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-horror-sft-v1-5e4-v9-mkmlizer
Waiting for job on chaiml-horror-sft-v1-5e4-v9-mkmlizer to finish
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ _____ __ __ ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ /___/ ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ Version: 0.10.1 ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ https://mk1.ai ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ belonging to: ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ Chai Research Corp. ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ║ ║
chaiml-horror-sft-v1-5e4-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-horror-sft-v1-5e4-v9-mkmlizer: Downloaded to shared memory in 28.095s
chaiml-horror-sft-v1-5e4-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3syttr1w, device:0
chaiml-horror-sft-v1-5e4-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-horror-sft-v1-5e4-v9-mkmlizer: quantized model in 35.494s
chaiml-horror-sft-v1-5e4-v9-mkmlizer: Processed model ChaiML/Horror-SFT-v1-5e4 in 63.590s
chaiml-horror-sft-v1-5e4-v9-mkmlizer: creating bucket guanaco-mkml-models
chaiml-horror-sft-v1-5e4-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-horror-sft-v1-5e4-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v9
chaiml-horror-sft-v1-5e4-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v9/config.json
chaiml-horror-sft-v1-5e4-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v9/special_tokens_map.json
chaiml-horror-sft-v1-5e4-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v9/tokenizer_config.json
chaiml-horror-sft-v1-5e4-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v9/tokenizer.json
chaiml-horror-sft-v1-5e4-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v9/flywheel_model.0.safetensors
chaiml-horror-sft-v1-5e4-v9-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.30it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.16it/s]
Loading 0: 5%|▌ | 19/363 [00:00<00:07, 44.97it/s]
Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.01it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.06it/s]
Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.59it/s]
Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.18it/s]
Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.58it/s]
Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 44.95it/s]
Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.48it/s]
Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.49it/s]
Loading 0: 20%|█▉ | 71/363 [00:01<00:07, 38.89it/s]
Loading 0: 21%|██ | 76/363 [00:01<00:07, 40.18it/s]
Loading 0: 22%|██▏ | 81/363 [00:01<00:06, 40.45it/s]
Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 42.75it/s]
Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 36.59it/s]
Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 44.02it/s]
Loading 0: 28%|██▊ | 103/363 [00:02<00:05, 43.80it/s]
Loading 0: 30%|███ | 109/363 [00:02<00:05, 47.49it/s]
Loading 0: 31%|███▏ | 114/363 [00:02<00:06, 40.54it/s]
Loading 0: 33%|███▎ | 119/363 [00:02<00:06, 39.35it/s]
Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 43.46it/s]
Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 42.38it/s]
Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 43.25it/s]
Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 42.01it/s]
Loading 0: 40%|████ | 146/363 [00:03<00:07, 30.72it/s]
Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 30.70it/s]
Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.30it/s]
Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 37.98it/s]
Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.37it/s]
Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 42.19it/s]
Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 35.72it/s]
Loading 0: 50%|█████ | 183/363 [00:04<00:04, 43.13it/s]
Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 43.26it/s]
Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 44.86it/s]
Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 45.76it/s]
Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 38.51it/s]
Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 46.37it/s]
Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 47.14it/s]
Loading 0: 61%|██████ | 222/363 [00:05<00:03, 45.40it/s]
Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.64it/s]
Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 32.09it/s]
Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.15it/s]
Loading 0: 67%|██████▋ | 244/363 [00:06<00:02, 40.32it/s]
Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 40.43it/s]
Loading 0: 71%|███████ | 256/363 [00:06<00:02, 45.29it/s]
Loading 0: 72%|███████▏ | 261/363 [00:06<00:02, 46.35it/s]
Loading 0: 73%|███████▎ | 266/363 [00:06<00:02, 39.81it/s]
Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 47.84it/s]
Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 46.84it/s]
Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 46.38it/s]
Loading 0: 80%|████████ | 292/363 [00:07<00:01, 50.40it/s]
Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 48.69it/s]
Loading 0: 84%|████████▎ | 304/363 [00:13<00:20, 2.87it/s]
Loading 0: 85%|████████▍ | 308/363 [00:14<00:15, 3.60it/s]
Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.56it/s]
Loading 0: 88%|████████▊ | 320/363 [00:14<00:05, 7.34it/s]
Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.79it/s]
Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.29it/s]
Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 17.06it/s]
Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.61it/s]
Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 23.67it/s]
Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 30.03it/s]
Loading 0: 99%|█████████▉| 361/363 [00:15<00:00, 32.78it/s]
Job chaiml-horror-sft-v1-5e4-v9-mkmlizer completed after 95.55s with status: succeeded
Stopping job with name chaiml-horror-sft-v1-5e4-v9-mkmlizer
Pipeline stage MKMLizer completed in 96.52s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-horror-sft-v1-5e4-v9
Waiting for inference service chaiml-horror-sft-v1-5e4-v9 to be ready
Inference service chaiml-horror-sft-v1-5e4-v9 ready after 140.79677963256836s
Pipeline stage MKMLDeployer completed in 141.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8249261379241943s
Received healthy response to inference request in 1.3453898429870605s
Received healthy response to inference request in 2.7240710258483887s
Received healthy response to inference request in 2.2615277767181396s
Received healthy response to inference request in 1.9248437881469727s
5 requests
0 failed requests
5th percentile: 1.461280632019043
10th percentile: 1.5771714210510255
20th percentile: 1.8089529991149902
30th percentile: 1.992180585861206
40th percentile: 2.126854181289673
50th percentile: 2.2615277767181396
60th percentile: 2.4465450763702394
70th percentile: 2.631562376022339
80th percentile: 2.74424204826355
90th percentile: 2.784584093093872
95th percentile: 2.804755115509033
99th percentile: 2.820891933441162
mean time: 2.216151714324951
Pipeline stage StressChecker completed in 11.95s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.86s
Shutdown handler de-registered
chaiml-horror-sft-v1-5e4_v9 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-horror-sft-v1-5e4-v9-profiler
Waiting for inference service chaiml-horror-sft-v1-5e4-v9-profiler to be ready
Inference service chaiml-horror-sft-v1-5e4-v9-profiler ready after 150.3579707145691s
Pipeline stage MKMLProfilerDeployer completed in 150.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-horror-sft-v1-5e4-v9-profiler-predictor-00001-deplol4s7l:/code/chaiverse_profiler_1725564970 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-horror-sft-v1-5e4-v9-profiler-predictor-00001-deplol4s7l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725564970 && python profiles.py profile --best_of_n 4 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1725564970/summary.json'
kubectl exec -it chaiml-horror-sft-v1-5e4-v9-profiler-predictor-00001-deplol4s7l --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725564970/summary.json'
Pipeline stage MKMLProfilerRunner completed in 964.33s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-horror-sft-v1-5e4-v9-profiler is running
Tearing down inference service chaiml-horror-sft-v1-5e4-v9-profiler
Service chaiml-horror-sft-v1-5e4-v9-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.64s
Shutdown handler de-registered
chaiml-horror-sft-v1-5e4_v9 status is now inactive due to auto deactivation removed underperforming models
chaiml-horror-sft-v1-5e4_v9 status is now torndown due to DeploymentManager action