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-fairy32b-sfts1-e-82024-v2-mkmlizer
Waiting for job on chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer to finish
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ _____ __ __ ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ /___/ ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ belonging to: ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ║ ║
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: Downloaded to shared memory in 113.203s
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvp9br_g_, device:0
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: quantized model in 63.013s
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: Processed model ChaiML/fairy32B-sfts1-exp1-ss-retryv2-1 in 176.216s
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-fairy32b-sfts1-e-82024-v2
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-fairy32b-sfts1-e-82024-v2/config.json
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-fairy32b-sfts1-e-82024-v2/special_tokens_map.json
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-fairy32b-sfts1-e-82024-v2/tokenizer_config.json
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-fairy32b-sfts1-e-82024-v2/flywheel_model.2.safetensors
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-fairy32b-sfts1-e-82024-v2/flywheel_model.0.safetensors
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-fairy32b-sfts1-e-82024-v2/flywheel_model.1.safetensors
chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer:
Loading 0: 0%| | 0/771 [00:00<?, ?it/s]
Loading 0: 1%| | 5/771 [00:00<00:18, 41.71it/s]
Loading 0: 2%|▏ | 16/771 [00:00<00:09, 78.51it/s]
Loading 0: 4%|▎ | 27/771 [00:00<00:08, 91.73it/s]
Loading 0: 5%|▍ | 37/771 [00:00<00:07, 94.12it/s]
Loading 0: 6%|▌ | 47/771 [00:00<00:13, 54.60it/s]
Loading 0: 7%|▋ | 55/771 [00:00<00:13, 52.84it/s]
Loading 0: 8%|▊ | 65/771 [00:01<00:12, 58.41it/s]
Loading 0: 10%|▉ | 77/771 [00:01<00:10, 66.15it/s]
Loading 0: 12%|█▏ | 89/771 [00:01<00:09, 71.53it/s]
Loading 0: 14%|█▎ | 106/771 [00:01<00:09, 68.01it/s]
Loading 0: 15%|█▍ | 114/771 [00:01<00:09, 66.22it/s]
Loading 0: 16%|█▌ | 121/771 [00:01<00:10, 63.42it/s]
Loading 0: 17%|█▋ | 133/771 [00:01<00:09, 69.64it/s]
Loading 0: 20%|█▉ | 151/771 [00:02<00:06, 90.43it/s]
Loading 0: 21%|██ | 161/771 [00:02<00:07, 79.88it/s]
Loading 0: 22%|██▏ | 170/771 [00:02<00:10, 59.18it/s]
Loading 0: 23%|██▎ | 177/771 [00:02<00:10, 57.84it/s]
Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 58.57it/s]
Loading 0: 26%|██▌ | 197/771 [00:02<00:08, 66.14it/s]
Loading 0: 27%|██▋ | 209/771 [00:03<00:07, 71.88it/s]
Loading 0: 29%|██▉ | 226/771 [00:03<00:07, 68.31it/s]
Loading 0: 30%|███ | 234/771 [00:03<00:09, 58.54it/s]
Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 63.64it/s]
Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 69.39it/s]
Loading 0: 35%|███▍ | 269/771 [00:03<00:06, 73.99it/s]
Loading 0: 37%|███▋ | 286/771 [00:04<00:06, 69.93it/s]
Loading 0: 38%|███▊ | 294/771 [00:04<00:07, 60.01it/s]
Loading 0: 39%|███▉ | 303/771 [00:18<03:14, 2.41it/s]
Loading 0: 41%|████ | 313/771 [00:19<02:17, 3.33it/s]
Loading 0: 42%|████▏ | 321/771 [00:19<01:43, 4.34it/s]
Loading 0: 43%|████▎ | 329/771 [00:19<01:17, 5.71it/s]
Loading 0: 45%|████▍ | 346/771 [00:19<00:44, 9.53it/s]
Loading 0: 46%|████▌ | 353/771 [00:19<00:38, 10.74it/s]
Loading 0: 47%|████▋ | 365/771 [00:20<00:26, 15.21it/s]
Loading 0: 49%|████▉ | 377/771 [00:20<00:18, 20.75it/s]
Loading 0: 50%|█████ | 388/771 [00:20<00:14, 27.31it/s]
Loading 0: 52%|█████▏ | 398/771 [00:20<00:10, 34.23it/s]
Loading 0: 53%|█████▎ | 407/771 [00:20<00:10, 34.27it/s]
