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-prm-v1-pair-def-16871-v10-mkmlizer
Waiting for job on chaiml-prm-v1-pair-def-16871-v10-mkmlizer to finish
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ Version: 0.30.2 ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ https://mk1.ai ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ belonging to: ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ Chai Research Corp. ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ║ ║
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: Downloaded to shared memory in 21.185s
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: Checking if ChaiML/prm-v1-pair_default8b-cosine-lr26e1 already exists in ChaiML
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpuzhd5ghg, device:0
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: quantized model in 16.359s
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: Processed model ChaiML/prm-v1-pair_default8b-cosine-lr26e1 in 37.545s
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: creating bucket guanaco-mkml-models
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-prm-v1-pair-def-16871-v10/nvidia
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-prm-v1-pair-def-16871-v10/nvidia/config.json
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-prm-v1-pair-def-16871-v10/nvidia/special_tokens_map.json
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-prm-v1-pair-def-16871-v10/nvidia/tokenizer_config.json
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-prm-v1-pair-def-16871-v10/nvidia/tokenizer.json
chaiml-prm-v1-pair-def-16871-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-prm-v1-pair-def-16871-v10/nvidia/flywheel_model.0.safetensors
chaiml-prm-v1-pair-def-16871-v10-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 37.58it/s]
Loading 0: 5%|▍ | 14/291 [00:00<00:05, 54.21it/s]
Loading 0: 8%|▊ | 23/291 [00:00<00:04, 57.05it/s]
Loading 0: 11%|█ | 32/291 [00:00<00:04, 59.40it/s]
Loading 0: 14%|█▍ | 41/291 [00:00<00:04, 60.76it/s]
Loading 0: 17%|█▋ | 50/291 [00:00<00:03, 61.47it/s]
Loading 0: 20%|██ | 59/291 [00:00<00:03, 62.20it/s]
Loading 0: 23%|██▎ | 68/291 [00:01<00:03, 62.26it/s]
Loading 0: 26%|██▋ | 77/291 [00:01<00:03, 60.79it/s]
Loading 0: 29%|██▉ | 84/291 [00:01<00:04, 49.89it/s]
Loading 0: 31%|███ | 90/291 [00:01<00:04, 43.10it/s]
Loading 0: 33%|███▎ | 95/291 [00:02<00:06, 29.47it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 32.19it/s]
Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 40.58it/s]
Loading 0: 39%|███▉ | 114/291 [00:02<00:04, 40.83it/s]
Loading 0: 42%|████▏ | 122/291 [00:02<00:03, 45.19it/s]
Loading 0: 45%|████▌ | 131/291 [00:02<00:03, 50.23it/s]
Loading 0: 48%|████▊ | 140/291 [00:02<00:02, 54.10it/s]
Loading 0: 51%|█████ | 149/291 [00:02<00:02, 56.48it/s]
Loading 0: 54%|█████▍ | 158/291 [00:03<00:02, 58.69it/s]
Loading 0: 57%|█████▋ | 167/291 [00:03<00:02, 60.18it/s]
