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-nis-qwen25-14b-s-40584-v2-mkmlizer
Waiting for job on chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer to finish
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ _____ __ __ ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ /___/ ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ belonging to: ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ║ ║
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: Downloaded to shared memory in 47.041s
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt1ozd6me, device:0
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: quantized model in 35.773s
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: Processed model ChaiML/nis-qwen25-14b-sft-exp1-datav1ffsys20k in 82.815s
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/config.json
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/added_tokens.json
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/tokenizer_config.json
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/special_tokens_map.json
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/merges.txt
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/vocab.json
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/tokenizer.json
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/flywheel_model.1.safetensors
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen25-14b-s-40584-v2/flywheel_model.0.safetensors
chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer:
Loading 0: 0%| | 0/579 [00:00<?, ?it/s]
Loading 0: 3%|▎ | 15/579 [00:00<00:03, 145.58it/s]
Loading 0: 5%|▌ | 30/579 [00:00<00:04, 134.92it/s]
Loading 0: 9%|▉ | 51/579 [00:00<00:03, 156.32it/s]
Loading 0: 12%|█▏ | 67/579 [00:00<00:03, 146.68it/s]
Loading 0: 14%|█▍ | 82/579 [00:00<00:05, 96.03it/s]
Loading 0: 17%|█▋ | 96/579 [00:00<00:04, 101.88it/s]
Loading 0: 20%|██ | 118/579 [00:00<00:03, 125.53it/s]
Loading 0: 23%|██▎ | 132/579 [00:01<00:03, 124.12it/s]
Loading 0: 27%|██▋ | 154/579 [00:01<00:02, 142.99it/s]
Loading 0: 29%|██▉ | 170/579 [00:01<00:02, 140.19it/s]
Loading 0: 33%|███▎ | 189/579 [00:01<00:03, 105.60it/s]
Loading 0: 35%|███▍ | 202/579 [00:01<00:03, 104.08it/s]
Loading 0: 38%|███▊ | 219/579 [00:01<00:03, 116.33it/s]
Loading 0: 40%|████ | 233/579 [00:01<00:02, 117.25it/s]
Loading 0: 44%|████▍ | 255/579 [00:02<00:02, 137.29it/s]
Loading 0: 47%|████▋ | 270/579 [00:02<00:02, 134.88it/s]
Loading 0: 50%|█████ | 292/579 [00:02<00:01, 154.20it/s]
Loading 0: 53%|█████▎ | 309/579 [00:02<00:02, 102.49it/s]
Loading 0: 56%|█████▋ | 327/579 [00:02<00:02, 116.49it/s]
Loading 0: 59%|█████▉ | 342/579 [00:02<00:02, 118.05it/s]
Loading 0: 63%|██████▎ | 363/579 [00:02<00:01, 133.52it/s]
Loading 0: 65%|██████▌ | 378/579 [00:03<00:01, 131.92it/s]
Loading 0: 69%|██████▉ | 400/579 [00:03<00:01, 152.79it/s]
Loading 0: 72%|███████▏ | 417/579 [00:03<00:01, 101.22it/s]
Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 115.55it/s]
Loading 0: 78%|███████▊ | 450/579 [00:03<00:01, 118.29it/s]
Loading 0: 81%|████████▏ | 471/579 [00:03<00:00, 134.24it/s]
Loading 0: 84%|████████▍ | 487/579 [00:03<00:00, 135.50it/s]
Loading 0: 88%|████████▊ | 508/579 [00:04<00:00, 152.46it/s]
Loading 0: 88%|████████▊ | 512/579 [00:25<00:00, 152.46it/s]
Loading 0: 89%|████████▊ | 513/579 [00:25<00:29, 2.25it/s]
Loading 0: 90%|█████████ | 522/579 [00:25<00:20, 2.82it/s]
Loading 0: 94%|█████████▍| 544/579 [00:25<00:07, 4.84it/s]
Loading 0: 97%|█████████▋| 560/579 [00:25<00:02, 6.85it/s]
Job chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer completed after 116.38s with status: succeeded
Stopping job with name chaiml-nis-qwen25-14b-s-40584-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.04s
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-nis-qwen25-14b-s-40584-v2
Waiting for inference service chaiml-nis-qwen25-14b-s-40584-v2 to be ready
Inference service chaiml-nis-qwen25-14b-s-40584-v2 ready after 131.1038956642151s
Pipeline stage MKMLDeployer completed in 132.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4525630474090576s
Received healthy response to inference request in 2.2453324794769287s
Received healthy response to inference request in 1.878248929977417s
Received healthy response to inference request in 1.891801118850708s
Received healthy response to inference request in 1.977036714553833s
5 requests
0 failed requests
5th percentile: 1.8809593677520753
10th percentile: 1.8836698055267334
20th percentile: 1.8890906810760497
30th percentile: 1.908848237991333
40th percentile: 1.942942476272583
50th percentile: 1.977036714553833
60th percentile: 2.084355020523071
70th percentile: 2.1916733264923094
80th percentile: 2.2867785930633544
90th percentile: 2.3696708202362062
95th percentile: 2.411116933822632
99th percentile: 2.4442738246917726
mean time: 2.0889964580535887
Pipeline stage StressChecker completed in 11.55s
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 0.68s
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 0.64s
Shutdown handler de-registered
chaiml-nis-qwen25-14b-s_40584_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4682.84s
Shutdown handler de-registered
chaiml-nis-qwen25-14b-s_40584_v2 status is now inactive due to auto deactivation removed underperforming models