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-02-full-0615-v1-mkmlizer
Waiting for job on junhua024-chai-02-full-0615-v1-mkmlizer to finish
junhua024-chai-02-full-0615-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ Version: 0.29.15 ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ https://mk1.ai ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ The license key for the current software has been verified as ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ belonging to: ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ Chai Research Corp. ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
junhua024-chai-02-full-0615-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0615-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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`
Failed to get response for submission junhua024-chai-02-full-0111_v2: HTTPConnectionPool(host='junhua024-chai-02-full-0111-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-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-02-full-0615-v1-mkmlizer: Downloaded to shared memory in 133.477s
junhua024-chai-02-full-0615-v1-mkmlizer: Checking if junhua024/chai_02_full_0615 already exists in ChaiML
junhua024-chai-02-full-0615-v1-mkmlizer: Creating repo ChaiML/chai_02_full_0615 and uploading /tmp/tmpe3o03sfa to it
junhua024-chai-02-full-0615-v1-mkmlizer:
0%| | 0/26 [00:00<?, ?it/s]
4%|▍ | 1/26 [00:02<01:07, 2.72s/it]
8%|▊ | 2/26 [00:04<00:56, 2.34s/it]
12%|█▏ | 3/26 [00:07<00:53, 2.32s/it]
15%|█▌ | 4/26 [00:09<00:50, 2.28s/it]
19%|█▉ | 5/26 [00:11<00:47, 2.27s/it]
23%|██▎ | 6/26 [00:13<00:42, 2.11s/it]
27%|██▋ | 7/26 [00:15<00:38, 2.01s/it]
31%|███ | 8/26 [00:21<00:59, 3.30s/it]
35%|███▍ | 9/26 [00:23<00:49, 2.92s/it]
38%|███▊ | 10/26 [00:29<01:02, 3.89s/it]
42%|████▏ | 11/26 [00:32<00:54, 3.64s/it]
46%|████▌ | 12/26 [00:34<00:44, 3.15s/it]
50%|█████ | 13/26 [00:40<00:52, 4.07s/it]
54%|█████▍ | 14/26 [00:42<00:40, 3.36s/it]
58%|█████▊ | 15/26 [00:44<00:33, 3.06s/it]
62%|██████▏ | 16/26 [00:46<00:26, 2.64s/it]
65%|██████▌ | 17/26 [00:48<00:21, 2.41s/it]
69%|██████▉ | 18/26 [00:50<00:18, 2.28s/it]
73%|███████▎ | 19/26 [00:53<00:17, 2.51s/it]
77%|███████▋ | 20/26 [00:55<00:13, 2.27s/it]
81%|████████ | 21/26 [00:57<00:11, 2.20s/it]
85%|████████▍ | 22/26 [00:58<00:07, 1.98s/it]
88%|████████▊ | 23/26 [01:00<00:05, 1.87s/it]
92%|█████████▏| 24/26 [01:05<00:06, 3.01s/it]
96%|█████████▌| 25/26 [01:09<00:03, 3.15s/it]
100%|██████████| 26/26 [01:10<00:00, 2.55s/it]
100%|██████████| 26/26 [01:10<00:00, 2.71s/it]
junhua024-chai-02-full-0615-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe3o03sfa, device:0
junhua024-chai-02-full-0615-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-0615-v1-mkmlizer: quantized model in 31.372s
junhua024-chai-02-full-0615-v1-mkmlizer: Processed model junhua024/chai_02_full_0615 in 261.776s
junhua024-chai-02-full-0615-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-0615-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v1/nvidia
junhua024-chai-02-full-0615-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v1/nvidia/config.json
junhua024-chai-02-full-0615-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v1/nvidia/special_tokens_map.json
junhua024-chai-02-full-0615-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v1/nvidia/tokenizer_config.json
junhua024-chai-02-full-0615-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v1/nvidia/tokenizer.json
junhua024-chai-02-full-0615-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-0615-v1/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-0615-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:00<00:23, 15.40it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:19, 17.91it/s]
Loading 0: 3%|▎ | 12/363 [00:00<00:12, 28.98it/s]
Loading 0: 5%|▍ | 17/363 [00:00<00:11, 30.64it/s]
Loading 0: 6%|▋ | 23/363 [00:00<00:10, 32.74it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:07, 43.64it/s]
Loading 0: 10%|▉ | 36/363 [00:01<00:10, 31.19it/s]
Loading 0: 11%|█▏ | 41/363 [00:01<00:10, 31.89it/s]
Loading 0: 14%|█▍ | 50/363 [00:01<00:07, 39.17it/s]
Loading 0: 15%|█▌ | 55/363 [00:01<00:09, 33.30it/s]
Loading 0: 16%|█▋ | 59/363 [00:01<00:09, 32.99it/s]
Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 34.95it/s]
Loading 0: 19%|█▉ | 69/363 [00:02<00:08, 33.75it/s]
Loading 0: 21%|██ | 75/363 [00:02<00:08, 34.30it/s]
Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 33.08it/s]
Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 38.49it/s]
Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 38.11it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:06, 38.95it/s]
Loading 0: 28%|██▊ | 102/363 [00:02<00:06, 37.74it/s]
Loading 0: 29%|██▉ | 106/363 [00:03<00:06, 37.05it/s]
Loading 0: 31%|███ | 113/363 [00:03<00:06, 41.27it/s]
Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 34.36it/s]
