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-20250611-retune-1558-v11-mkmlizer
Waiting for job on chaiml-20250611-retune-1558-v11-mkmlizer to finish
Failed to get response for submission chaiml-the-twilight-sag_42496_v1: ('http://chaiml-the-twilight-sag-42496-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50222->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission chaiml-pieck-pieck-fing_26592_v1: HTTPConnectionPool(host='chaiml-pieck-pieck-fing-26592-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-daren-god-of-deat_6797_v1: HTTPConnectionPool(host='chaiml-daren-god-of-deat-6797-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission chaiml-daren-god-of-deat_6797_v1: HTTPConnectionPool(host='chaiml-daren-god-of-deat-6797-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-pieck-pieck-fing_26592_v1: HTTPConnectionPool(host='chaiml-pieck-pieck-fing-26592-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-20250611-retune-1558-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ Version: 0.29.15 ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ https://mk1.ai ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ belonging to: ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ Chai Research Corp. ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-20250611-retune-1558-v11-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-20250611-retune-1558-v11-mkmlizer: Downloaded to shared memory in 20.793s
chaiml-20250611-retune-1558-v11-mkmlizer: Checking if ChaiML/20250611_retune_US_7_to_13_seconds already exists in ChaiML
chaiml-20250611-retune-1558-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpdo1zsbx2, device:0
chaiml-20250611-retune-1558-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-20250611-retune-1558-v11-mkmlizer: quantized model in 19.649s
chaiml-20250611-retune-1558-v11-mkmlizer: Processed model ChaiML/20250611_retune_US_7_to_13_seconds in 40.442s
chaiml-20250611-retune-1558-v11-mkmlizer: creating bucket guanaco-mkml-models
chaiml-20250611-retune-1558-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-20250611-retune-1558-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v11/nvidia
chaiml-20250611-retune-1558-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v11/nvidia/config.json
chaiml-20250611-retune-1558-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v11/nvidia/special_tokens_map.json
chaiml-20250611-retune-1558-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v11/nvidia/tokenizer_config.json
chaiml-20250611-retune-1558-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v11/nvidia/tokenizer.json
chaiml-20250611-retune-1558-v11-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.09it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:06, 45.31it/s]
Loading 0: 6%|▌ | 18/291 [00:00<00:05, 47.67it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:06, 39.17it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 45.36it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 42.53it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 42.09it/s]
Loading 0: 17%|█▋ | 49/291 [00:01<00:05, 47.92it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 44.62it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 43.76it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 48.47it/s]
Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 48.58it/s]
Loading 0: 26%|██▋ | 77/291 [00:01<00:05, 39.00it/s]
