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 zonemercy-vingt-deux-v1-1e5-v13-mkmlizer
Waiting for job on zonemercy-vingt-deux-v1-1e5-v13-mkmlizer to finish
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ _____ __ __ ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ /___/ ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ https://mk1.ai ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ belonging to: ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ Chai Research Corp. ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: ║ ║
zonemercy-vingt-deux-v1-1e5-v13-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: Downloaded to shared memory in 86.360s
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw85p2mfb, device:0
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: quantized model in 50.565s
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: Processed model zonemercy/Vingt-Deux-v1-1e5 in 136.925s
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v13
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v13/config.json
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v13/special_tokens_map.json
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v13/tokenizer_config.json
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v13/tokenizer.json
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v13/flywheel_model.1.safetensors
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v13/flywheel_model.0.safetensors
zonemercy-vingt-deux-v1-1e5-v13-mkmlizer:
Loading 0: 0%| | 0/507 [00:00<?, ?it/s]
Loading 0: 1%| | 5/507 [00:00<00:22, 22.19it/s]
Loading 0: 2%|▏ | 10/507 [00:00<00:15, 31.24it/s]
Loading 0: 3%|▎ | 14/507 [00:00<00:19, 25.88it/s]
Loading 0: 4%|▎ | 19/507 [00:00<00:15, 30.71it/s]
Loading 0: 5%|▍ | 23/507 [00:00<00:18, 26.65it/s]
Loading 0: 6%|▌ | 28/507 [00:00<00:15, 30.26it/s]
Loading 0: 6%|▋ | 32/507 [00:01<00:17, 27.31it/s]
Loading 0: 7%|▋ | 37/507 [00:01<00:15, 31.31it/s]
Loading 0: 8%|▊ | 41/507 [00:01<00:16, 28.17it/s]
Loading 0: 9%|▉ | 46/507 [00:01<00:14, 32.25it/s]
Loading 0: 10%|▉ | 50/507 [00:01<00:15, 28.60it/s]
Loading 0: 11%|█ | 54/507 [00:02<00:25, 17.92it/s]
Loading 0: 11%|█ | 57/507 [00:02<00:24, 18.17it/s]
Loading 0: 12%|█▏ | 61/507 [00:02<00:21, 20.88it/s]
Loading 0: 13%|█▎ | 65/507 [00:02<00:21, 20.25it/s]
Loading 0: 14%|█▍ | 70/507 [00:02<00:17, 24.86it/s]
Loading 0: 14%|█▍ | 73/507 [00:02<00:16, 25.54it/s]
Loading 0: 16%|█▌ | 80/507 [00:03<00:14, 28.72it/s]
Loading 0: 17%|█▋ | 85/507 [00:03<00:12, 32.74it/s]
Loading 0: 18%|█▊ | 89/507 [00:03<00:13, 29.88it/s]
Loading 0: 19%|█▊ | 94/507 [00:03<00:12, 34.05it/s]
Loading 0: 19%|█▉ | 98/507 [00:03<00:13, 30.11it/s]
Loading 0: 20%|██ | 103/507 [00:03<00:11, 33.85it/s]
Loading 0: 21%|██ | 107/507 [00:03<00:13, 29.55it/s]
Loading 0: 22%|██▏ | 112/507 [00:04<00:11, 33.26it/s]
Loading 0: 23%|██▎ | 116/507 [00:04<00:18, 21.31it/s]
Loading 0: 24%|██▍ | 122/507 [00:04<00:15, 24.25it/s]
Loading 0: 25%|██▌ | 127/507 [00:04<00:13, 27.83it/s]
Loading 0: 26%|██▌ | 131/507 [00:04<00:15, 24.44it/s]