Loading 0: 61%|██████ | 177/291 [00:03<00:01, 65.41it/s]
Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 65.62it/s]
Loading 0: 66%|██████▌ | 191/291 [00:03<00:02, 47.69it/s]
Loading 0: 68%|██████▊ | 199/291 [00:03<00:01, 49.90it/s]
Loading 0: 71%|███████▏ | 208/291 [00:04<00:01, 53.46it/s]
Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 56.06it/s]
Loading 0: 78%|███████▊ | 226/291 [00:04<00:01, 57.91it/s]
Loading 0: 80%|████████ | 234/291 [00:04<00:00, 62.76it/s]
Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 59.27it/s]
Loading 0: 85%|████████▌ | 248/291 [00:04<00:00, 55.03it/s]
Loading 0: 88%|████████▊ | 257/291 [00:04<00:00, 56.55it/s]
Loading 0: 91%|█████████▏| 266/291 [00:05<00:00, 58.05it/s]
Loading 0: 93%|█████████▎| 272/291 [00:05<00:00, 57.20it/s]
Loading 0: 96%|█████████▌| 279/291 [00:05<00:00, 60.25it/s]
Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 52.94it/s]
Job chaiml-prm-v1-pair-def-16871-v10-mkmlizer completed after 94.11s with status: succeeded
Stopping job with name chaiml-prm-v1-pair-def-16871-v10-mkmlizer
Pipeline stage MKMLizer completed in 94.69s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-prm-v1-pair-def-16871-v10
Waiting for inference service chaiml-prm-v1-pair-def-16871-v10 to be ready
Inference service chaiml-prm-v1-pair-def-16871-v10 ready after 151.1756558418274s
Pipeline stage MKMLDeployer completed in 151.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4868297576904297s
Received healthy response to inference request in 3.322160243988037s
Received healthy response to inference request in 2.3391501903533936s
Received healthy response to inference request in 2.7895970344543457s
Received healthy response to inference request in 2.0369694232940674s
5 requests
0 failed requests
5th percentile: 2.0974055767059325
10th percentile: 2.1578417301177977
20th percentile: 2.2787140369415284
30th percentile: 2.3686861038208007
40th percentile: 2.4277579307556154
50th percentile: 2.4868297576904297
60th percentile: 2.607936668395996
70th percentile: 2.7290435791015626
80th percentile: 2.896109676361084
90th percentile: 3.1091349601745604
95th percentile: 3.2156476020812987
99th percentile: 3.3008577156066896
mean time: 2.594941329956055
Pipeline stage StressChecker completed in 14.30s
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 0.64s
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 0.69s
Shutdown handler de-registered
chaiml-prm-v1-pair-def_16871_v10 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
%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-prm-v1-pair-def-16871-v10-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 0.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-prm-v1-pair-def-16871-v10-profiler
Waiting for inference service chaiml-prm-v1-pair-def-16871-v10-profiler to be ready
Inference service chaiml-prm-v1-pair-def-16871-v10-profiler ready after 60.60682821273804s