Loading 0: 29%|██▊ | 83/291 [00:02<00:06, 30.84it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 31.56it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 38.78it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 39.30it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 39.50it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 45.47it/s]
Loading 0: 41%|████ | 118/291 [00:02<00:04, 42.81it/s]
Loading 0: 42%|████▏ | 123/291 [00:02<00:04, 41.12it/s]
Loading 0: 45%|████▍ | 130/291 [00:03<00:03, 46.15it/s]
Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 43.09it/s]
Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 40.52it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:03, 45.67it/s]
Loading 0: 53%|█████▎ | 154/291 [00:03<00:03, 42.31it/s]
Loading 0: 55%|█████▍ | 159/291 [00:03<00:03, 41.87it/s]
Loading 0: 57%|█████▋ | 165/291 [00:03<00:02, 45.84it/s]
Loading 0: 58%|█████▊ | 170/291 [00:04<00:02, 44.82it/s]
Loading 0: 60%|██████ | 175/291 [00:04<00:02, 46.08it/s]
Loading 0: 62%|██████▏ | 180/291 [00:04<00:02, 45.84it/s]
Loading 0: 64%|██████▍ | 186/291 [00:04<00:02, 39.82it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 28.88it/s]
Loading 0: 67%|██████▋ | 195/291 [00:04<00:03, 29.59it/s]
Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 35.79it/s]
Loading 0: 71%|███████ | 206/291 [00:05<00:02, 37.98it/s]
Loading 0: 73%|███████▎ | 211/291 [00:05<00:02, 39.64it/s]
Loading 0: 75%|███████▍ | 217/291 [00:05<00:01, 39.30it/s]
Loading 0: 76%|███████▋ | 222/291 [00:05<00:01, 40.10it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 45.63it/s]
Loading 0: 80%|████████ | 234/291 [00:05<00:01, 46.30it/s]
Loading 0: 82%|████████▏ | 239/291 [00:05<00:01, 37.98it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 46.01it/s]
Loading 0: 87%|████████▋ | 253/291 [00:06<00:00, 41.79it/s]
Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 40.73it/s]
Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 45.98it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 43.06it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 42.51it/s]
Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 44.13it/s]
Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 38.84it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 33.53it/s]
Job chaiml-20250611-retune-1558-v11-mkmlizer completed after 1924.54s with status: succeeded
Stopping job with name chaiml-20250611-retune-1558-v11-mkmlizer
Pipeline stage MKMLizer completed in 1925.13s
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-20250611-retune-1558-v11
Waiting for inference service chaiml-20250611-retune-1558-v11 to be ready
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-20250611-retune-1558-v11 ready after 332.2047379016876s
Pipeline stage MKMLDeployer completed in 332.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.648567199707031s
Failed to get response for submission chaiml-pieck-pieck-fing_26592_v1: HTTPConnectionPool(host='chaiml-pieck-pieck-fing-26592-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 3.73745059967041s
Received healthy response to inference request in 3.713414430618286s
Received healthy response to inference request in 5.809397459030151s
Received healthy response to inference request in 2.5392799377441406s
5 requests
0 failed requests
5th percentile: 2.77410683631897
10th percentile: 3.008933734893799
20th percentile: 3.478587532043457
30th percentile: 3.718221664428711
40th percentile: 3.7278361320495605
50th percentile: 3.73745059967041
60th percentile: 4.101897239685059
70th percentile: 4.466343879699707
80th percentile: 4.880733251571655
90th percentile: 5.345065355300903
