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-qwen32b-sftexp1-40281-v1-mkmlizer
Waiting for job on chaiml-qwen32b-sftexp1-40281-v1-mkmlizer to finish
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ /___/ ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ║ ║
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: Downloaded to shared memory in 105.574s
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwgp32p9n, device:0
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: quantized model in 62.581s
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: Processed model ChaiML/qwen32b-sftexp1-s1-retryv2lex50perc in 168.156s
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/config.json
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/added_tokens.json
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/tokenizer_config.json
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/special_tokens_map.json
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/merges.txt
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/vocab.json
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/tokenizer.json
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/flywheel_model.2.safetensors
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/flywheel_model.1.safetensors
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sftexp1-40281-v1/flywheel_model.0.safetensors
chaiml-qwen32b-sftexp1-40281-v1-mkmlizer:
Loading 0: 0%| | 0/771 [00:00<?, ?it/s]
Loading 0: 1%| | 5/771 [00:00<00:17, 42.65it/s]
Loading 0: 2%|▏ | 17/771 [00:00<00:10, 71.14it/s]
Loading 0: 4%|▍ | 29/771 [00:00<00:09, 79.12it/s]
Loading 0: 6%|▌ | 46/771 [00:00<00:10, 66.24it/s]
Loading 0: 7%|▋ | 53/771 [00:00<00:13, 55.12it/s]
Loading 0: 8%|▊ | 65/771 [00:01<00:11, 64.00it/s]
Loading 0: 10%|▉ | 77/771 [00:01<00:09, 70.87it/s]
Loading 0: 12%|█▏ | 89/771 [00:01<00:09, 75.76it/s]
Loading 0: 14%|█▎ | 106/771 [00:01<00:09, 71.99it/s]
Loading 0: 15%|█▍ | 114/771 [00:01<00:09, 69.59it/s]
Loading 0: 16%|█▌ | 122/771 [00:01<00:09, 67.98it/s]
Loading 0: 17%|█▋ | 133/771 [00:01<00:08, 71.25it/s]
Loading 0: 20%|█▉ | 151/771 [00:02<00:06, 92.72it/s]
Loading 0: 21%|██ | 161/771 [00:02<00:07, 81.72it/s]
Loading 0: 22%|██▏ | 170/771 [00:02<00:10, 59.85it/s]
Loading 0: 23%|██▎ | 178/771 [00:02<00:09, 60.56it/s]
Loading 0: 24%|██▍ | 185/771 [00:02<00:09, 59.59it/s]
Loading 0: 26%|██▌ | 197/771 [00:02<00:08, 67.80it/s]
Loading 0: 27%|██▋ | 209/771 [00:03<00:07, 74.22it/s]
Loading 0: 29%|██▉ | 226/771 [00:03<00:07, 72.89it/s]
Loading 0: 30%|███ | 234/771 [00:03<00:08, 62.09it/s]
Loading 0: 32%|███▏ | 245/771 [00:03<00:07, 67.39it/s]
Loading 0: 33%|███▎ | 257/771 [00:03<00:06, 73.67it/s]
Loading 0: 35%|███▍ | 269/771 [00:03<00:06, 78.91it/s]
Loading 0: 37%|███▋ | 286/771 [00:04<00:06, 76.80it/s]
Loading 0: 38%|███▊ | 294/771 [00:04<00:07, 64.83it/s]
Loading 0: 39%|███▉ | 303/771 [00:18<03:10, 2.46it/s]
Loading 0: 41%|████ | 315/771 [00:18<02:07, 3.58it/s]
Loading 0: 42%|████▏ | 327/771 [00:18<01:26, 5.13it/s]
Loading 0: 44%|████▍ | 338/771 [00:18<01:01, 7.06it/s]
Loading 0: 45%|████▌ | 347/771 [00:19<00:49, 8.59it/s]
Loading 0: 46%|████▌ | 354/771 [00:19<00:40, 10.40it/s]
Loading 0: 47%|████▋ | 365/771 [00:19<00:27, 14.65it/s]
Loading 0: 49%|████▉ | 377/771 [00:19<00:19, 20.46it/s]
Loading 0: 50%|█████ | 389/771 [00:19<00:13, 27.36it/s]
Loading 0: 53%|█████▎ | 406/771 [00:20<00:10, 35.32it/s]
Loading 0: 54%|█████▎ | 414/771 [00:20<00:09, 36.07it/s]
Loading 0: 55%|█████▌ | 425/771 [00:20<00:07, 43.26it/s]
Loading 0: 57%|█████▋ | 437/771 [00:20<00:06, 51.68it/s]
Loading 0: 58%|█████▊ | 449/771 [00:20<00:05, 59.45it/s]
Loading 0: 60%|██████ | 466/771 [00:21<00:04, 62.62it/s]
Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 55.73it/s]
Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 61.42it/s]
Loading 0: 64%|██████▍ | 497/771 [00:21<00:04, 67.71it/s]
Loading 0: 66%|██████▌ | 509/771 [00:21<00:03, 73.23it/s]