Pipeline stage MKMLProfilerDeployer completed in 61.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deplo2d6xq:/code/chaiverse_profiler_1763429218 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deplo2d6xq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763429218 && python profiles.py profile --best_of_n 8 --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 1536 --output_tokens 1 --summary /code/chaiverse_profiler_1763429218/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deplo2d6xq:/code/chaiverse_profiler_1763430026 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deplo2d6xq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763430026 && python profiles.py profile --best_of_n 8 --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 1536 --output_tokens 1 --summary /code/chaiverse_profiler_1763430026/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deplo2d6xq:/code/chaiverse_profiler_1763430782 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deplo2d6xq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763430782 && python profiles.py profile --best_of_n 8 --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 1536 --output_tokens 1 --summary /code/chaiverse_profiler_1763430782/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 [00:06<20:29, 6.18s/it]\n 1%| | 2/200 [00:12<20:25, 6.19s/it]\n 2%|▏ | 3/200 [00:18<20:24, 6.22s/it]\n 2%|▏ | 4/200 [00:19<12:55, 3.96s/it]\n 2%|▎ | 5/200 [00:19<08:56, 2.75s/it]\n 3%|▎ | 6/200 [00:20<06:28, 2.00s/it]\n 4%|▎ | 7/200 [00:20<04:54, 1.52s/it]\n 4%|▍ | 8/200 [00:21<03:51, 1.21s/it]\n 4%|▍ | 9/200 [00:21<03:14, 1.02s/it]\n 5%|▌ | 10/200 [00:28<08:17, 2.62s/it]\n 6%|▌ | 11/200 [00:28<06:18, 2.00s/it]\n 6%|▌ | 12/200 [00:35<10:22, 3.31s/it]\n 6%|▋ | 13/200 [00:35<07:39, 2.46s/it]\n 7%|▋ | 14/200 [00:36<05:49, 1.88s/it]\n 8%|▊ | 15/200 [00:42<09:54, 3.21s/it]\n 8%|▊ | 16/200 [00:48<12:34, 4.10s/it]\n 8%|▊ | 17/200 [00:49<09:13, 3.02s/it]\n 9%|▉ | 18/200 [00:49<06:54, 2.28s/it]\n 10%|▉ | 19/200 [00:55<10:34, 3.50s/it]\n 10%|█ | 20/200 [00:56<07:49, 2.61s/it]\n 10%|█ | 21/200 [01:02<11:09, 3.74s/it]\n 11%|█ | 22/200 [01:03<08:12, 2.77s/it]\n 12%|█▏ | 23/200 [01:03<06:11, 2.10s/it]\n 12%|█▏ | 24/200 [01:10<09:59, 3.41s/it]\n 12%|█▎ | 25/200 [01:10<07:23, 2.54s/it]\n 13%|█▎ | 26/200 [01:11<05:42, 1.97s/it]\n 14%|█▎ | 27/200 [01:17<09:30, 3.30s/it]\n 14%|█▍ | 28/200 [01:24<12:03, 4.21s/it]\n 14%|█▍ | 29/200 [01:30<13:43, 4.82s/it]\n 15%|█▌ | 30/200 [01:36<14:56, 5.27s/it]\n 16%|█▌ | 31/200 [01:37<10:49, 3.84s/it]\n 16%|█▌ | 32/200 [01:37<07:59, 2.85s/it]\n 16%|█▋ | 33/200 [01:38<06:01, 2.16s/it]\n 17%|█▋ | 34/200 [01:44<09:27, 3.42s/it]\n 18%|█▊ | 35/200 [01:50<11:41, 4.25s/it]\n 18%|█▊ | 36/200 [01:51<08:34, 3.13s/it]\n 18%|█▊ | 37/200 [01:52<06:23, 2.35s/it]\n 19%|█▉ | 38/200 [01:52<05:03, 1.88s/it]\n 20%|█▉ | 39/200 [01:53<04:05, 1.53s/it]\n 20%|██ | 40/200 [01:54<03:19, 1.25s/it]\n 20%|██ | 41/200 [01:54<02:44, 1.04s/it]\n 21%|██ | 42/200 [02:00<06:54, 2.62s/it]\n 22%|██▏ | 43/200 [02:01<05:12, 1.99s/it]\n 22%|██▏ | 44/200 [02:07<08:31, 3.28s/it]\n 22%|██▎ | 45/200 [02:08<06:19, 2.45s/it]\n 23%|██▎ | 46/200 [02:08<04:52, 1.90s/it]\n 24%|██▎ | 47/200 [02:09<03:48, 1.50s/it]\n 24%|██▍ | 48/200 [02:10<03:04, 1.21s/it]\n 24%|██▍ | 49/200 [02:16<06:50, 2.72s/it]\n 25%|██▌ | 50/200 [02:22<09:27, 3.78s/it]\n 26%|██▌ | 51/200 [02:28<11:16, 4.54s/it]\n 26%|██▌ | 52/200 [02:34<12:24, 5.03s/it]\n 26%|██▋ | 53/200 [02:41<13:20, 5.45s/it]\n 27%|██▋ | 54/200 [02:47<13:51, 5.69s/it]\n 28%|██▊ | 55/200 [02:48<10:00, 4.14s/it]\n 28%|██▊ | 56/200 [02:54<11:30, 4.79s/it]\n 28%|██▊ | 57/200 [03:00<12:23, 5.20s/it]\n 29%|██▉ | 58/200 [03:06<13:00, 5.50s/it]\n 30%|██▉ | 59/200 [03:13<13:28, 5.74s/it]\n 30%|███ | 60/200 [03:19<13:40, 5.86s/it]\n 30%|███ | 61/200 [03:25<13:50, 5.97s/it]\n 31%|███ | 62/200 [03:31<13:56, 6.06s/it]\n 32%|███▏ | 63/200 [03:38<13:56, 6.11s/it]\n 32%|███▏ | 64/200 [03:44<13:52, 6.12s/it]\n 32%|███▎ | 65/200 [03:44<10:04, 4.48s/it]\n 33%|███▎ | 66/200 [03:45<07:22, 3.30s/it]\n 34%|███▎ | 67/200 [03:45<05:29, 2.48s/it]\n 34%|███▍ | 68/200 [03:52<07:59, 3.63s/it]\n 34%|███▍ | 69/200 [03:52<05:56, 2.72s/it]\n 35%|███▌ | 70/200 [03:53<04:29, 2.07s/it]\n 36%|███▌ | 71/200 [03:59<07:09, 3.33s/it]\n 36%|███▌ | 72/200 [04:00<05:22, 2.52s/it]\n 36%|███▋ | 73/200 [04:06<07:44, 3.66s/it]\n 37%|███▋ | 74/200 [04:12<09:17, 4.43s/it]\n 38%|███▊ | 75/200 [04:19<10:24, 4.99s/it]\n 38%|███▊ | 76/200 [04:19<07:31, 3.64s/it]\n 38%|███▊ | 77/200 [04:26<09:11, 4.48s/it]\n 39%|███▉ | 78/200 [04:26<06:40, 3.28s/it]\n 40%|███▉ | 79/200 [04:27<05:01, 2.49s/it]\n 40%|████ | 80/200 [04:27<03:50, 1.92s/it]\n 40%|████ | 81/200 [04:28<02:59, 1.51s/it]\n 41%|████ | 82/200 [04:28<02:24, 1.23s/it]\n 42%|████▏ | 83/200 [04:35<05:25, 2.78s/it]\n 42%|████▏ | 84/200 [04:41<07:22, 3.81s/it]\n 42%|████▎ | 85/200 [04:47<08:40, 4.53s/it]\n 43%|████▎ | 86/200 [04:48<06:22, 3.35s/it]\n 44%|████▎ | 87/200 [04:48<04:44, 2.52s/it]\n 44%|████▍ | 88/200 [04:55<06:46, 3.63s/it]\n 44%|████▍ | 89/200 [04:55<05:00, 2.71s/it]\n 45%|████▌ | 90/200 [05:02<06:58, 3.80s/it]\n 46%|████▌ | 91/200 [05:02<05:06, 2.81s/it]\n 46%|████▌ | 92/200 [05:08<06:54, 3.84s/it]\n 46%|████▋ | 93/200 [05:14<08:06, 4.55s/it]\n 47%|████▋ | 94/200 [05:21<08:56, 5.07s/it]\n 48%|████▊ | 95/200 [05:27<09:30, 5.43s/it]\n 48%|████▊ | 96/200 [05:33<09:49, 5.67s/it]\n 48%|████▊ | 97/200 [05:39<10:00, 5.83s/it]\n 49%|████▉ | 98/200 [05:46<10:08, 5.96s/it]\n 50%|████▉ | 99/200 [05:52<10:08, 6.02s/it]\n 50%|█████ | 100/200 [05:58<10:10, 6.10s/it]\n 50%|█████ | 101/200 [06:04<10:07, 6.13s/it]\n 51%|█████ | 102/200 [06:05<07:14, 4.44s/it]\n 52%|█████▏ | 103/200 [06:11<08:04, 5.00s/it]\n 52%|█████▏ | 104/200 [06:12<05:50, 3.65s/it]\n 52%|█████▎ | 105/200 [06:18<07:01, 4.44s/it]\n 53%|█████▎ | 106/200 [06:24<07:49, 5.00s/it]\n 54%|█████▎ | 107/200 [06:25<05:39, 3.65s/it]\n 54%|█████▍ | 108/200 [06:25<04:10, 2.73s/it]\n 55%|█████▍ | 109/200 [06:32<05:45, 3.79s/it]\n 