95th percentile: 5.577231407165527
99th percentile: 5.762964248657227
mean time: 4.089621925354004
Pipeline stage StressChecker completed in 22.01s
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 0.87s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Failed to get response for submission chaiml-pieck-pieck-fing_26592_v1: HTTPConnectionPool(host='chaiml-pieck-pieck-fing-26592-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 1.20s
Shutdown handler de-registered
chaiml-20250611-retune-_1558_v11 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...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-20250611-retune-1558-v11-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 5.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-20250611-retune-1558-v11-profiler
Waiting for inference service chaiml-20250611-retune-1558-v11-profiler to be ready
Inference service chaiml-20250611-retune-1558-v11-profiler ready after 50.50617218017578s
Pipeline stage MKMLProfilerDeployer completed in 51.05s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retu99f3e65ee2c8b5725895bbd4ea5130e2-deplo2fp4s:/code/chaiverse_profiler_1752859862 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retu99f3e65ee2c8b5725895bbd4ea5130e2-deplo2fp4s --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752859862 && python profiles.py profile --best_of_n 1 --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 512 --output_tokens 1 --summary /code/chaiverse_profiler_1752859862/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retu99f3e65ee2c8b5725895bbd4ea5130e2-deplo2fp4s:/code/chaiverse_profiler_1752860297 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retu99f3e65ee2c8b5725895bbd4ea5130e2-deplo2fp4s --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752860297 && python profiles.py profile --best_of_n 1 --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 512 --output_tokens 1 --summary /code/chaiverse_profiler_1752860297/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retu99f3e65ee2c8b5725895bbd4ea5130e2-deplo2fp4s:/code/chaiverse_profiler_1752860747 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retu99f3e65ee2c8b5725895bbd4ea5130e2-deplo2fp4s --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752860747 && python profiles.py profile --best_of_n 1 --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 512 --output_tokens 1 --summary /code/chaiverse_profiler_1752860747/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\n\n 0%| | 0/200 [00:00<?, ?it/s]\n 0%| | 1/200 [00:03<11:28, 3.46s/it]\n 1%| | 2/200 [00:03<04:56, 1.50s/it]\n 2%|▏ | 3/200 [00:03<03:03, 1.07it/s]\n 2%|▏ | 4/200 [00:07<06:23, 1.96s/it]\n 2%|▎ | 5/200 [00:10<08:08, 2.51s/it]\n 3%|▎ | 6/200 [00:14<09:18, 2.88s/it]\n 4%|▎ | 7/200 [00:17<09:51, 3.06s/it]\n 4%|▍ | 8/200 [00:21<10:15, 3.21s/it]\n 4%|▍ | 9/200 [00:24<10:25, 3.28s/it]\n 5%|▌ | 10/200 [00:24<07:17, 2.30s/it]\n 6%|▌ | 11/200 [00:28<08:22, 2.66s/it]\n 6%|▌ | 12/200 [00:28<06:02, 1.93s/it]\n 6%|▋ | 13/200 [00:28<04:26, 1.43s/it]\n 7%|▋ | 14/200 [00:32<06:20, 2.04s/it]\n 8%|▊ | 15/200 [00:32<04:38, 1.51s/it]\n 8%|▊ | 16/200 [00:36<06:25, 2.10s/it]\n 8%|▊ | 17/200 [00:36<04:42, 1.54s/it]\n 9%|▉ | 18/200 [00:36<03:31, 1.16s/it]\n 10%|▉ | 19/200 [00:40<05:35, 1.85s/it]\n 10%|█ | 20/200 [00:43<07:10, 2.39s/it]\n 10%|█ | 21/200 [00:43<05:05, 1.71s/it]\n 11%|█ | 22/200 [00:47<06:38, 2.24s/it]\n 12%|█▏ | 23/200 [00:51<07:49, 2.65s/it]\n 12%|█▏ | 24/200 [00:54<08:31, 2.90s/it]\n 12%|█▎ | 25/200 [00:57<08:57, 3.07s/it]\n 13%|█▎ | 26/200 [00:58<06:20, 