Loading 0: 68%|██████▊ | 526/771 [00:21<00:03, 72.20it/s]
Loading 0: 69%|██████▉ | 534/771 [00:22<00:03, 62.41it/s]
Loading 0: 71%|███████ | 545/771 [00:22<00:03, 67.24it/s]
Loading 0: 72%|███████▏ | 557/771 [00:22<00:02, 72.70it/s]
Loading 0: 74%|███████▍ | 569/771 [00:22<00:02, 77.17it/s]
Loading 0: 76%|███████▌ | 586/771 [00:22<00:02, 73.06it/s]
Loading 0: 77%|███████▋ | 594/771 [00:22<00:02, 62.50it/s]
Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 67.26it/s]
Loading 0: 80%|████████ | 617/771 [00:23<00:02, 72.82it/s]
Loading 0: 81%|████████▏ | 627/771 [00:37<00:57, 2.53it/s]
Loading 0: 83%|████████▎ | 638/771 [00:37<00:37, 3.55it/s]
Loading 0: 84%|████████▍ | 646/771 [00:37<00:27, 4.51it/s]
Loading 0: 85%|████████▍ | 653/771 [00:38<00:21, 5.49it/s]
Loading 0: 86%|████████▋ | 665/771 [00:38<00:12, 8.27it/s]
Loading 0: 88%|████████▊ | 677/771 [00:38<00:07, 11.94it/s]
Loading 0: 89%|████████▉ | 689/771 [00:38<00:04, 16.64it/s]
Loading 0: 92%|█████████▏| 706/771 [00:38<00:02, 23.67it/s]
Loading 0: 93%|█████████▎| 714/771 [00:39<00:02, 26.00it/s]
Loading 0: 94%|█████████▍| 725/771 [00:39<00:01, 32.54it/s]
Loading 0: 96%|█████████▌| 737/771 [00:39<00:00, 40.65it/s]
Loading 0: 97%|█████████▋| 749/771 [00:39<00:00, 49.01it/s]
Loading 0: 99%|█████████▉| 766/771 [00:47<00:00, 5.30it/s]
Job chaiml-qwen32b-sftexp1-40281-v1-mkmlizer completed after 206.9s with status: succeeded
Stopping job with name chaiml-qwen32b-sftexp1-40281-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.36s
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 chaiml-qwen32b-sftexp1-40281-v1
Waiting for inference service chaiml-qwen32b-sftexp1-40281-v1 to be ready
Inference service chaiml-qwen32b-sftexp1-40281-v1 ready after 150.49087524414062s
Pipeline stage MKMLDeployer completed in 150.96s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.412438154220581s
Received healthy response to inference request in 2.506201982498169s
Received healthy response to inference request in 2.5141191482543945s
Received healthy response to inference request in 2.693033218383789s
5 requests
1 failed requests
5th percentile: 2.507785415649414
10th percentile: 2.5093688488006594
20th percentile: 2.5125357151031493
30th percentile: 2.5499019622802734
40th percentile: 2.6214675903320312
50th percentile: 2.693033218383789
60th percentile: 2.9807951927185057
70th percentile: 3.2685571670532223
80th percentile: 6.7584174633026155
90th percentile: 13.450376081466676
95th percentile: 16.796355390548705
99th percentile: 19.473138837814332
mean time: 6.253625440597534
%s, retrying in %s seconds...
Received healthy response to inference request in 2.5971012115478516s
Received healthy response to inference request in 3.055154800415039s
Received healthy response to inference request in 2.4841482639312744s
Received healthy response to inference request in 2.6737990379333496s
Received healthy response to inference request in 2.8198599815368652s
5 requests
0 failed requests
5th percentile: 2.50673885345459
10th percentile: 2.529329442977905
20th percentile: 2.574510622024536
30th percentile: 2.6124407768249513
40th percentile: 2.6431199073791505
50th percentile: 2.6737990379333496
60th percentile: 2.7322234153747558
70th percentile: 2.790647792816162
80th percentile: 2.8669189453125
90th percentile: 2.9610368728637697
95th percentile: 3.0080958366394044
99th percentile: 3.045743007659912
mean time: 2.726012659072876
Pipeline stage StressChecker completed in 47.47s
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 0.71s
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 0.93s
Shutdown handler de-registered
chaiml-qwen32b-sftexp1-_40281_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 6712.13s
Shutdown handler de-registered
chaiml-qwen32b-sftexp1-_40281_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-sftexp1-_40281_v1 status is now torndown due to DeploymentManager action