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 junhua024-chai-06-full-01-v1-mkmlizer
Waiting for job on junhua024-chai-06-full-01-v1-mkmlizer to finish
junhua024-chai-06-full-01-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-01-v1-mkmlizer: ║ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ Version: 0.29.15 ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ https://mk1.ai ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ The license key for the current software has been verified as ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ belonging to: ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ Chai Research Corp. ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
junhua024-chai-06-full-01-v1-mkmlizer: ║ ║
junhua024-chai-06-full-01-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-01-v1-mkmlizer: Downloaded to shared memory in 129.463s
junhua024-chai-06-full-01-v1-mkmlizer: Checking if junhua024/chai_06_full_01 already exists in ChaiML
junhua024-chai-06-full-01-v1-mkmlizer: Creating repo ChaiML/chai_06_full_01 and uploading /tmp/tmpbkgjyn5l to it
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-01-v1-mkmlizer:
0%| | 0/26 [00:00<?, ?it/s]
4%|▍ | 1/26 [00:01<00:49, 1.98s/it]
8%|▊ | 2/26 [00:03<00:39, 1.66s/it]
12%|█▏ | 3/26 [00:04<00:36, 1.58s/it]
15%|█▌ | 4/26 [00:06<00:36, 1.65s/it]
19%|█▉ | 5/26 [00:12<01:08, 3.25s/it]
23%|██▎ | 6/26 [00:15<01:00, 3.04s/it]
27%|██▋ | 7/26 [00:16<00:47, 2.50s/it]
31%|███ | 8/26 [00:18<00:38, 2.16s/it]
35%|███▍ | 9/26 [00:19<00:33, 1.97s/it]
38%|███▊ | 10/26 [00:23<00:40, 2.52s/it]
42%|████▏ | 11/26 [00:24<00:32, 2.17s/it]
46%|████▌ | 12/26 [00:28<00:36, 2.63s/it]
50%|█████ | 13/26 [00:33<00:43, 3.33s/it]
54%|█████▍ | 14/26 [00:35<00:34, 2.90s/it]
58%|█████▊ | 15/26 [00:39<00:37, 3.38s/it]
62%|██████▏ | 16/26 [00:42<00:30, 3.10s/it]
65%|██████▌ | 17/26 [00:43<00:23, 2.63s/it]
69%|██████▉ | 18/26 [00:45<00:18, 2.29s/it]
73%|███████▎ | 19/26 [00:47<00:14, 2.10s/it]
77%|███████▋ | 20/26 [00:48<00:11, 1.97s/it]
81%|████████ | 21/26 [00:50<00:09, 1.89s/it]
85%|████████▍ | 22/26 [00:52<00:07, 1.87s/it]
88%|████████▊ | 23/26 [00:53<00:05, 1.80s/it]
92%|█████████▏| 24/26 [01:00<00:06, 3.14s/it]
96%|█████████▌| 25/26 [01:02<00:02, 2.79s/it]
100%|██████████| 26/26 [01:03<00:00, 2.32s/it]
100%|██████████| 26/26 [01:03<00:00, 2.44s/it]
junhua024-chai-06-full-01-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbkgjyn5l, device:0
junhua024-chai-06-full-01-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-01-v1-mkmlizer: quantized model in 30.824s
junhua024-chai-06-full-01-v1-mkmlizer: Processed model junhua024/chai_06_full_01 in 249.650s
junhua024-chai-06-full-01-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-01-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-01-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-01-v1/nvidia
junhua024-chai-06-full-01-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-01-v1/nvidia/config.json
junhua024-chai-06-full-01-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-01-v1/nvidia/special_tokens_map.json
junhua024-chai-06-full-01-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-01-v1/nvidia/tokenizer_config.json
junhua024-chai-06-full-01-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-01-v1/nvidia/tokenizer.json
junhua024-chai-06-full-01-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-01-v1/nvidia/flywheel_model.0.safetensors
junhua024-chai-06-full-01-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:00<00:24, 15.04it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:20, 17.42it/s]
Loading 0: 3%|▎ | 12/363 [00:00<00:11, 29.91it/s]
Loading 0: 5%|▍ | 17/363 [00:00<00:10, 32.22it/s]
Loading 0: 6%|▋ | 23/363 [00:00<00:09, 34.06it/s]
Loading 0: 9%|▉ | 32/363 [00:00<00:06, 47.75it/s]
Loading 0: 10%|█ | 38/363 [00:01<00:08, 37.85it/s]
Loading 0: 12%|█▏ | 43/363 [00:01<00:08, 37.42it/s]
Loading 0: 14%|█▍ | 50/363 [00:01<00:07, 41.23it/s]
Loading 0: 15%|█▌ | 55/363 [00:01<00:08, 35.57it/s]
Loading 0: 16%|█▋ | 59/363 [00:01<00:08, 35.06it/s]
Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 36.59it/s]
Loading 0: 19%|█▉ | 69/363 [00:01<00:08, 34.42it/s]
Loading 0: 21%|██ | 75/363 [00:02<00:08, 35.21it/s]
Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 33.80it/s]
Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 38.66it/s]
Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 38.82it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:06, 40.07it/s]
Loading 0: 28%|██▊ | 102/363 [00:02<00:06, 39.49it/s]
Loading 0: 29%|██▉ | 107/363 [00:02<00:06, 39.66it/s]
Loading 0: 31%|███ | 113/363 [00:03<00:05, 42.32it/s]
Loading 0: 33%|███▎ | 118/363 [00:03<00:06, 36.29it/s]
Loading 0: 34%|███▎ | 122/363 [00:03<00:06, 35.09it/s]
Loading 0: 35%|███▌ | 128/363 [00:03<00:06, 37.31it/s]