2.19s/it]\n 14%|█▎ | 27/200 [01:01<07:39, 2.66s/it]\n 14%|█▍ | 28/200 [01:05<08:20, 2.91s/it]\n 14%|█▍ | 29/200 [01:08<08:49, 3.09s/it]\n 15%|█▌ | 30/200 [01:12<09:10, 3.24s/it]\n 16%|█▌ | 31/200 [01:12<06:29, 2.31s/it]\n 16%|█▌ | 32/200 [01:16<07:29, 2.68s/it]\n 16%|█▋ | 33/200 [01:19<08:13, 2.96s/it]\n 17%|█▋ | 34/200 [01:23<08:37, 3.12s/it]\n 18%|█▊ | 35/200 [01:23<06:06, 2.22s/it]\n 18%|█▊ | 36/200 [01:26<07:08, 2.61s/it]\n 18%|█▊ | 37/200 [01:27<05:10, 1.91s/it]\n 19%|█▉ | 38/200 [01:27<03:49, 1.42s/it]\n 20%|█▉ | 39/200 [01:30<05:31, 2.06s/it]\n 20%|██ | 40/200 [01:34<06:43, 2.52s/it]\n 20%|██ | 41/200 [01:38<07:25, 2.80s/it]\n 21%|██ | 42/200 [01:41<07:55, 3.01s/it]\n 22%|██▏ | 43/200 [01:45<08:16, 3.16s/it]\n 22%|██▏ | 44/200 [01:45<05:51, 2.25s/it]\n 22%|██▎ | 45/200 [01:48<06:46, 2.62s/it]\n 23%|██▎ | 46/200 [01:52<07:29, 2.92s/it]\n 24%|██▎ | 47/200 [01:52<05:18, 2.08s/it]\n 24%|██▍ | 48/200 [01:55<06:22, 2.51s/it]\n 24%|██▍ | 49/200 [01:56<04:36, 1.83s/it]\n 25%|██▌ | 50/200 [01:59<05:54, 2.36s/it]\n 26%|██▌ | 51/200 [01:59<04:11, 1.69s/it]\n 26%|██▌ | 52/200 [02:03<05:36, 2.27s/it]\n 26%|██▋ | 53/200 [02:03<03:59, 1.63s/it]\n 27%|██▋ | 54/200 [02:07<05:25, 2.23s/it]\n 28%|██▊ | 55/200 [02:10<06:17, 2.60s/it]\n 28%|██▊ | 56/200 [02:14<06:53, 2.87s/it]\n 28%|██▊ | 57/200 [02:17<07:18, 3.07s/it]\n 29%|██▉ | 58/200 [02:17<05:10, 2.18s/it]\n 30%|██▉ | 59/200 [02:18<03:47, 1.61s/it]\n 30%|███ | 60/200 [02:21<05:06, 2.19s/it]\n 30%|███ | 61/200 [02:21<03:44, 1.61s/it]\n 31%|███ | 62/200 [02:25<05:06, 2.22s/it]\n 32%|███▏ | 63/200 [02:25<03:43, 1.63s/it]\n 32%|███▏ | 64/200 [02:26<02:46, 1.22s/it]\n 32%|███▎ | 65/200 [02:29<04:18, 1.91s/it]\n 33%|███▎ | 66/200 [02:33<05:19, 2.38s/it]\n 34%|███▎ | 67/200 [02:36<06:00, 2.71s/it]\n 34%|███▍ | 68/200 [02:40<06:28, 2.94s/it]\n 34%|███▍ | 69/200 [02:43<06:54, 3.16s/it]\n 35%|███▌ | 70/200 [02:47<07:04, 3.27s/it]\n 36%|███▌ | 71/200 [02:50<07:10, 3.33s/it]\n 36%|███▌ | 72/200 [02:50<05:03, 2.37s/it]\n 36%|███▋ | 73/200 [02:51<03:41, 1.74s/it]\n 37%|███▋ | 74/200 [02:54<04:43, 2.25s/it]\n 38%|███▊ | 75/200 [02:58<05:31, 2.65s/it]\n 38%|███▊ | 76/200 [02:58<03:54, 1.89s/it]\n 38%|███▊ | 77/200 [02:58<02:53, 1.41s/it]\n 39%|███▉ | 78/200 [03:02<04:07, 2.03s/it]\n 40%|███▉ | 79/200 [03:02<03:01, 1.50s/it]\n 40%|████ | 80/200 [03:05<04:12, 2.10s/it]\n 40%|████ | 81/200 [03:09<05:06, 2.57s/it]\n 41%|████ | 82/200 [03:09<03:36, 1.84s/it]\n 42%|████▏ | 83/200 [03:13<04:33, 2.34s/it]\n 42%|████▏ | 84/200 [03:16<05:15, 2.72s/it]\n 42%|████▎ | 85/200 [03:16<03:43, 1.94s/it]\n 43%|████▎ | 86/200 [03:20<04:36, 2.43s/it]\n 44%|████▎ | 87/200 [03:20<03:20, 1.78s/it]\n 44%|████▍ | 88/200 [03:20<02:28, 1.32s/it]\n 44%|████▍ | 89/200 [03:21<01:51, 1.01s/it]\n 45%|████▌ | 90/200 [03:21<01:26, 1.28it/s]\n 46%|████▌ | 91/200 [03:21<01:09, 1.58it/s]\n 46%|████▌ | 92/200 [03:25<02:41, 1.49s/it]\n 46%|████▋ | 93/200 [03:25<02:00, 1.12s/it]\n 47%|████▋ | 94/200 [03:29<03:14, 1.84s/it]\n 48%|████▊ | 95/200 [03:29<02:23, 1.37s/it]\n 48%|████▊ | 96/200 [03:29<01:48, 1.04s/it]\n 48%|████▊ | 97/200 [03:33<03:02, 1.77s/it]\n 49%|████▉ | 98/200 [03:36<03:54, 2.30s/it]\n 50%|████▉ | 99/200 [03:36<02:46, 1.65s/it]\n 50%|█████ | 100/200 [03:37<02:04, 1.24s/it]\n 50%|█████ | 101/200 [03:40<03:10, 1.92s/it]\n 51%|█████ | 102/200 [03:40<02:19, 1.42s/it]\n 52%|█████▏ | 103/200 [03:44<03:18, 2.04s/it]\n 52%|█████▏ | 104/200 [03:47<03:56, 2.46s/it]\n 52%|█████▎ | 105/200 [03:51<04:28, 2.83s/it]\n 53%|█████▎ | 106/200 [03:51<03:09, 2.02s/it]\n 54%|█████▎ | 107/200 [03:51<02:18, 