Loading 0: 27%|██▋ | 136/507 [00:05<00:13, 27.72it/s]
Loading 0: 28%|██▊ | 140/507 [00:05<00:14, 26.16it/s]
Loading 0: 29%|██▊ | 145/507 [00:05<00:11, 30.60it/s]
Loading 0: 29%|██▉ | 149/507 [00:05<00:12, 28.35it/s]
Loading 0: 30%|███ | 154/507 [00:05<00:10, 32.17it/s]
Loading 0: 31%|███ | 158/507 [00:05<00:12, 28.62it/s]
Loading 0: 32%|███▏ | 163/507 [00:05<00:10, 31.97it/s]
Loading 0: 33%|███▎ | 168/507 [00:06<00:11, 29.78it/s]
Loading 0: 34%|███▍ | 172/507 [00:06<00:17, 18.76it/s]
Loading 0: 35%|███▍ | 176/507 [00:06<00:17, 19.29it/s]
Loading 0: 36%|███▌ | 181/507 [00:06<00:13, 23.35it/s]
Loading 0: 36%|███▋ | 185/507 [00:07<00:14, 22.73it/s]
Loading 0: 37%|███▋ | 190/507 [00:07<00:12, 26.26it/s]
Loading 0: 38%|███▊ | 194/507 [00:07<00:13, 24.01it/s]
Loading 0: 39%|███▉ | 199/507 [00:07<00:11, 27.06it/s]
Loading 0: 40%|████ | 203/507 [00:07<00:12, 24.70it/s]
Loading 0: 41%|████ | 208/507 [00:07<00:10, 29.01it/s]
Loading 0: 42%|████▏ | 212/507 [00:08<00:11, 26.60it/s]
Loading 0: 43%|████▎ | 217/507 [00:08<00:09, 30.77it/s]
Loading 0: 44%|████▎ | 221/507 [00:08<00:10, 28.30it/s]
Loading 0: 44%|████▍ | 225/507 [00:08<00:14, 19.81it/s]
Loading 0: 45%|████▌ | 230/507 [00:08<00:12, 22.20it/s]
Loading 0: 46%|████▋ | 235/507 [00:08<00:10, 26.51it/s]
Loading 0: 47%|████▋ | 239/507 [00:09<00:10, 25.47it/s]
Loading 0: 48%|████▊ | 244/507 [00:09<00:08, 30.23it/s]
Loading 0: 49%|████▉ | 248/507 [00:09<00:09, 28.04it/s]
Loading 0: 50%|████▉ | 253/507 [00:09<00:07, 32.44it/s]
Loading 0: 51%|█████ | 257/507 [00:09<00:08, 29.32it/s]
Loading 0: 52%|█████▏ | 262/507 [00:09<00:07, 33.29it/s]
Loading 0: 52%|█████▏ | 266/507 [00:09<00:08, 29.65it/s]
Loading 0: 53%|█████▎ | 271/507 [00:10<00:07, 31.63it/s]
Loading 0: 54%|█████▍ | 275/507 [00:10<00:08, 27.63it/s]
Loading 0: 55%|█████▌ | 280/507 [00:10<00:07, 32.31it/s]
Loading 0: 56%|█████▌ | 284/507 [00:10<00:09, 23.66it/s]
Loading 0: 57%|█████▋ | 287/507 [00:10<00:10, 20.36it/s]
Loading 0: 58%|█████▊ | 293/507 [00:11<00:09, 23.30it/s]
Loading 0: 59%|█████▉ | 298/507 [00:11<00:07, 27.72it/s]
Loading 0: 60%|█████▉ | 302/507 [00:27<03:47, 1.11s/it]
Loading 0: 61%|██████ | 307/507 [00:27<02:32, 1.31it/s]
Loading 0: 61%|██████▏ | 311/507 [00:27<01:52, 1.74it/s]
Loading 0: 62%|██████▏ | 316/507 [00:28<01:16, 2.51it/s]
Loading 0: 63%|██████▎ | 320/507 [00:28<00:56, 3.30it/s]
Loading 0: 64%|██████▍ | 325/507 [00:28<00:38, 4.71it/s]
Loading 0: 65%|██████▍ | 329/507 [00:28<00:29, 5.98it/s]
Loading 0: 66%|██████▌ | 334/507 [00:28<00:20, 8.31it/s]
Loading 0: 67%|██████▋ | 339/507 [00:28<00:15, 10.97it/s]
Loading 0: 68%|██████▊ | 343/507 [00:29<00:14, 11.00it/s]
Loading 0: 68%|██████▊ | 347/507 [00:29<00:12, 12.73it/s]
Loading 0: 69%|██████▉ | 352/507 [00:29<00:09, 16.67it/s]
Loading 0: 70%|███████ | 356/507 [00:29<00:08, 17.99it/s]
Loading 0: 71%|███████ | 361/507 [00:29<00:06, 22.23it/s]
Loading 0: 72%|███████▏ | 365/507 [00:29<00:06, 22.16it/s]
Loading 0: 73%|███████▎ | 370/507 [00:30<00:05, 26.29it/s]
Loading 0: 74%|███████▍ | 374/507 [00:30<00:05, 25.55it/s]