Loading 0: 36%|███▋ | 132/363 [00:03<00:06, 35.66it/s]
Loading 0: 38%|███▊ | 138/363 [00:03<00:06, 35.13it/s]
Loading 0: 39%|███▉ | 143/363 [00:03<00:06, 33.44it/s]
Loading 0: 41%|████ | 149/363 [00:04<00:06, 35.36it/s]
Loading 0: 43%|████▎ | 157/363 [00:04<00:04, 44.54it/s]
Loading 0: 45%|████▍ | 162/363 [00:04<00:05, 34.73it/s]
Loading 0: 46%|████▌ | 167/363 [00:04<00:05, 34.17it/s]
Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 43.14it/s]
Loading 0: 50%|████▉ | 180/363 [00:05<00:05, 30.55it/s]
Loading 0: 51%|█████ | 185/363 [00:05<00:05, 31.88it/s]
Loading 0: 53%|█████▎ | 191/363 [00:05<00:05, 33.50it/s]
Loading 0: 54%|█████▎ | 195/363 [00:05<00:05, 32.10it/s]
Loading 0: 55%|█████▌ | 200/363 [00:05<00:04, 35.82it/s]
Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 34.65it/s]
Loading 0: 58%|█████▊ | 209/363 [00:05<00:04, 35.75it/s]
Loading 0: 59%|█████▊ | 213/363 [00:05<00:04, 33.46it/s]
Loading 0: 60%|██████ | 219/363 [00:06<00:03, 39.62it/s]
Loading 0: 62%|██████▏ | 224/363 [00:06<00:03, 35.31it/s]
Loading 0: 63%|██████▎ | 228/363 [00:06<00:03, 34.19it/s]
Loading 0: 64%|██████▍ | 232/363 [00:06<00:03, 33.38it/s]
Loading 0: 66%|██████▌ | 239/363 [00:06<00:03, 38.66it/s]
Loading 0: 67%|██████▋ | 243/363 [00:06<00:03, 31.02it/s]
Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 32.86it/s]
Loading 0: 70%|██████▉ | 254/363 [00:07<00:03, 34.96it/s]
Loading 0: 71%|███████ | 258/363 [00:07<00:03, 33.96it/s]
Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 34.84it/s]
Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 34.39it/s]
Loading 0: 76%|███████▌ | 275/363 [00:07<00:02, 35.59it/s]
Loading 0: 78%|███████▊ | 282/363 [00:07<00:01, 43.04it/s]
Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 38.92it/s]
Loading 0: 80%|████████ | 292/363 [00:08<00:01, 37.99it/s]
Loading 0: 82%|████████▏ | 298/363 [00:08<00:01, 38.52it/s]
Loading 0: 83%|████████▎ | 303/363 [00:08<00:01, 38.03it/s]
Loading 0: 85%|████████▍ | 307/363 [00:08<00:01, 36.36it/s]
Loading 0: 86%|████████▌ | 311/363 [00:08<00:01, 34.26it/s]
Loading 0: 87%|████████▋ | 317/363 [00:08<00:01, 36.53it/s]
Loading 0: 88%|████████▊ | 321/363 [00:08<00:01, 34.13it/s]
Loading 0: 90%|████████▉ | 326/363 [00:09<00:00, 37.50it/s]
Loading 0: 91%|█████████ | 331/363 [00:09<00:00, 36.11it/s]
Loading 0: 93%|█████████▎| 336/363 [00:09<00:00, 37.81it/s]
Loading 0: 94%|█████████▎| 340/363 [00:09<00:00, 37.64it/s]
Loading 0: 96%|█████████▌| 347/363 [00:09<00:00, 45.82it/s]
Loading 0: 97%|█████████▋| 352/363 [00:10<00:00, 22.03it/s]
Loading 0: 98%|█████████▊| 357/363 [00:10<00:00, 24.61it/s]
Job junhua024-chai-06-full-01-v1-mkmlizer completed after 275.4s with status: succeeded
Stopping job with name junhua024-chai-06-full-01-v1-mkmlizer
Pipeline stage MKMLizer completed in 276.01s
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 junhua024-chai-06-full-01-v1
Waiting for inference service junhua024-chai-06-full-01-v1 to be ready
Failed to get response for submission zmeeks-capitanito-52_v4: ('http://zmeeks-capitanito-52-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:56818->127.0.0.1:8080: read: connection reset by peer\n')
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-06-full-01-v1 ready after 271.33314657211304s
Pipeline stage MKMLDeployer completed in 272.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4106204509735107s
Received healthy response to inference request in 1.4602930545806885s
Received healthy response to inference request in 1.5453336238861084s
Received healthy response to inference request in 1.760782241821289s
Received healthy response to inference request in 1.5244882106781006s
5 requests
0 failed requests
5th percentile: 1.4731320858001709
10th percentile: 1.4859711170196532
20th percentile: 1.5116491794586182
30th percentile: 1.5286572933197022
40th percentile: 1.5369954586029053
50th percentile: 1.5453336238861084
60th percentile: 1.6315130710601806
70th percentile: 1.7176925182342528
80th percentile: 1.8907498836517336
90th percentile: 2.150685167312622
95th percentile: 2.2806528091430662
99th percentile: 2.384626922607422
mean time: 1.7403035163879395
Pipeline stage StressChecker completed in 10.07s
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 0.70s
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 0.72s
Shutdown handler de-registered
junhua024-chai-06-full-01_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-06-full-01-v1-profiler
Waiting for inference service junhua024-chai-06-full-01-v1-profiler to be ready
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 10341.65s
Shutdown handler de-registered
junhua024-chai-06-full-01_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-01_v1 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-01_v1 status is now torndown due to DeploymentManager action