42651_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen14b-dpoexp5-_42651_v2 status is now torndown due to DeploymentManager action