Loading 0: 75%|███████▍ | 379/507 [00:30<00:04, 30.19it/s]
Loading 0: 76%|███████▌ | 383/507 [00:30<00:04, 27.75it/s]
Loading 0: 77%|███████▋ | 389/507 [00:30<00:03, 32.52it/s]
Loading 0: 78%|███████▊ | 393/507 [00:30<00:03, 31.57it/s]
Loading 0: 78%|███████▊ | 397/507 [00:31<00:04, 22.43it/s]
Loading 0: 79%|███████▉ | 401/507 [00:31<00:04, 21.67it/s]
Loading 0: 80%|████████ | 406/507 [00:31<00:03, 26.28it/s]
Loading 0: 81%|████████ | 410/507 [00:31<00:03, 25.16it/s]
Loading 0: 82%|████████▏ | 415/507 [00:31<00:03, 29.51it/s]
Loading 0: 83%|████████▎ | 419/507 [00:31<00:03, 27.48it/s]
Loading 0: 84%|████████▎ | 424/507 [00:31<00:02, 31.17it/s]
Loading 0: 84%|████████▍ | 428/507 [00:32<00:02, 27.83it/s]
Loading 0: 85%|████████▌ | 433/507 [00:32<00:02, 30.93it/s]
Loading 0: 86%|████████▌ | 437/507 [00:32<00:02, 25.62it/s]
Loading 0: 87%|████████▋ | 442/507 [00:32<00:02, 29.35it/s]
Loading 0: 88%|████████▊ | 446/507 [00:32<00:02, 25.64it/s]
Loading 0: 89%|████████▉ | 451/507 [00:32<00:01, 28.56it/s]
Loading 0: 90%|████████▉ | 455/507 [00:35<00:10, 5.17it/s]
Loading 0: 91%|█████████ | 459/507 [00:35<00:07, 6.54it/s]
Loading 0: 92%|█████████▏| 465/507 [00:35<00:04, 9.23it/s]
Loading 0: 93%|█████████▎| 470/507 [00:35<00:03, 12.20it/s]
Loading 0: 93%|█████████▎| 474/507 [00:36<00:02, 13.66it/s]
Loading 0: 94%|█████████▍| 479/507 [00:36<00:01, 17.20it/s]
Loading 0: 95%|█████████▌| 483/507 [00:36<00:01, 18.76it/s]
Loading 0: 96%|█████████▋| 488/507 [00:36<00:00, 23.34it/s]
Loading 0: 97%|█████████▋| 492/507 [00:36<00:00, 23.76it/s]
Loading 0: 98%|█████████▊| 499/507 [00:36<00:00, 30.84it/s]
Loading 0: 99%|█████████▉| 503/507 [00:36<00:00, 31.09it/s]
Job zonemercy-vingt-deux-v1-1e5-v13-mkmlizer completed after 266.81s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v1-1e5-v13-mkmlizer
Pipeline stage MKMLizer completed in 269.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v1-1e5-v13
Waiting for inference service zonemercy-vingt-deux-v1-1e5-v13 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
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
Failed to get response for submission zonemercy-lexical-nemov8_5966_v2: ('http://zonemercy-lexical-nemov8-5966-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:58782->127.0.0.1:8080: read: connection reset by peer\n')
Inference service zonemercy-vingt-deux-v1-1e5-v13 ready after 212.3195927143097s
Pipeline stage MKMLDeployer completed in 212.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9147017002105713s
Received healthy response to inference request in 3.528937578201294s
Received healthy response to inference request in 2.755174398422241s
Received healthy response to inference request in 2.543273448944092s
Received healthy response to inference request in 3.752454996109009s
5 requests
0 failed requests
5th percentile: 2.5856536388397218
10th percentile: 2.6280338287353517
20th percentile: 2.7127942085266112
30th percentile: 2.9099270343780517
40th percentile: 3.219432306289673
50th percentile: 3.528937578201294
