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 sanchuanhehe-adjusted-co-9529-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-9529-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ _____ __ __ ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ /___/ ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ Version: 0.10.1 ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ https://mk1.ai ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ belonging to: ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ Chai Research Corp. ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: Downloaded to shared memory in 30.960s
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr26x5gfj, device:0
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: quantized model in 17.953s
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_23_l in 48.913s
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9529-v1
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9529-v1/config.json
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9529-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9529-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9529-v1/tokenizer.model
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9529-v1/tokenizer.json
sanchuanhehe-adjusted-co-9529-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9529-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-9529-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 7/291 [00:00<00:05, 53.13it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:04, 62.66it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:03, 72.33it/s]
Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 72.79it/s]
Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 73.67it/s]
Loading 0: 18%|█▊ | 52/291 [00:00<00:03, 74.65it/s]
Loading 0: 21%|██ | 61/291 [00:00<00:03, 74.13it/s]
Loading 0: 24%|██▍ | 70/291 [00:00<00:03, 70.98it/s]
Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 71.65it/s]
Loading 0: 30%|███ | 88/291 [00:01<00:02, 72.50it/s]
Loading 0: 33%|███▎ | 97/291 [00:01<00:02, 71.94it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:09, 19.98it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:07, 24.40it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:05, 31.23it/s]
Loading 0: 45%|████▍ | 130/291 [00:02<00:04, 37.82it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 42.95it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:02, 48.29it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 52.66it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 57.08it/s]
Loading 0: 59%|█████▉ | 173/291 [00:03<00:02, 58.11it/s]
Loading 0: 62%|██████▏ | 180/291 [00:03<00:01, 58.12it/s]
Loading 0: 64%|██████▍ | 187/291 [00:03<00:01, 58.84it/s]
Loading 0: 67%|██████▋ | 196/291 [00:03<00:01, 65.41it/s]
Loading 0: 70%|███████ | 204/291 [00:04<00:04, 21.22it/s]
Loading 0: 73%|███████▎ | 211/291 [00:04<00:03, 25.74it/s]
Loading 0: 76%|███████▌ | 220/291 [00:05<00:02, 33.34it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 40.74it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 48.76it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 56.24it/s]
Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 62.66it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 66.39it/s]
Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 71.20it/s]
Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 73.06it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.24it/s]
Job sanchuanhehe-adjusted-co-9529-v1-mkmlizer completed after 73.67s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-9529-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-9529-v1
Waiting for inference service sanchuanhehe-adjusted-co-9529-v1 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
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 sanchuanhehe-adjusted-co-2717-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-2717-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ _____ __ __ ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ /___/ ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ Version: 0.10.1 ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ https://mk1.ai ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ belonging to: ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ Chai Research Corp. ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: Downloaded to shared memory in 37.171s
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0c1akv1j, device:0
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: quantized model in 18.099s
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_35_l in 55.271s
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2717-v1
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2717-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2717-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2717-v1/config.json
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2717-v1/tokenizer.model
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2717-v1/tokenizer.json
sanchuanhehe-adjusted-co-2717-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2717-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-2717-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 4/291 [00:00<00:07, 39.01it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 60.52it/s]
Loading 0: 8%|▊ | 22/291 [00:00<00:04, 66.96it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:03, 68.23it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 67.78it/s]
Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 67.96it/s]
Loading 0: 20%|█▉ | 58/291 [00:00<00:03, 68.73it/s]
Loading 0: 23%|██▎ | 67/291 [00:00<00:03, 69.08it/s]
Loading 0: 26%|██▌ | 76/291 [00:01<00:03, 69.70it/s]
Loading 0: 29%|██▉ | 85/291 [00:01<00:03, 67.85it/s]
Loading 0: 32%|███▏ | 94/291 [00:01<00:02, 67.49it/s]
Loading 0: 35%|███▍ | 101/291 [00:02<00:09, 19.07it/s]
Loading 0: 36%|███▋ | 106/291 [00:02<00:08, 21.05it/s]
Loading 0: 40%|███▉ | 115/291 [00:02<00:06, 27.56it/s]
Loading 0: 43%|████▎ | 124/291 [00:02<00:04, 33.75it/s]
Loading 0: 46%|████▌ | 133/291 [00:03<00:03, 40.28it/s]
Loading 0: 49%|████▉ | 142/291 [00:03<00:03, 46.31it/s]
Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 50.53it/s]
Loading 0: 55%|█████▍ | 160/291 [00:03<00:02, 54.20it/s]
Loading 0: 58%|█████▊ | 169/291 [00:03<00:02, 57.97it/s]
Loading 0: 61%|██████ | 178/291 [00:03<00:01, 58.90it/s]
Loading 0: 64%|██████▍ | 187/291 [00:03<00:01, 61.37it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:01, 62.51it/s]
Loading 0: 70%|███████ | 204/291 [00:05<00:04, 21.44it/s]
Loading 0: 73%|███████▎ | 211/291 [00:05<00:03, 25.37it/s]
Loading 0: 76%|███████▌ | 220/291 [00:05<00:02, 32.31it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 38.03it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 44.61it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 51.94it/s]
Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 58.88it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 62.02it/s]
Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 62.03it/s]
Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 67.43it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.73it/s]
Job sanchuanhehe-adjusted-co-2717-v1-mkmlizer completed after 84.64s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-2717-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.03s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.26s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-2717-v1
Waiting for inference service sanchuanhehe-adjusted-co-2717-v1 to be ready
Inference service sanchuanhehe-adjusted-co-9529-v1 ready after 191.5917251110077s
Pipeline stage MKMLDeployer completed in 191.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3684005737304688s
Received healthy response to inference request in 1.8605387210845947s
Received healthy response to inference request in 1.5130705833435059s
Received healthy response to inference request in 0.9213335514068604s
Received healthy response to inference request in 1.402127742767334s
5 requests
0 failed requests
5th percentile: 1.010746955871582
10th percentile: 1.1001603603363037
20th percentile: 1.278987169265747
30th percentile: 1.3751460075378419
40th percentile: 1.388636875152588
50th percentile: 1.402127742767334
60th percentile: 1.4465048789978028
70th percentile: 1.4908820152282716
80th percentile: 1.5825642108917237
90th percentile: 1.7215514659881592
95th percentile: 1.7910450935363769
99th percentile: 1.846639995574951
mean time: 1.4130942344665527
Pipeline stage StressChecker completed in 9.86s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.02s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_9529_v1 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 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-9529-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-9529-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-9529-v1-profiler ready after 190.47712206840515s
Pipeline stage MKMLProfilerDeployer completed in 190.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste8909cb05a9c69734fb1aa7783c767b69-deploc822g:/code/chaiverse_profiler_1726579272 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste8909cb05a9c69734fb1aa7783c767b69-deploc822g --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579272 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726579272/summary.json'
kubectl exec -it sanchuanhehe-adjuste8909cb05a9c69734fb1aa7783c767b69-deploc822g --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579272/summary.json'
Pipeline stage MKMLProfilerRunner completed in 449.39s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-9529-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-9529-v1-profiler
Service sanchuanhehe-adjusted-co-9529-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.00s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_9529_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_9529_v1 status is now torndown due to DeploymentManager action