1.49s/it]\n 54%|█████▍ | 108/200 [03:55<03:11, 2.08s/it]\n 55%|█████▍ | 109/200 [03:55<02:19, 1.53s/it]\n 55%|█████▌ | 110/200 [03:58<03:09, 2.11s/it]\n 56%|█████▌ | 111/200 [03:59<02:18, 1.55s/it]\n 56%|█████▌ | 112/200 [03:59<01:42, 1.17s/it]\n 56%|█████▋ | 113/200 [04:02<02:42, 1.87s/it]\n 57%|█████▋ | 114/200 [04:03<01:58, 1.38s/it]\n 57%|█████▊ | 115/200 [04:06<02:52, 2.03s/it]\n 58%|█████▊ | 116/200 [04:07<02:06, 1.50s/it]\n 58%|█████▊ | 117/200 [04:10<02:59, 2.17s/it]\n 59%|█████▉ | 118/200 [04:14<03:31, 2.57s/it]\n 60%|█████▉ | 119/200 [04:17<03:52, 2.87s/it]\n 60%|██████ | 120/200 [04:21<04:07, 3.09s/it]\n 60%|██████ | 121/200 [04:21<02:53, 2.20s/it]\n 61%|██████ | 122/200 [04:21<02:06, 1.62s/it]\n 62%|██████▏ | 123/200 [04:25<02:48, 2.19s/it]\n 62%|██████▏ | 124/200 [04:25<02:02, 1.61s/it]\n 62%|██████▎ | 125/200 [04:29<02:42, 2.16s/it]\n 63%|██████▎ | 126/200 [04:32<03:08, 2.55s/it]\n 64%|██████▎ | 127/200 [04:35<03:25, 2.82s/it]\n 64%|██████▍ | 128/200 [04:36<02:27, 2.05s/it]\n 64%|██████▍ | 129/200 [04:36<01:47, 1.51s/it]\n 65%|██████▌ | 130/200 [04:36<01:19, 1.14s/it]\n 66%|██████▌ | 131/200 [04:37<01:00, 1.14it/s]\n 66%|██████▌ | 132/200 [04:37<00:47, 1.43it/s]\n 66%|██████▋ | 133/200 [04:37<00:38, 1.75it/s]\n 67%|██████▋ | 134/200 [04:37<00:31, 2.07it/s]\n 68%|██████▊ | 135/200 [04:41<01:30, 1.39s/it]\n 68%|██████▊ | 136/200 [04:41<01:07, 1.06s/it]\n 68%|██████▊ | 137/200 [04:45<01:54, 1.82s/it]\n 69%|██████▉ | 138/200 [04:48<02:22, 2.29s/it]\n 70%|██████▉ | 139/200 [04:48<01:40, 1.64s/it]\n 70%|███████ | 140/200 [04:49<01:13, 1.23s/it]\n 70%|███████ | 141/200 [04:52<01:53, 1.92s/it]\n 71%|███████ | 142/200 [04:56<02:21, 2.44s/it]\n 72%|███████▏ | 143/200 [04:59<02:37, 2.76s/it]\n 72%|███████▏ | 144/200 [04:59<01:50, 1.97s/it]\n 72%|███████▎ | 145/200 [05:03<02:14, 2.44s/it]\n 73%|███████▎ | 146/200 [05:03<01:36, 1.78s/it]\n 74%|███████▎ | 147/200 [05:07<02:02, 2.30s/it]\n 74%|███████▍ | 148/200 [05:10<02:21, 2.72s/it]\n 74%|███████▍ | 149/200 [05:10<01:39, 1.94s/it]\n 75%|███████▌ | 150/200 [05:11<01:12, 1.44s/it]\n 76%|███████▌ | 151/200 [05:14<01:41, 2.08s/it]\n 76%|███████▌ | 152/200 [05:18<02:02, 2.55s/it]\n 76%|███████▋ | 153/200 [05:22<02:14, 2.86s/it]\n 77%|███████▋ | 154/200 [05:25<02:21, 3.08s/it]\n 78%|███████▊ | 155/200 [05:29<02:24, 3.20s/it]\n 78%|███████▊ | 156/200 [05:32<02:25, 3.30s/it]\n 78%|███████▊ | 157/200 [05:36<02:24, 3.36s/it]\n 79%|███████▉ | 158/200 [05:36<01:40, 2.39s/it]\n 80%|███████▉ | 159/200 [05:36<01:11, 1.75s/it]\n 80%|████████ | 160/200 [05:36<00:52, 1.31s/it]\n 80%|████████ | 161/200 [05:37<00:38, 1.00it/s]\n 81%|████████ | 162/200 [05:40<01:06, 1.74s/it]\n 82%|████████▏ | 163/200 [05:44<01:23, 2.27s/it]\n 82%|████████▏ | 164/200 [05:44<00:59, 1.66s/it]\n 82%|████████▎ | 165/200 [05:47<01:17, 2.22s/it]\n 83%|████████▎ | 166/200 [05:51<01:28, 2.59s/it]\n 84%|████████▎ | 167/200 [05:51<01:02, 1.89s/it]\n 84%|████████▍ | 168/200 [05:54<01:15, 2.36s/it]\n 84%|████████▍ | 169/200 [05:58<01:25, 2.74s/it]\n 85%|████████▌ | 170/200 [06:02<01:29, 2.97s/it]\n 86%|████████▌ | 171/200 [06:02<01:01, 2.11s/it]\n 86%|████████▌ | 172/200 [06:05<01:10, 2.53s/it]\n 86%|████████▋ | 173/200 [06:09<01:17, 2.89s/it]\n 87%|████████▋ | 174/200 [06:09<00:53, 2.06s/it]\n 88%|████████▊ | 175/200 [06:09<00:38, 1.52s/it]\n 88%|████████▊ | 176/200 [06:13<00:51, 2.13s/it]\n 88%|████████▊ | 177/200 [06:13<00:36, 1.57s/it]\n 89%|████████▉ | 178/200 [06:17<00:46, 2.13s/it]\n 90%|████████▉ | 179/200 [06:17<00:32, 1.57s/it]\n 90%|█████████ | 180/200 [06:17<00:23, 