60th percentile: 3.61834454536438
70th percentile: 3.707751512527466
80th percentile: 3.7849043369293214
90th percentile: 3.849803018569946
95th percentile: 3.8822523593902587
99th percentile: 3.9082118320465087
mean time: 3.2989084243774416
%s, retrying in %s seconds...
Received healthy response to inference request in 2.9828412532806396s
Received healthy response to inference request in 2.9320871829986572s
Received healthy response to inference request in 4.336303949356079s
Received healthy response to inference request in 3.255922794342041s
Received healthy response to inference request in 2.8754942417144775s
5 requests
0 failed requests
5th percentile: 2.8868128299713134
10th percentile: 2.8981314182281492
20th percentile: 2.9207685947418214
30th percentile: 2.9422379970550536
40th percentile: 2.962539625167847
50th percentile: 2.9828412532806396
60th percentile: 3.0920738697052004
70th percentile: 3.2013064861297607
80th percentile: 3.4719990253448487
90th percentile: 3.904151487350464
95th percentile: 4.120227718353271
99th percentile: 4.293088703155518
mean time: 3.276529884338379
Pipeline stage StressChecker completed in 35.19s
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 5.20s
Shutdown handler de-registered
zonemercy-vingt-deux-v1-1e5_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v1-1e5-v13-profiler
Waiting for inference service zonemercy-vingt-deux-v1-1e5-v13-profiler to be ready
Inference service zonemercy-vingt-deux-v1-1e5-v13-profiler ready after 220.49314641952515s
Pipeline stage MKMLProfilerDeployer completed in 220.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deuxea0b18d21a1d78de5504c64a32112c3b-deplop6887:/code/chaiverse_profiler_1727217964 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxea0b18d21a1d78de5504c64a32112c3b-deplop6887 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727217964 && python profiles.py profile --best_of_n 8 --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_1727217964/summary.json'
kubectl exec -it zonemercy-vingt-deuxea0b18d21a1d78de5504c64a32112c3b-deplop6887 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727217964/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1571.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v1-1e5-v13-profiler is running
Tearing down inference service zonemercy-vingt-deux-v1-1e5-v13-profiler
Service zonemercy-vingt-deux-v1-1e5-v13-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.05s
Shutdown handler de-registered
zonemercy-vingt-deux-v1-1e5_v13 status is now inactive due to auto deactivation removed underperforming models
Shutdown handler de-registered
Shutdown handler de-registered
Shutdown handler de-registered
zonemercy-vingt-deux-v1-1e5_v14 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
zonemercy-vingt-deux-v1-_8973_v2 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-v1-1e5_v13 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-gfv_3432_v2 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-v2-1e5_v16 status is now torndown due to DeploymentManager action