55%|█████▌ | 110/200 [06:38<06:45, 4.50s/it]\n 56%|█████▌ | 111/200 [06:38<04:53, 3.30s/it]\n 56%|█████▌ | 112/200 [06:45<06:08, 4.19s/it]\n 56%|█████▋ | 113/200 [06:45<04:27, 3.07s/it]\n 57%|█████▋ | 114/200 [06:51<05:50, 4.08s/it]\n 57%|█████▊ | 115/200 [06:52<04:15, 3.00s/it]\n 58%|█████▊ | 116/200 [06:53<03:12, 2.29s/it]\n 58%|█████▊ | 117/200 [06:59<04:47, 3.46s/it]\n 59%|█████▉ | 118/200 [07:05<05:53, 4.31s/it]\n 60%|█████▉ | 119/200 [07:06<04:16, 3.16s/it]\n 60%|██████ | 120/200 [07:12<05:27, 4.09s/it]\n 60%|██████ | 121/200 [07:18<06:14, 4.74s/it]\n 61%|██████ | 122/200 [07:24<06:41, 5.15s/it]\n 62%|██████▏ | 123/200 [07:30<07:02, 5.49s/it]\n 62%|██████▏ | 124/200 [07:31<05:03, 4.00s/it]\n 62%|██████▎ | 125/200 [07:32<03:44, 2.99s/it]\n 63%|██████▎ | 126/200 [07:38<04:53, 3.96s/it]\n 64%|██████▎ | 127/200 [07:44<05:39, 4.66s/it]\n 64%|██████▍ | 128/200 [07:50<06:08, 5.11s/it]\n 64%|██████▍ | 129/200 [07:51<04:24, 3.73s/it]\n 65%|██████▌ | 130/200 [07:57<05:15, 4.51s/it]\n 66%|██████▌ | 131/200 [08:03<05:47, 5.03s/it]\n 66%|██████▌ | 132/200 [08:10<06:05, 5.38s/it]\n 66%|██████▋ | 133/200 [08:10<04:22, 3.92s/it]\n 67%|██████▋ | 134/200 [08:16<05:03, 4.60s/it]\n 68%|██████▊ | 135/200 [08:17<03:40, 3.40s/it]\n 68%|██████▊ | 136/200 [08:17<02:42, 2.54s/it]\n 68%|██████▊ | 137/200 [08:24<03:49, 3.64s/it]\n 69%|██████▉ | 138/200 [08:30<04:34, 4.43s/it]\n 70%|██████▉ | 139/200 [08:30<03:17, 3.25s/it]\n 70%|███████ | 140/200 [08:37<04:09, 4.16s/it]\n 70%|███████ | 141/200 [08:37<03:00, 3.06s/it]\n 71%|███████ | 142/200 [08:38<02:15, 2.33s/it]\n 72%|███████▏ | 143/200 [08:38<01:42, 1.81s/it]\n 72%|███████▏ | 144/200 [08:45<02:55, 3.14s/it]\n 72%|███████▎ | 145/200 [08:51<03:41, 4.02s/it]\n 73%|███████▎ | 146/200 [08:57<04:13, 4.70s/it]\n 74%|███████▎ | 147/200 [08:57<03:02, 3.45s/it]\n 74%|███████▍ | 148/200 [08:58<02:15, 2.61s/it]\n 74%|███████▍ | 149/200 [09:04<03:09, 3.71s/it]\n 75%|███████▌ | 150/200 [09:11<03:45, 4.51s/it]\n 76%|███████▌ | 151/200 [09:17<04:06, 5.04s/it]\n 76%|███████▌ | 152/200 [09:23<04:21, 5.44s/it]\n 76%|███████▋ | 153/200 [09:30<04:27, 5.69s/it]\n 77%|███████▋ | 154/200 [09:30<03:10, 4.13s/it]\n 78%|███████▊ | 155/200 [09:37<03:35, 4.80s/it]\n 78%|███████▊ | 156/200 [09:37<02:34, 3.51s/it]\n 78%|███████▊ | 157/200 [09:43<03:07, 4.37s/it]\n 79%|███████▉ | 158/200 [09:50<03:28, 4.96s/it]\n 80%|███████▉ | 159/200 [09:50<02:28, 3.63s/it]\n 80%|████████ | 160/200 [09:57<02:56, 4.41s/it]\n 80%|████████ | 161/200 [10:03<03:13, 4.95s/it]\n 81%|████████ | 162/200 [10:03<02:18, 3.65s/it]\n 82%|████████▏ | 163/200 [10:04<01:40, 2.73s/it]\n 82%|████████▏ | 164/200 [10:10<02:17, 3.81s/it]\n 82%|████████▎ | 165/200 [10:11<01:38, 2.82s/it]\n 83%|████████▎ | 166/200 [10:17<02:12, 3.89s/it]\n 84%|████████▎ | 167/200 [10:18<01:34, 2.88s/it]\n 84%|████████▍ | 168/200 [10:24<02:04, 3.88s/it]\n 84%|████████▍ | 169/200 [10:24<01:28, 2.87s/it]\n 85%|████████▌ | 170/200 [10:25<01:05, 2.17s/it]\n 86%|████████▌ | 171/200 [10:26<00:49, 1.71s/it]\n 86%|████████▌ | 172/200 [10:26<00:38, 1.36s/it]\n 86%|████████▋ | 173/200 [10:32<01:16, 2.84s/it]\n 87%|████████▋ | 174/200 [10:39<01:40, 3.86s/it]\n 88%|████████▊ | 175/200 [10:39<01:11, 2.86s/it]\n 88%|████████▊ | 176/200 [10:40<00:52, 2.19s/it]\n 88%|████████▊ | 177/200 [10:40<00:39, 1.70s/it]\n 89%|████████▉ | 178/200 [10:41<00:29, 1.36s/it]\n 90%|████████▉ | 179/200 [10:47<00:59, 2.85s/it]\n 90%|█████████ | 180/200 [10:48<00:43, 2.15s/it]\n 90%|█████████ | 181/200 [10:48<00:31, 1.68s/it]\n 91%|█████████ | 182/200 [10:55<00:55, 3.06s/it]\n 92%|█████████▏| 183/200 [10:55<00:39, 2.30s/it]\n 92%|█████████▏| 184/200 [11:01<00:56, 3.50s/it]\n 92%|█████████▎| 185/200 [11:08<01:04, 4.31s/it]\n 93%|█████████▎| 186/200 [11:08<00:44, 3.17s/it]\n 94%|█████████▎| 187/200 [11:09<00:30, 2.38s/it]\n 94%|█████████▍| 188/200 [11:09<00:22, 1.86s/it]\n 94%|█████████▍| 189/200 [11:10<00:16, 1.47s/it]\n 95%|█████████▌| 190/200 [11:16<00:29, 2.98s/it]\n 96%|█████████▌| 191/200 [11:17<00:20, 2.27s/it]\n 96%|█████████▌| 192/200 [11:23<00:27, 3.46s/it]\n 96%|█████████▋| 193/200 [11:29<00:29, 4.28s/it]\n 97%|█████████▋| 194/200 [11:36<00:29, 4.87s/it]\n 98%|█████████▊| 195/200 [11:36<00:17, 3.56s/it]\n 98%|█████████▊| 196/200 [11:37<00:10, 2.66s/it]\n 98%|█████████▊| 197/200 [11:43<00:11, 3.76s/it]\n 99%|█████████▉| 198/200 [11:49<00:09, 4.51s/it]\n100%|█████████▉| 199/200 [11:50<00:03, 3.32s/it]\n100%|██████████| 200/200 [11:56<00:00, 4.19s/it]\n100%|██████████| 200/200 [11:56<00:00, 3.58s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1763430782/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_1763430782/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_1763430782/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_1763430782/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 : 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 : 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 (0,)"}\')\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 (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 : 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 : 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 : 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 : 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 : 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 : 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 (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 (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 : 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 : 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,)"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 716.6360545158386\nerrors 94\nmean length: 1.59\n\nthroughput (request / second): 0.27908168831265484\nthroughput (character / second): 0.4437398844171212\naverage request duration (s) 3.5830558383464814\n50%ile request duration (s) 6.161022782325745\n75%ile request duration (s) 6.272554457187653\n90%ile request duration (s) 6.33408522605896\n95%ile request duration (s) 6.374994397163391\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-prm-v1-pair-def-16871-v10-profiler is running