Loading 0: 34%|███▎ | 122/363 [00:03<00:07, 31.44it/s]
Loading 0: 35%|███▌ | 128/363 [00:03<00:07, 31.76it/s]
Loading 0: 36%|███▋ | 132/363 [00:03<00:07, 31.14it/s]
Loading 0: 38%|███▊ | 137/363 [00:03<00:06, 35.15it/s]
Loading 0: 39%|███▉ | 141/363 [00:04<00:06, 35.95it/s]
Loading 0: 40%|███▉ | 145/363 [00:04<00:06, 31.85it/s]
Loading 0: 41%|████ | 149/363 [00:04<00:06, 30.75it/s]
Loading 0: 43%|████▎ | 155/363 [00:04<00:05, 37.48it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:05, 34.27it/s]
Loading 0: 45%|████▌ | 164/363 [00:04<00:05, 34.24it/s]
Loading 0: 46%|████▋ | 168/363 [00:04<00:06, 31.65it/s]
Loading 0: 48%|████▊ | 176/363 [00:05<00:04, 37.95it/s]
Loading 0: 50%|████▉ | 180/363 [00:05<00:06, 29.66it/s]
Loading 0: 51%|█████ | 185/363 [00:05<00:05, 31.55it/s]
Loading 0: 53%|█████▎ | 191/363 [00:05<00:05, 34.18it/s]
Loading 0: 54%|█████▎ | 195/363 [00:05<00:05, 33.38it/s]
Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 34.44it/s]
Loading 0: 57%|█████▋ | 206/363 [00:06<00:04, 34.43it/s]
Loading 0: 58%|█████▊ | 212/363 [00:06<00:04, 35.09it/s]
Loading 0: 61%|██████ | 220/363 [00:06<00:03, 44.35it/s]
Loading 0: 62%|██████▏ | 225/363 [00:06<00:04, 33.07it/s]
Loading 0: 63%|██████▎ | 230/363 [00:06<00:03, 33.82it/s]
Loading 0: 66%|██████▌ | 239/363 [00:06<00:02, 41.93it/s]
Loading 0: 67%|██████▋ | 244/363 [00:07<00:03, 35.77it/s]
Loading 0: 68%|██████▊ | 248/363 [00:07<00:03, 34.99it/s]
Loading 0: 70%|██████▉ | 254/363 [00:07<00:02, 36.53it/s]
Loading 0: 71%|███████ | 258/363 [00:07<00:02, 35.14it/s]
Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 35.16it/s]
Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 34.84it/s]
Loading 0: 76%|███████▌ | 275/363 [00:07<00:02, 35.48it/s]
Loading 0: 78%|███████▊ | 283/363 [00:08<00:01, 44.64it/s]
Loading 0: 79%|███████▉ | 288/363 [00:08<00:02, 34.12it/s]
Loading 0: 81%|████████ | 293/363 [00:08<00:02, 34.62it/s]
Loading 0: 83%|████████▎ | 302/363 [00:08<00:01, 41.55it/s]
Loading 0: 85%|████████▍ | 307/363 [00:08<00:01, 34.76it/s]
Loading 0: 86%|████████▌ | 311/363 [00:08<00:01, 33.22it/s]
Loading 0: 87%|████████▋ | 317/363 [00:09<00:01, 33.81it/s]
Loading 0: 88%|████████▊ | 321/363 [00:09<00:01, 32.41it/s]
Loading 0: 90%|████████▉ | 326/363 [00:09<00:01, 36.14it/s]
Loading 0: 91%|█████████ | 330/363 [00:09<00:00, 35.65it/s]
Loading 0: 92%|█████████▏| 334/363 [00:09<00:00, 32.19it/s]
Loading 0: 93%|█████████▎| 338/363 [00:09<00:00, 31.42it/s]
Loading 0: 95%|█████████▍| 344/363 [00:09<00:00, 38.03it/s]
Loading 0: 96%|█████████▌| 349/363 [00:10<00:00, 25.76it/s]
Loading 0: 97%|█████████▋| 353/363 [00:10<00:00, 23.55it/s]
Loading 0: 98%|█████████▊| 357/363 [00:10<00:00, 25.54it/s]
Job junhua024-chai-02-full-0615-v1-mkmlizer completed after 294.26s with status: succeeded
Stopping job with name junhua024-chai-02-full-0615-v1-mkmlizer
Pipeline stage MKMLizer completed in 294.88s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-0615-v1
Waiting for inference service junhua024-chai-02-full-0615-v1 to be ready
Failed to get response for submission junhua024-chai-02-full-01220_v3: HTTPConnectionPool(host='junhua024-chai-02-full-01220-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x75c5606d2750>, 'Connection to junhua024-chai-02-full-01220-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service junhua024-chai-02-full-0615-v1 ready after 271.00715804100037s
Pipeline stage MKMLDeployer completed in 271.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.514662742614746s
Received healthy response to inference request in 1.5304090976715088s
Received healthy response to inference request in 1.7922577857971191s
Received healthy response to inference request in 1.6111347675323486s
Received healthy response to inference request in 1.773115634918213s
5 requests
0 failed requests
5th percentile: 1.5465542316436767
10th percentile: 1.5626993656158448
20th percentile: 1.5949896335601808
30th percentile: 1.6435309410095216
40th percentile: 1.7083232879638672
50th percentile: 1.773115634918213
60th percentile: 1.7807724952697754
70th percentile: 1.788429355621338
80th percentile: 1.9367387771606446
90th percentile: 2.2257007598876952
95th percentile: 2.3701817512512204
99th percentile: 2.485766544342041
mean time: 1.844316005706787
Pipeline stage StressChecker completed in 10.72s
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 0.80s
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 0.89s
Shutdown handler de-registered
junhua024-chai-02-full-0615_v1 status is now deployed due to DeploymentManager action
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
Received signal 15, running shutdown handler
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3261.67s
Shutdown handler de-registered
junhua024-chai-02-full-0615_v1 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-0615_v1 status is now torndown due to DeploymentManager action