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-llama-8b-nis-ft-39927-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-ft-39927-v1-mkmlizer to finish
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: Downloaded to shared memory in 28.007s
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_ft_new1m_512seq_v2500 already exists in ChaiML
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp8dyyzaxr, device:0
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: quantized model in 19.169s
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_ft_new1m_512seq_v2500 in 47.177s
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-39927-v1/nvidia
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-39927-v1/nvidia/config.json
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-39927-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-39927-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-39927-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-39927-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-ft-39927-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:08, 34.46it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 55.07it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 47.16it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:05, 46.67it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:04, 53.19it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 47.63it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 46.50it/s]
Loading 0: 16%|█▋ | 48/291 [00:00<00:04, 50.00it/s]
Loading 0: 19%|█▊ | 54/291 [00:01<00:04, 52.14it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 45.27it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 50.74it/s]
Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 45.15it/s]
Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 44.06it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 32.74it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 31.91it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 39.37it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 38.55it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 39.66it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 45.77it/s]
Loading 0: 41%|████ | 118/291 [00:02<00:04, 43.17it/s]
Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 43.48it/s]
Loading 0: 44%|████▍ | 129/291 [00:02<00:03, 47.30it/s]
Loading 0: 46%|████▌ | 134/291 [00:03<00:03, 46.42it/s]
Loading 0: 48%|████▊ | 140/291 [00:03<00:03, 41.22it/s]
Loading 0: 51%|█████ | 147/291 [00:03<00:03, 47.61it/s]
Loading 0: 53%|█████▎ | 153/291 [00:03<00:02, 48.10it/s]
Loading 0: 55%|█████▍ | 159/291 [00:03<00:03, 41.58it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 47.13it/s]
Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 44.15it/s]
Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 48.53it/s]
Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 49.00it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 32.43it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 34.20it/s]
Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 38.47it/s]
Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 38.42it/s]
Loading 0: 73%|███████▎ | 213/291 [00:04<00:02, 38.67it/s]
Loading 0: 75%|███████▌ | 219/291 [00:05<00:01, 42.97it/s]
Loading 0: 77%|███████▋ | 224/291 [00:05<00:01, 42.37it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 43.79it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 41.98it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 41.82it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 47.53it/s]
Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 44.54it/s]
Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 44.21it/s]
Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 49.72it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 45.72it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 45.41it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 41.66it/s]
Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 31.87it/s]
Job chaiml-llama-8b-nis-ft-39927-v1-mkmlizer completed after 74.57s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-ft-39927-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.26s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-ft-39927-v1
Waiting for inference service chaiml-llama-8b-nis-ft-39927-v1 to be ready
Inference service chaiml-llama-8b-nis-ft-39927-v1 ready after 221.66443824768066s
Pipeline stage MKMLDeployer completed in 222.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.594107389450073s
Received healthy response to inference request in 4.4557013511657715s
Received healthy response to inference request in 2.928319215774536s
Received healthy response to inference request in 2.751664161682129s
Received healthy response to inference request in 2.391986608505249s
5 requests
0 failed requests
5th percentile: 2.463922119140625
10th percentile: 2.535857629776001
20th percentile: 2.679728651046753
30th percentile: 2.7869951725006104
40th percentile: 2.8576571941375732
50th percentile: 2.928319215774536
60th percentile: 3.5392720699310303
70th percentile: 4.150224924087524
80th percentile: 4.4833825588226315
90th percentile: 4.538744974136352
95th percentile: 4.566426181793213
99th percentile: 4.588571147918701
mean time: 3.4243557453155518
Pipeline stage StressChecker completed in 18.71s
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 0.66s
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 1.04s
Shutdown handler de-registered
chaiml-llama-8b-nis-ft-_39927_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 6560.37s
Shutdown handler de-registered
chaiml-llama-8b-nis-ft-_39927_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-ft-_39927_v1 status is now torndown due to DeploymentManager action