1.18s/it]\n 90%|█████████ | 181/200 [06:21<00:35, 1.88s/it]\n 91%|█████████ | 182/200 [06:24<00:43, 2.41s/it]\n 92%|█████████▏| 183/200 [06:28<00:46, 2.74s/it]\n 92%|█████████▏| 184/200 [06:28<00:31, 1.95s/it]\n 92%|█████████▎| 185/200 [06:28<00:21, 1.44s/it]\n 93%|█████████▎| 186/200 [06:28<00:15, 1.09s/it]\n 94%|█████████▎| 187/200 [06:29<00:10, 1.19it/s]\n 94%|█████████▍| 188/200 [06:32<00:19, 1.65s/it]\n 94%|█████████▍| 189/200 [06:32<00:13, 1.24s/it]\n 95%|█████████▌| 190/200 [06:36<00:19, 1.92s/it]\n 96%|█████████▌| 191/200 [06:39<00:21, 2.38s/it]\n 96%|█████████▌| 192/200 [06:43<00:21, 2.71s/it]\n 96%|█████████▋| 193/200 [06:47<00:20, 2.98s/it]\n 97%|█████████▋| 194/200 [06:50<00:18, 3.12s/it]\n 98%|█████████▊| 195/200 [06:50<00:11, 2.27s/it]\n 98%|█████████▊| 196/200 [06:54<00:10, 2.63s/it]\n 98%|█████████▊| 197/200 [06:57<00:08, 2.89s/it]\n 99%|█████████▉| 198/200 [06:58<00:04, 2.10s/it]\n100%|█████████▉| 199/200 [06:58<00:01, 1.55s/it]\n100%|██████████| 200/200 [07:01<00:00, 2.15s/it]\n100%|██████████| 200/200 [07:01<00:00, 2.11s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1752860747/profiles.py", line 621, in <module>\n cli()\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__\n return self.main(*args, **kwargs)\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main\n rv = self.invoke(ctx)\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke\n return _process_result(sub_ctx.command.invoke(sub_ctx))\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke\n return ctx.invoke(self.callback, **ctx.params)\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke\n return __callback(*args, **kwargs)\n File "/code/chaiverse_profiler_1752860747/profiles.py", line 112, in profile_batches\n profiles = run_batch_profile_with_auto_batch(target, batches, settings, auto_batch, output)\n File "/code/chaiverse_profiler_1752860747/profiles.py", line 163, in run_batch_profile_with_auto_batch\n profiles = run_batch_profile(target, batches, settings, output)\n File "/code/chaiverse_profiler_1752860747/profiles.py", line 277, in run_batch_profile\n analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n f.write(json.dumps(row) + \'\\n\')\n File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n return _default_encoder.encode(obj)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n chunks = self.iterencode(o, _one_shot=True)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n return _iterencode(o, 0)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 421.83955788612366\nerrors 86\nmean length: 1.71\n\nthroughput (request / second): 0.47411390482727167\nthroughput (character / second): 0.8107347772546346\naverage request duration (s) 2.109032518863678\n50%ile request duration (s) 3.4579267501831055\n75%ile request duration (s) 3.522073805332184\n90%ile request duration (s) 3.603185296058655\n95%ile request duration (s) 3.6392194628715515\n\nmean input tokens 2.0\nmean output tokens 1.0\n\n\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-20250611-retune-1558-v11-profiler is running
Tearing down inference service chaiml-20250611-retune-1558-v11-profiler
Service chaiml-20250611-retune-1558-v11-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.52s
Shutdown handler de-registered
chaiml-20250611-retune-_1558_v11 status is now inactive due to auto deactivation removed underperforming models
chaiml-20250611-retune-_1558_v11 status is now torndown due to DeploymentManager action
chaiml-20250611-retune-_1558_v11 status is now torndown due to DeploymentManager action