Loading 0: 54%|█████▍ | 415/771 [00:20<00:09, 37.07it/s]
Loading 0: 55%|█████▌ | 425/771 [00:20<00:07, 43.83it/s]
Loading 0: 57%|█████▋ | 437/771 [00:21<00:06, 53.34it/s]
Loading 0: 58%|█████▊ | 449/771 [00:21<00:05, 61.67it/s]
Loading 0: 60%|██████ | 466/771 [00:21<00:04, 64.16it/s]
Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 56.17it/s]
Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 61.84it/s]
Loading 0: 64%|██████▍ | 497/771 [00:21<00:03, 68.62it/s]
Loading 0: 66%|██████▌ | 509/771 [00:22<00:03, 73.53it/s]
Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 70.65it/s]
Loading 0: 69%|██████▉ | 534/771 [00:22<00:03, 60.27it/s]
Loading 0: 71%|███████ | 545/771 [00:22<00:03, 65.35it/s]
Loading 0: 72%|███████▏ | 557/771 [00:22<00:03, 71.27it/s]
Loading 0: 74%|███████▍ | 569/771 [00:22<00:02, 76.11it/s]
Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 73.37it/s]
Loading 0: 77%|███████▋ | 594/771 [00:23<00:02, 61.33it/s]
Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 67.01it/s]
Loading 0: 80%|████████ | 617/771 [00:23<00:02, 73.34it/s]
Loading 0: 81%|████████▏ | 627/771 [00:37<00:55, 2.58it/s]
Loading 0: 83%|████████▎ | 638/771 [00:37<00:36, 3.62it/s]
Loading 0: 84%|████████▍ | 646/771 [00:38<00:27, 4.61it/s]
Loading 0: 85%|████████▍ | 653/771 [00:38<00:21, 5.58it/s]
Loading 0: 86%|████████▋ | 665/771 [00:38<00:12, 8.39it/s]
Loading 0: 88%|████████▊ | 676/771 [00:38<00:07, 11.89it/s]
Loading 0: 89%|████████▉ | 688/771 [00:38<00:04, 16.66it/s]
Loading 0: 91%|█████████ | 699/771 [00:38<00:03, 22.41it/s]
Loading 0: 92%|█████████▏| 708/771 [00:39<00:02, 24.21it/s]
Loading 0: 93%|█████████▎| 716/771 [00:39<00:01, 28.71it/s]
Loading 0: 94%|█████████▍| 725/771 [00:39<00:01, 34.69it/s]
Loading 0: 96%|█████████▌| 737/771 [00:39<00:00, 44.27it/s]
Loading 0: 97%|█████████▋| 749/771 [00:39<00:00, 53.28it/s]
Loading 0: 99%|█████████▉| 766/771 [00:47<00:00, 5.09it/s]
Job chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer completed after 206.78s with status: succeeded
Stopping job with name chaiml-fairy32b-sfts1-e-82024-v2-mkmlizer
Pipeline stage MKMLizer completed in 207.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-fairy32b-sfts1-e-82024-v2
Waiting for inference service chaiml-fairy32b-sfts1-e-82024-v2 to be ready
Inference service chaiml-fairy32b-sfts1-e-82024-v2 ready after 150.7584846019745s
Pipeline stage MKMLDeployer completed in 151.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.367248058319092s
Received healthy response to inference request in 2.892390489578247s
Received healthy response to inference request in 2.6285183429718018s
Received healthy response to inference request in 2.7174880504608154s
Received healthy response to inference request in 2.674686908721924s
5 requests
0 failed requests
5th percentile: 2.637752056121826
10th percentile: 2.6469857692718506
20th percentile: 2.6654531955718994
30th percentile: 2.683247137069702
40th percentile: 2.7003675937652587
50th percentile: 2.7174880504608154
60th percentile: 2.787449026107788
70th percentile: 2.8574100017547606
80th percentile: 2.987362003326416
90th percentile: 3.1773050308227537
95th percentile: 3.2722765445709228
99th percentile: 3.348253755569458
mean time: 2.856066370010376
Pipeline stage StressChecker completed in 15.65s
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 0.79s
Shutdown handler de-registered
chaiml-fairy32b-sfts1-e_82024_v2 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3455.81s
Shutdown handler de-registered
chaiml-fairy32b-sfts1-e_82024_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-fairy32b-sfts1-e_82024_v2 status is now torndown due to DeploymentManager action