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 mistralai-mistral-nemo-9330-v80-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v80-mkmlizer to finish
mistralai-mistral-nemo-9330-v80-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ _____ __ __ ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ /___/ ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ Version: 0.10.1 ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ https://mk1.ai ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ The license key for the current software has been verified as ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ belonging to: ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ Chai Research Corp. ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v80-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
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
mistralai-mistral-nemo-9330-v80-mkmlizer: Downloaded to shared memory in 48.924s
mistralai-mistral-nemo-9330-v80-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfyb38cpt, device:0
mistralai-mistral-nemo-9330-v80-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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', '')
mistralai-mistral-nemo-9330-v80-mkmlizer: quantized model in 36.892s
mistralai-mistral-nemo-9330-v80-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 85.816s
mistralai-mistral-nemo-9330-v80-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v80-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v80-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v80
mistralai-mistral-nemo-9330-v80-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v80/special_tokens_map.json
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', '')
mistralai-mistral-nemo-9330-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v80/tokenizer.json
mistralai-mistral-nemo-9330-v80-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v80/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v80-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:10, 33.01it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:06, 54.38it/s]
Loading 0: 5%|▌ | 19/363 [00:00<00:06, 50.66it/s]
Loading 0: 7%|▋ | 25/363 [00:00<00:06, 51.59it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:06, 53.74it/s]
Loading 0: 10%|█ | 37/363 [00:00<00:06, 50.19it/s]
Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 50.34it/s]
Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 52.77it/s]
Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 50.42it/s]
Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 37.53it/s]
Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 37.64it/s]
Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 41.11it/s]
Loading 0: 21%|██ | 77/363 [00:01<00:07, 40.48it/s]
Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 35.59it/s]
Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 43.99it/s]
Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.39it/s]
Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 43.06it/s]
Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.52it/s]
Loading 0: 31%|███▏ | 114/363 [00:02<00:06, 41.24it/s]
Loading 0: 33%|███▎ | 119/363 [00:02<00:06, 38.32it/s]
Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 42.78it/s]
Loading 0: 36%|███▌ | 130/363 [00:02<00:05, 43.75it/s]
Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 43.01it/s]
Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 43.21it/s]
Loading 0: 40%|███▉ | 145/363 [00:03<00:08, 25.81it/s]
Loading 0: 41%|████ | 149/363 [00:03<00:08, 26.46it/s]
Loading 0: 43%|████▎ | 156/363 [00:03<00:06, 33.62it/s]
Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 34.42it/s]
Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 34.17it/s]
Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 34.98it/s]
Loading 0: 48%|████▊ | 174/363 [00:04<00:05, 37.54it/s]
Loading 0: 49%|████▉ | 178/363 [00:04<00:05, 35.44it/s]
Loading 0: 50%|█████ | 183/363 [00:04<00:04, 37.47it/s]
Loading 0: 52%|█████▏ | 187/363 [00:04<00:04, 35.80it/s]
Loading 0: 53%|█████▎ | 192/363 [00:04<00:04, 39.10it/s]
Loading 0: 54%|█████▍ | 197/363 [00:04<00:04, 39.74it/s]
Loading 0: 56%|█████▌ | 202/363 [00:05<00:03, 40.28it/s]
Loading 0: 57%|█████▋ | 207/363 [00:05<00:03, 42.19it/s]
Loading 0: 58%|█████▊ | 212/363 [00:05<00:04, 36.34it/s]
Loading 0: 61%|██████ | 220/363 [00:05<00:03, 46.18it/s]
Loading 0: 62%|██████▏ | 225/363 [00:05<00:04, 30.55it/s]
Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 32.67it/s]
Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 40.17it/s]
Loading 0: 67%|██████▋ | 242/363 [00:06<00:02, 40.64it/s]
Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 41.96it/s]
Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 42.65it/s]
Loading 0: 71%|███████ | 257/363 [00:06<00:03, 33.73it/s]
Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 36.06it/s]
Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 36.57it/s]
Loading 0: 75%|███████▌ | 273/363 [00:06<00:02, 41.44it/s]
Loading 0: 77%|███████▋ | 278/363 [00:06<00:02, 42.35it/s]
Loading 0: 78%|███████▊ | 283/363 [00:07<00:01, 43.96it/s]
Loading 0: 80%|███████▉ | 289/363 [00:07<00:01, 42.05it/s]
Loading 0: 81%|████████ | 294/363 [00:07<00:01, 37.37it/s]
Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 39.74it/s]
Loading 0: 84%|████████▎ | 304/363 [00:14<00:24, 2.37it/s]
Loading 0: 85%|████████▍ | 307/363 [00:14<00:19, 2.89it/s]
Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.12it/s]
Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.89it/s]
Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.29it/s]
Loading 0: 91%|█████████ | 331/363 [00:15<00:02, 11.72it/s]
Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.49it/s]
Loading 0: 94%|█████████▍| 343/363 [00:15<00:01, 19.94it/s]
Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 21.47it/s]
Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.49it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.35it/s]
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job mistralai-mistral-nemo-9330-v80-mkmlizer completed after 115.44s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v80-mkmlizer
Pipeline stage MKMLizer completed in 116.56s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.25s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v80
Waiting for inference service mistralai-mistral-nemo-9330-v80 to be ready
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', '')
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', '')
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', '')
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', '')
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', '')
Inference service mistralai-mistral-nemo-9330-v80 ready after 172.12739539146423s
Pipeline stage MKMLDeployer completed in 172.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9077792167663574s
Received healthy response to inference request in 1.0007109642028809s
Received healthy response to inference request in 1.443934679031372s
Received healthy response to inference request in 0.6814961433410645s
Received healthy response to inference request in 0.8573176860809326s
5 requests
0 failed requests
5th percentile: 0.716660451889038
10th percentile: 0.7518247604370117
20th percentile: 0.822153377532959
30th percentile: 0.8859963417053223
40th percentile: 0.9433536529541016
50th percentile: 1.0007109642028809
60th percentile: 1.1780004501342773
70th percentile: 1.3552899360656738
80th percentile: 1.5367035865783691
90th percentile: 1.7222414016723633
95th percentile: 1.8150103092193604
99th percentile: 1.889225435256958
mean time: 1.1782477378845215
Pipeline stage StressChecker completed in 8.30s
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 5.60s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v80 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-nemo-9330-v80-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v80-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v80-profiler ready after 180.75355625152588s
Pipeline stage MKMLProfilerDeployer completed in 181.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-ne10bded0c43e309f3b7bc760312549199-deplo6wl2x:/code/chaiverse_profiler_1726554867 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-ne10bded0c43e309f3b7bc760312549199-deplo6wl2x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726554867 && python profiles.py profile --best_of_n 4 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726554867/summary.json'
kubectl exec -it mistralai-mistral-ne10bded0c43e309f3b7bc760312549199-deplo6wl2x --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726554867/summary.json'
Pipeline stage MKMLProfilerRunner completed in 968.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v80-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v80-profiler
Service mistralai-mistral-nemo-9330-v80-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.82s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v80 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v80 status is now torndown due to DeploymentManager action