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 downtown-case-tifa-deep-21429-v1-mkmlizer
Waiting for job on downtown-case-tifa-deep-21429-v1-mkmlizer to finish
downtown-case-tifa-deep-21429-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ Version: 0.29.15 ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ https://mk1.ai ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ The license key for the current software has been verified as ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ belonging to: ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ Chai Research Corp. ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ║ ║
downtown-case-tifa-deep-21429-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
downtown-case-tifa-deep-21429-v1-mkmlizer: Downloaded to shared memory in 53.666s
downtown-case-tifa-deep-21429-v1-mkmlizer: Checking if Downtown-Case/Tifa-Deepsex-14b-CoT-Chat-HF already exists in ChaiML
downtown-case-tifa-deep-21429-v1-mkmlizer: Creating repo ChaiML/Tifa-Deepsex-14b-CoT-Chat-HF and uploading /tmp/tmp3jtvasif to it
Retrying (%r) after connection broken by '%r': %s
downtown-case-tifa-deep-21429-v1-mkmlizer:
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:08<00:51, 8.51s/it]
29%|██▊ | 2/7 [00:28<01:15, 15.06s/it]
43%|████▎ | 3/7 [00:36<00:47, 11.84s/it]
57%|█████▋ | 4/7 [00:42<00:29, 9.74s/it]
71%|███████▏ | 5/7 [00:48<00:16, 8.24s/it]
86%|████████▌ | 6/7 [00:51<00:06, 6.63s/it]
100%|██████████| 7/7 [00:52<00:00, 4.80s/it]
100%|██████████| 7/7 [00:52<00:00, 7.54s/it]
downtown-case-tifa-deep-21429-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3jtvasif, device:0
downtown-case-tifa-deep-21429-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
downtown-case-tifa-deep-21429-v1-mkmlizer: quantized model in 39.029s
downtown-case-tifa-deep-21429-v1-mkmlizer: Processed model Downtown-Case/Tifa-Deepsex-14b-CoT-Chat-HF in 176.845s
downtown-case-tifa-deep-21429-v1-mkmlizer: creating bucket guanaco-mkml-models
downtown-case-tifa-deep-21429-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
downtown-case-tifa-deep-21429-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/config.json
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/added_tokens.json
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/special_tokens_map.json
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/tokenizer_config.json
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/vocab.json
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/merges.txt
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/tokenizer.json
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/flywheel_model.1.safetensors
downtown-case-tifa-deep-21429-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/downtown-case-tifa-deep-21429-v1/nvidia/flywheel_model.0.safetensors
downtown-case-tifa-deep-21429-v1-mkmlizer:
Loading 0: 0%| | 0/579 [00:00<?, ?it/s]
Loading 0: 1%| | 5/579 [00:00<00:20, 27.60it/s]
Loading 0: 2%|▏ | 13/579 [00:00<00:12, 45.74it/s]
Loading 0: 3%|▎ | 18/579 [00:00<00:13, 40.28it/s]
Loading 0: 4%|▍ | 25/579 [00:00<00:11, 46.23it/s]
Loading 0: 5%|▌ | 30/579 [00:00<00:12, 43.93it/s]
Loading 0: 6%|▋ | 37/579 [00:00<00:11, 48.06it/s]
Loading 0: 7%|▋ | 42/579 [00:00<00:12, 43.68it/s]
Loading 0: 8%|▊ | 49/579 [00:01<00:11, 46.07it/s]
Loading 0: 9%|▉ | 54/579 [00:01<00:11, 44.26it/s]
Loading 0: 11%|█ | 61/579 [00:01<00:11, 45.81it/s]
Loading 0: 11%|█▏ | 66/579 [00:01<00:12, 41.91it/s]
