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-nemo-chai-5merge-ties-v8-mkmlizer
Waiting for job on chaiml-nemo-chai-5merge-ties-v8-mkmlizer to finish
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ /___/ ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ belonging to: ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ║ ║
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: Downloaded to shared memory in 30.382s
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppoz7e3gz, device:0
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: quantized model in 36.769s
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: Processed model ChaiML/nemo-chai-5merge-ties in 67.152s
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-chai-5merge-ties-v8
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-chai-5merge-ties-v8/config.json
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-chai-5merge-ties-v8/special_tokens_map.json
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-chai-5merge-ties-v8/tokenizer_config.json
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-chai-5merge-ties-v8/tokenizer.json
chaiml-nemo-chai-5merge-ties-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-chai-5merge-ties-v8/flywheel_model.0.safetensors
chaiml-nemo-chai-5merge-ties-v8-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:06<18:34, 3.09s/it]
Loading 0: 2%|▏ | 6/363 [00:06<04:58, 1.20it/s]
Loading 0: 4%|▎ | 13/363 [00:06<01:46, 3.29it/s]
Loading 0: 5%|▍ | 17/363 [00:06<01:11, 4.81it/s]
Loading 0: 6%|▋ | 23/363 [00:06<00:43, 7.86it/s]
Loading 0: 8%|▊ | 28/363 [00:06<00:30, 10.96it/s]
Loading 0: 9%|▉ | 33/363 [00:06<00:23, 13.80it/s]
Loading 0: 11%|█ | 40/363 [00:07<00:19, 16.54it/s]
Loading 0: 12%|█▏ | 44/363 [00:07<00:16, 18.88it/s]
Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 24.27it/s]
Loading 0: 15%|█▌ | 56/363 [00:07<00:10, 28.22it/s]
Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 30.53it/s]
Loading 0: 18%|█▊ | 67/363 [00:07<00:08, 36.27it/s]
Loading 0: 20%|█▉ | 72/363 [00:07<00:07, 38.47it/s]
Loading 0: 21%|██ | 77/363 [00:08<00:07, 40.44it/s]
Loading 0: 23%|██▎ | 83/363 [00:08<00:06, 40.14it/s]
Loading 0: 24%|██▍ | 88/363 [00:08<00:06, 39.90it/s]
Loading 0: 26%|██▌ | 94/363 [00:08<00:06, 44.07it/s]
Loading 0: 27%|██▋ | 99/363 [00:08<00:06, 42.77it/s]
Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 43.80it/s]
Loading 0: 30%|███ | 109/363 [00:08<00:05, 45.04it/s]
Loading 0: 31%|███▏ | 114/363 [00:08<00:06, 37.11it/s]
Loading 0: 33%|███▎ | 121/363 [00:09<00:07, 30.49it/s]
Loading 0: 34%|███▍ | 125/363 [00:09<00:07, 30.78it/s]
Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 35.71it/s]
Loading 0: 38%|███▊ | 137/363 [00:09<00:06, 37.49it/s]
Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 37.90it/s]
Loading 0: 41%|████ | 148/363 [00:09<00:05, 42.92it/s]
Loading 0: 42%|████▏ | 153/363 [00:10<00:04, 43.17it/s]
Loading 0: 44%|████▎ | 158/363 [00:10<00:04, 43.94it/s]
Loading 0: 45%|████▌ | 164/363 [00:10<00:04, 43.11it/s]
Loading 0: 47%|████▋ | 169/363 [00:10<00:04, 41.77it/s]
Loading 0: 48%|████▊ | 176/363 [00:10<00:04, 46.27it/s]
Loading 0: 50%|█████ | 182/363 [00:10<00:04, 45.14it/s]
Loading 0: 52%|█████▏ | 187/363 [00:10<00:03, 44.46it/s]
Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 48.73it/s]
Loading 0: 55%|█████▍ | 199/363 [00:11<00:03, 48.94it/s]
Loading 0: 56%|█████▌ | 204/363 [00:11<00:05, 27.66it/s]
Loading 0: 58%|█████▊ | 211/363 [00:11<00:04, 33.85it/s]
Loading 0: 60%|█████▉ | 216/363 [00:11<00:04, 34.40it/s]
Loading 0: 61%|██████ | 221/363 [00:11<00:04, 35.34it/s]
Loading 0: 62%|██████▏ | 226/363 [00:11<00:03, 37.99it/s]
Loading 0: 64%|██████▎ | 231/363 [00:12<00:03, 34.75it/s]
Loading 0: 66%|██████▌ | 239/363 [00:12<00:02, 42.96it/s]
Loading 0: 67%|██████▋ | 245/363 [00:12<00:02, 42.55it/s]
Loading 0: 69%|██████▉ | 250/363 [00:12<00:02, 41.88it/s]
Loading 0: 71%|███████ | 257/363 [00:12<00:02, 47.16it/s]
Loading 0: 72%|███████▏ | 262/363 [00:12<00:02, 47.69it/s]
