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-v1-1e5-v1-mkmlizer
Waiting for job on chaiml-horror-sft-v1-1e5-v1-mkmlizer to finish
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ _____ __ __ ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ /___/ ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ Version: 0.10.1 ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ belonging to: ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ║ ║
chaiml-horror-sft-v1-1e5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-horror-sft-v1-1e5-v1-mkmlizer: Downloaded to shared memory in 281.596s
chaiml-horror-sft-v1-1e5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxf6yumpw, device:0
chaiml-horror-sft-v1-1e5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-horror-sft-v1-1e5-v1-mkmlizer: quantized model in 35.800s
chaiml-horror-sft-v1-1e5-v1-mkmlizer: Processed model ChaiML/Horror-SFT-v1-1e5 in 317.397s
chaiml-horror-sft-v1-1e5-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-horror-sft-v1-1e5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-horror-sft-v1-1e5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-horror-sft-v1-1e5-v1
chaiml-horror-sft-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-1e5-v1/config.json
chaiml-horror-sft-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-1e5-v1/special_tokens_map.json
chaiml-horror-sft-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-1e5-v1/tokenizer_config.json
chaiml-horror-sft-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-1e5-v1/tokenizer.json
chaiml-horror-sft-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-horror-sft-v1-1e5-v1/flywheel_model.0.safetensors
chaiml-horror-sft-v1-1e5-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.56it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.41it/s]
Loading 0: 5%|▌ | 19/363 [00:00<00:07, 48.89it/s]
Loading 0: 7%|▋ | 25/363 [00:00<00:06, 49.85it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:06, 52.78it/s]
Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.80it/s]
Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 48.02it/s]
Loading 0: 13%|█▎ | 49/363 [00:00<00:06, 50.18it/s]
Loading 0: 15%|█▌ | 55/363 [00:01<00:07, 43.84it/s]
Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.14it/s]
Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.93it/s]
Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.57it/s]
Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 38.90it/s]
Loading 0: 23%|██▎ | 83/363 [00:01<00:07, 38.27it/s]
Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.18it/s]
Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 41.96it/s]
Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 40.66it/s]
Loading 0: 30%|███ | 109/363 [00:02<00:05, 49.33it/s]
Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 46.51it/s]
Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 44.88it/s]
Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 48.26it/s]
Loading 0: 36%|███▌ | 131/363 [00:02<00:04, 47.68it/s]
Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 40.50it/s]
Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.10it/s]
Loading 0: 40%|████ | 146/363 [00:03<00:06, 35.52it/s]
Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.39it/s]
Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 41.28it/s]
Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 41.31it/s]
Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 40.81it/s]
Loading 0: 48%|████▊ | 174/363 [00:04<00:04, 44.23it/s]
Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 43.53it/s]
Loading 0: 51%|█████ | 184/363 [00:04<00:04, 44.09it/s]
Loading 0: 52%|█████▏ | 189/363 [00:04<00:03, 44.96it/s]
Loading 0: 53%|█████▎ | 194/363 [00:04<00:04, 39.73it/s]
Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 47.58it/s]
Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 46.32it/s]
Loading 0: 59%|█████▊ | 213/363 [00:04<00:03, 45.75it/s]
Loading 0: 60%|██████ | 218/363 [00:05<00:03, 44.39it/s]
Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 32.87it/s]
Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 33.13it/s]
Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.42it/s]
Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 37.46it/s]
Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 39.72it/s]
Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 41.99it/s]
Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 42.26it/s]
Loading 0: 71%|███████ | 258/363 [00:06<00:02, 41.63it/s]
Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 45.62it/s]
Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 43.84it/s]
Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 42.40it/s]
Loading 0: 77%|███████▋ | 279/363 [00:06<00:01, 43.65it/s]
Loading 0: 78%|███████▊ | 284/363 [00:06<00:02, 36.89it/s]
Loading 0: 80%|████████ | 292/363 [00:06<00:01, 45.33it/s]
Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 44.57it/s]
Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 45.46it/s]
Loading 0: 85%|████████▍ | 308/363 [00:14<00:21, 2.54it/s]
Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.26it/s]
Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.31it/s]
Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.22it/s]
Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.27it/s]
Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.20it/s]
Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.65it/s]
Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 19.94it/s]
Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 26.21it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.66it/s]
Job chaiml-horror-sft-v1-1e5-v1-mkmlizer completed after 342.54s with status: succeeded
Stopping job with name chaiml-horror-sft-v1-1e5-v1-mkmlizer
Pipeline stage MKMLizer completed in 343.61s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-horror-sft-v1-1e5-v1
Waiting for inference service chaiml-horror-sft-v1-1e5-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-horror-sft-v1-1e5-v1 ready after 150.74756836891174s
Pipeline stage MKMLDeployer completed in 151.66s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.783828020095825s
Received healthy response to inference request in 2.059445381164551s
Received healthy response to inference request in 2.053541421890259s
Received healthy response to inference request in 1.9439594745635986s
Received healthy response to inference request in 1.788719892501831s
5 requests
0 failed requests
5th percentile: 1.8197678089141847
10th percentile: 1.850815725326538
20th percentile: 1.912911558151245
30th percentile: 1.9658758640289307
40th percentile: 2.0097086429595947
50th percentile: 2.053541421890259
60th percentile: 2.0559030055999754
70th percentile: 2.0582645893096925
80th percentile: 2.204321908950806
90th percentile: 2.4940749645233153
95th percentile: 2.63895149230957
99th percentile: 2.754852714538574
mean time: 2.125898838043213
Pipeline stage StressChecker completed in 11.30s
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 5.15s
Shutdown handler de-registered
chaiml-horror-sft-v1-1e5_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-horror-sft-v1-1e5-v1-profiler
Waiting for inference service chaiml-horror-sft-v1-1e5-v1-profiler to be ready
Inference service chaiml-horror-sft-v1-1e5-v1-profiler ready after 140.32623267173767s
Pipeline stage MKMLProfilerDeployer completed in 140.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-horror-sft-v1-1e5-v1-profiler-predictor-00001-deplo2t8rr:/code/chaiverse_profiler_1725568170 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-horror-sft-v1-1e5-v1-profiler-predictor-00001-deplo2t8rr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725568170 && 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_1725568170/summary.json'
kubectl exec -it chaiml-horror-sft-v1-1e5-v1-profiler-predictor-00001-deplo2t8rr --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725568170/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-horror-sft-v1-1e5-v1-profiler-predictor-00001-deplo2t8rr:/code/chaiverse_profiler_1725569064 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-horror-sft-v1-1e5-v1-profiler-predictor-00001-deplo2t8rr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725569064 && 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_1725569064/summary.json'
kubectl exec -it chaiml-horror-sft-v1-1e5-v1-profiler-predictor-00001-deplo2t8rr --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725569064/summary.json'
%s, retrying in %s seconds...
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
clean up pipeline due to error=%s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-horror-sft-v1-1e5-v1-profiler is running
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
%s, retrying in %s seconds...
Checking if service chaiml-horror-sft-v1-1e5-v1-profiler is running
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
%s, retrying in %s seconds...
Checking if service chaiml-horror-sft-v1-1e5-v1-profiler is running
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Shutdown handler de-registered
chaiml-horror-sft-v1-1e5_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-horror-sft-v1-1e5_v1 status is now torndown due to DeploymentManager action