Loading 0: 12%|█▏ | 72/579 [00:01<00:11, 46.00it/s]
Loading 0: 14%|█▎ | 79/579 [00:01<00:11, 43.72it/s]
Loading 0: 15%|█▍ | 84/579 [00:02<00:19, 25.49it/s]
Loading 0: 16%|█▌ | 92/579 [00:02<00:15, 31.15it/s]
Loading 0: 17%|█▋ | 96/579 [00:02<00:15, 31.05it/s]
Loading 0: 18%|█▊ | 104/579 [00:02<00:12, 37.65it/s]
Loading 0: 19%|█▉ | 109/579 [00:02<00:12, 37.52it/s]
Loading 0: 20%|██ | 116/579 [00:02<00:11, 40.49it/s]
Loading 0: 21%|██ | 121/579 [00:03<00:11, 40.46it/s]
Loading 0: 22%|██▏ | 128/579 [00:03<00:10, 43.62it/s]
Loading 0: 23%|██▎ | 133/579 [00:03<00:10, 41.66it/s]
Loading 0: 24%|██▍ | 139/579 [00:03<00:09, 45.70it/s]
Loading 0: 25%|██▌ | 146/579 [00:03<00:09, 44.77it/s]
Loading 0: 26%|██▌ | 151/579 [00:03<00:11, 37.17it/s]
Loading 0: 27%|██▋ | 156/579 [00:03<00:11, 36.61it/s]
Loading 0: 28%|██▊ | 164/579 [00:04<00:09, 42.99it/s]
Loading 0: 29%|██▉ | 169/579 [00:04<00:09, 41.47it/s]
Loading 0: 30%|███ | 176/579 [00:04<00:09, 42.56it/s]
Loading 0: 31%|███▏ | 181/579 [00:04<00:09, 41.82it/s]
Loading 0: 32%|███▏ | 188/579 [00:04<00:08, 45.42it/s]
Loading 0: 33%|███▎ | 193/579 [00:04<00:13, 28.90it/s]
Loading 0: 34%|███▍ | 197/579 [00:05<00:12, 29.88it/s]
Loading 0: 35%|███▌ | 205/579 [00:05<00:09, 37.94it/s]
Loading 0: 36%|███▋ | 210/579 [00:05<00:09, 38.26it/s]
Loading 0: 37%|███▋ | 217/579 [00:05<00:08, 41.87it/s]
Loading 0: 38%|███▊ | 222/579 [00:05<00:08, 40.98it/s]
Loading 0: 40%|███▉ | 229/579 [00:05<00:07, 44.79it/s]
Loading 0: 40%|████ | 234/579 [00:05<00:07, 43.16it/s]
Loading 0: 42%|████▏ | 241/579 [00:05<00:07, 46.10it/s]
Loading 0: 42%|████▏ | 246/579 [00:06<00:07, 44.16it/s]
Loading 0: 44%|████▎ | 253/579 [00:06<00:06, 47.09it/s]
Loading 0: 45%|████▍ | 258/579 [00:06<00:07, 45.55it/s]
Loading 0: 46%|████▌ | 265/579 [00:06<00:06, 49.01it/s]
Loading 0: 47%|████▋ | 270/579 [00:06<00:06, 46.44it/s]
Loading 0: 48%|████▊ | 277/579 [00:06<00:06, 49.25it/s]
Loading 0: 49%|████▊ | 282/579 [00:06<00:06, 45.38it/s]
Loading 0: 50%|████▉ | 289/579 [00:07<00:06, 48.31it/s]
Loading 0: 51%|█████ | 296/579 [00:07<00:05, 50.89it/s]
Loading 0: 52%|█████▏ | 302/579 [00:07<00:08, 34.34it/s]
Loading 0: 53%|█████▎ | 307/579 [00:07<00:07, 35.36it/s]
Loading 0: 54%|█████▍ | 313/579 [00:07<00:06, 38.14it/s]
Loading 0: 55%|█████▍ | 318/579 [00:07<00:06, 37.52it/s]
Loading 0: 56%|█████▌ | 325/579 [00:07<00:06, 41.41it/s]
Loading 0: 57%|█████▋ | 330/579 [00:08<00:05, 41.84it/s]
Loading 0: 58%|█████▊ | 337/579 [00:08<00:05, 45.65it/s]
Loading 0: 59%|█████▉ | 342/579 [00:08<00:05, 44.26it/s]
Loading 0: 60%|██████ | 349/579 [00:08<00:04, 46.50it/s]
Loading 0: 61%|██████ | 354/579 [00:08<00:04, 45.54it/s]
Loading 0: 62%|██████▏ | 361/579 [00:08<00:04, 47.80it/s]
Loading 0: 63%|██████▎ | 366/579 [00:08<00:04, 44.07it/s]
Loading 0: 64%|██████▍ | 373/579 [00:09<00:04, 45.46it/s]
Loading 0: 65%|██████▌ | 378/579 [00:09<00:04, 44.51it/s]
Loading 0: 66%|██████▋ | 385/579 [00:09<00:04, 47.58it/s]
Loading 0: 67%|██████▋ | 390/579 [00:09<00:04, 44.57it/s]
Loading 0: 69%|██████▊ | 397/579 [00:09<00:03, 46.13it/s]
Loading 0: 70%|██████▉ | 404/579 [00:09<00:03, 49.02it/s]
Loading 0: 71%|███████ | 409/579 [00:09<00:05, 32.36it/s]
Loading 0: 71%|███████▏ | 413/579 [00:10<00:05, 32.32it/s]
Loading 0: 73%|███████▎ | 421/579 [00:10<00:04, 38.97it/s]
Loading 0: 74%|███████▎ | 426/579 [00:10<00:04, 37.56it/s]
Loading 0: 75%|███████▍ | 433/579 [00:10<00:03, 41.49it/s]
Loading 0: 76%|███████▌ | 438/579 [00:10<00:03, 41.86it/s]