Loading 0: 74%|███████▎ | 267/363 [00:12<00:02, 39.53it/s]
Loading 0: 75%|███████▌ | 274/363 [00:12<00:01, 46.46it/s]
Loading 0: 77%|███████▋ | 280/363 [00:13<00:01, 46.10it/s]
Loading 0: 79%|███████▊ | 285/363 [00:13<00:02, 27.93it/s]
Loading 0: 81%|████████ | 293/363 [00:13<00:01, 36.15it/s]
Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 37.92it/s]
Loading 0: 84%|████████▎ | 304/363 [00:13<00:01, 38.80it/s]
Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 43.58it/s]
Loading 0: 87%|████████▋ | 317/363 [00:14<00:01, 43.34it/s]
Loading 0: 89%|████████▊ | 322/363 [00:14<00:00, 43.46it/s]
Loading 0: 90%|█████████ | 328/363 [00:14<00:00, 45.90it/s]
Loading 0: 92%|█████████▏| 333/363 [00:14<00:00, 45.65it/s]
Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 46.18it/s]
Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 45.17it/s]
Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 43.56it/s]
Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 47.64it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 45.92it/s]
Job chaiml-nemo-chai-5merge-ties-v8-mkmlizer completed after 94.17s with status: succeeded
Stopping job with name chaiml-nemo-chai-5merge-ties-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.68s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-chai-5merge-ties-v8
Waiting for inference service chaiml-nemo-chai-5merge-ties-v8 to be ready
Inference service chaiml-nemo-chai-5merge-ties-v8 ready after 150.53591513633728s
Pipeline stage MKMLDeployer completed in 151.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9605679512023926s
Received healthy response to inference request in 1.5258066654205322s
Received healthy response to inference request in 1.7182953357696533s
Received healthy response to inference request in 1.410576581954956s
Received healthy response to inference request in 1.7846431732177734s
5 requests
0 failed requests
5th percentile: 1.4336225986480713
10th percentile: 1.4566686153411865
20th percentile: 1.502760648727417
30th percentile: 1.5643043994903565
40th percentile: 1.6412998676300048
50th percentile: 1.7182953357696533
60th percentile: 1.7448344707489014
70th percentile: 1.7713736057281495
80th percentile: 1.8198281288146974
90th percentile: 1.890198040008545
95th percentile: 1.9253829956054687
99th percentile: 1.9535309600830078
mean time: 1.6799779415130616
Pipeline stage StressChecker completed in 9.71s
Shutdown handler de-registered
chaiml-nemo-chai-5merge-ties_v8 status is now deployed due to DeploymentManager action
chaiml-nemo-chai-5merge-ties_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-nemo-chai-5merge-ties_v8
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Checking if service chaiml-nemo-chai-5merge-ties-v8 is running
Tearing down inference service chaiml-nemo-chai-5merge-ties-v8
admin requested tearing down of chaiml-small-anthropic-a_1700_v6
Service chaiml-nemo-chai-5merge-ties-v8 has been torndown
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLDeleter completed in 2.75s
run pipeline %s
run pipeline stage %s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLDeleter
Cleaning model data from S3
Checking if service chaiml-small-anthropic-a-1700-v6 is running
Cleaning model data from model cache
Deleting key chaiml-nemo-chai-5merge-ties-v8/config.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-chai-5merge-ties-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-nemo-chai-5merge-ties-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-chai-5merge-ties-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-chai-5merge-ties-v8/tokenizer_config.json from bucket guanaco-mkml-models
Tearing down inference service chaiml-small-anthropic-a-1700-v6
Pipeline stage MKMLModelDeleter completed in 2.60s
Shutdown handler de-registered
Service chaiml-small-anthropic-a-1700-v6 has been torndown
Service chaiml-small-anthropic-a-1700-v6 has been torndown
chaiml-nemo-chai-5merge-ties_v8 status is now torndown due to DeploymentManager action