Tearing down inference service chaiml-prm-v1-pair-def-16871-v10-profiler
Service chaiml-prm-v1-pair-def-16871-v10-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.75s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-prm-v1-pair-def-16871-v10-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 0.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-prm-v1-pair-def-16871-v10-profiler
Waiting for inference service chaiml-prm-v1-pair-def-16871-v10-profiler to be ready
Inference service chaiml-prm-v1-pair-def-16871-v10-profiler ready after 151.54004502296448s
Pipeline stage MKMLProfilerDeployer completed in 152.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deploczc7n:/code/chaiverse_profiler_1763431762 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deploczc7n --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763431762 && python profiles.py profile --best_of_n 8 --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 1536 --output_tokens 1 --summary /code/chaiverse_profiler_1763431762/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deploczc7n:/code/chaiverse_profiler_1763432576 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deploczc7n --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763432576 && python profiles.py profile --best_of_n 8 --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 1536 --output_tokens 1 --summary /code/chaiverse_profiler_1763432576/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deploczc7n:/code/chaiverse_profiler_1763433296 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-prm-v1-pair-d34559414d53461bb522893d01290d3c6-deploczc7n --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1763433296 && python profiles.py profile --best_of_n 8 --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 1536 --output_tokens 1 --summary /code/chaiverse_profiler_1763433296/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 [00:00<01:40, 1.99it/s]\n 1%| | 2/200 [00:06<12:41, 3.84s/it]\n 2%|▏ | 3/200 [00:07<07:37, 2.32s/it]\n 2%|▏ | 4/200 [00:07<05:19, 1.63s/it]\n 2%|▎ | 5/200 [00:08<04:01, 1.24s/it]\n 3%|▎ | 6/200 [00:14<09:29, 2.94s/it]\n 4%|▎ | 7/200 [00:20<12:46, 3.97s/it]\n 4%|▍ | 8/200 [00:21<09:09, 2.86s/it]\n 4%|▍ | 9/200 [00:27<12:29, 3.92s/it]\n 5%|▌ | 10/200 [00:27<09:05, 2.87s/it]\n 6%|▌ | 11/200 [00:28<06:48, 2.16s/it]\n 6%|▌ | 12/200 [00:29<05:15, 1.68s/it]\n 6%|▋ | 13/200 [00:35<09:28, 3.04s/it]\n 7%|▋ | 14/200 [00:41<12:15, 3.96s/it]\n 8%|▊ | 15/200 [00:47<14:13, 4.61s/it]\n 8%|▊ | 16/200 [00:47<10:20, 3.37s/it]\n 8%|▊ | 17/200 [00:54<12:51, 4.22s/it]\n 9%|▉ | 18/200 [00:54<09:23, 3.10s/it]\n 10%|▉ | 19/200 [01:00<12:08, 4.02s/it]\n 10%|█ | 20/200 [01:01<08:52, 2.96s/it]\n 10%|█ | 21/200 [01:07<11:43, 