Loading 0: 77%|███████▋ | 445/579 [00:10<00:03, 43.95it/s]
Loading 0: 78%|███████▊ | 450/579 [00:10<00:03, 42.44it/s]
Loading 0: 79%|███████▉ | 457/579 [00:11<00:02, 45.80it/s]
Loading 0: 80%|███████▉ | 462/579 [00:11<00:02, 45.14it/s]
Loading 0: 81%|████████ | 469/579 [00:11<00:02, 47.42it/s]
Loading 0: 82%|████████▏ | 474/579 [00:11<00:02, 44.31it/s]
Loading 0: 83%|████████▎ | 481/579 [00:11<00:02, 46.57it/s]
Loading 0: 84%|████████▍ | 486/579 [00:11<00:02, 44.86it/s]
Loading 0: 85%|████████▌ | 493/579 [00:11<00:01, 46.86it/s]
Loading 0: 86%|████████▌ | 498/579 [00:11<00:01, 45.09it/s]
Loading 0: 87%|████████▋ | 505/579 [00:12<00:01, 47.95it/s]
Loading 0: 88%|████████▊ | 512/579 [00:12<00:01, 50.49it/s]
Loading 0: 89%|████████▉ | 518/579 [00:26<00:42, 1.45it/s]
Loading 0: 90%|████████▉ | 521/579 [00:26<00:33, 1.72it/s]
Loading 0: 91%|█████████ | 526/579 [00:26<00:22, 2.36it/s]
Loading 0: 92%|█████████▏| 530/579 [00:26<00:15, 3.07it/s]
Loading 0: 92%|█████████▏| 534/579 [00:26<00:11, 4.01it/s]
Loading 0: 94%|█████████▎| 542/579 [00:27<00:05, 6.68it/s]
Loading 0: 94%|█████████▍| 547/579 [00:27<00:03, 8.70it/s]
Loading 0: 96%|█████████▌| 554/579 [00:27<00:02, 12.35it/s]
Loading 0: 97%|█████████▋| 559/579 [00:27<00:01, 15.00it/s]
Loading 0: 98%|█████████▊| 566/579 [00:27<00:00, 20.06it/s]
Loading 0: 99%|█████████▊| 571/579 [00:27<00:00, 23.18it/s]
Loading 0: 100%|█████████▉| 578/579 [00:27<00:00, 28.02it/s]
Job downtown-case-tifa-deep-21429-v1-mkmlizer completed after 238.95s with status: succeeded
Stopping job with name downtown-case-tifa-deep-21429-v1-mkmlizer
Pipeline stage MKMLizer completed in 239.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service downtown-case-tifa-deep-21429-v1
Waiting for inference service downtown-case-tifa-deep-21429-v1 to be ready
Inference service downtown-case-tifa-deep-21429-v1 ready after 220.81881260871887s
Pipeline stage MKMLDeployer completed in 221.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6795201301574707s
Received healthy response to inference request in 1.924088478088379s
Received healthy response to inference request in 1.84916090965271s
Received healthy response to inference request in 2.251129388809204s
Received healthy response to inference request in 1.780773401260376s
5 requests
0 failed requests
5th percentile: 1.7944509029388427
10th percentile: 1.8081284046173096
20th percentile: 1.8354834079742433
30th percentile: 1.8641464233398437
40th percentile: 1.8941174507141114
50th percentile: 1.924088478088379
60th percentile: 2.054904842376709
70th percentile: 2.185721206665039
80th percentile: 2.3368075370788577
90th percentile: 2.508163833618164
95th percentile: 2.593841981887817
99th percentile: 2.66238450050354
mean time: 2.096934461593628
Pipeline stage StressChecker completed in 11.87s
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 0.67s
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 0.67s
Shutdown handler de-registered
downtown-case-tifa-deep_21429_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 0.17s
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 downtown-case-tifa-deep-21429-v1-profiler
Waiting for inference service downtown-case-tifa-deep-21429-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 5808.52s
Shutdown handler de-registered
downtown-case-tifa-deep_21429_v1 status is now inactive due to auto deactivation removed underperforming models
downtown-case-tifa-deep_21429_v1 status is now torndown due to DeploymentManager action