3.93s/it]\n 11%|█ | 22/200 [01:13<13:40, 4.61s/it]\n 12%|█▏ | 23/200 [01:19<14:54, 5.05s/it]\n 12%|█▏ | 24/200 [01:20<10:49, 3.69s/it]\n 12%|█▎ | 25/200 [01:20<07:59, 2.74s/it]\n 13%|█▎ | 26/200 [01:21<06:06, 2.11s/it]\n 14%|█▎ | 27/200 [01:27<09:40, 3.35s/it]\n 14%|█▍ | 28/200 [01:28<07:08, 2.49s/it]\n 14%|█▍ | 29/200 [01:28<05:30, 1.93s/it]\n 15%|█▌ | 30/200 [01:29<04:18, 1.52s/it]\n 16%|█▌ | 31/200 [01:35<08:11, 2.91s/it]\n 16%|█▌ | 32/200 [01:41<10:53, 3.89s/it]\n 16%|█▋ | 33/200 [01:47<12:43, 4.57s/it]\n 17%|█▋ | 34/200 [01:48<09:15, 3.35s/it]\n 18%|█▊ | 35/200 [01:54<11:30, 4.19s/it]\n 18%|█▊ | 36/200 [02:00<13:05, 4.79s/it]\n 18%|█▊ | 37/200 [02:01<09:31, 3.51s/it]\n 19%|█▉ | 38/200 [02:07<11:35, 4.29s/it]\n 20%|█▉ | 39/200 [02:13<12:58, 4.83s/it]\n 20%|██ | 40/200 [02:13<09:28, 3.55s/it]\n 20%|██ | 41/200 [02:20<11:26, 4.32s/it]\n 21%|██ | 42/200 [02:20<08:26, 3.20s/it]\n 22%|██▏ | 43/200 [02:26<10:41, 4.08s/it]\n 22%|██▏ | 44/200 [02:32<12:09, 4.68s/it]\n 22%|██▎ | 45/200 [02:39<13:13, 5.12s/it]\n 23%|██▎ | 46/200 [02:45<13:52, 5.40s/it]\n 24%|██▎ | 47/200 [02:51<14:27, 5.67s/it]\n 24%|██▍ | 48/200 [02:57<14:44, 5.82s/it]\n 24%|██▍ | 49/200 [02:58<10:43, 4.26s/it]\n 25%|██▌ | 50/200 [02:58<07:52, 3.15s/it]\n 26%|██▌ | 51/200 [03:04<10:05, 4.06s/it]\n 26%|██▌ | 52/200 [03:11<11:38, 4.72s/it]\n 26%|██▋ | 53/200 [03:11<08:28, 3.46s/it]\n 27%|██▋ | 54/200 [03:17<10:27, 4.30s/it]\n 28%|██▊ | 55/200 [03:24<11:48, 4.89s/it]\n 28%|██▊ | 56/200 [03:30<12:36, 5.26s/it]\n 28%|██▊ | 57/200 [03:30<09:08, 3.83s/it]\n 29%|██▉ | 58/200 [03:37<10:50, 4.58s/it]\n 30%|██▉ | 59/200 [03:43<11:50, 5.04s/it]\n 30%|███ | 60/200 [03:43<08:34, 3.68s/it]\n 30%|███ | 61/200 [03:50<10:20, 4.46s/it]\n 31%|███ | 62/200 [03:56<11:23, 4.95s/it]\n 32%|███▏ | 63/200 [04:02<12:04, 5.29s/it]\n 32%|███▏ | 64/200 [04:02<08:47, 3.88s/it]\n 32%|███▎ | 65/200 [04:03<06:29, 2.88s/it]\n 33%|███▎ | 66/200 [04:03<04:52, 2.18s/it]\n 34%|███▎ | 67/200 [04:10<07:34, 3.42s/it]\n 34%|███▍ | 68/200 [04:10<05:36, 2.55s/it]\n 34%|███▍ | 69/200 [04:16<07:54, 3.63s/it]\n 35%|███▌ | 70/200 [04:23<09:31, 4.39s/it]\n 36%|███▌ | 71/200 [04:23<06:55, 3.22s/it]\n 36%|███▌ | 72/200 [04:29<08:44, 4.10s/it]\n 36%|███▋ | 73/200 [04:35<10:01, 4.73s/it]\n 37%|███▋ | 74/200 [04:36<07:17, 3.47s/it]\n 38%|███▊ | 75/200 [04:42<08:54, 4.27s/it]\n 38%|███▊ | 76/200 [04:43<06:29, 3.14s/it]\n 38%|███▊ | 77/200 [04:43<04:54, 2.39s/it]\n 39%|███▉ | 78/200 [04:49<07:10, 3.53s/it]\n 40%|███▉ | 79/200 [04:55<08:39, 4.29s/it]\n 40%|████ | 80/200 [05:02<09:45, 4.88s/it]\n 40%|████ | 81/200 [05:08<10:24, 5.25s/it]\n 41%|████ | 82/200 [05:14<10:47, 5.49s/it]\n 42%|████▏ | 83/200 [05:20<11:04, 5.68s/it]\n 42%|████▏ | 84/200 [05:20<07:58, 4.13s/it]\n 42%|████▎ | 85/200 [05:27<09:06, 4.75s/it]\n 43%|████▎ | 86/200 [05:27<06:35, 3.47s/it]\n 44%|████▎ | 87/200 [05:33<08:04, 4.29s/it]\n 44%|████▍ | 88/200 [05:40<09:05, 4.87s/it]\n 44%|████▍ | 89/200 [05:40<06:36, 3.57s/it]\n 45%|████▌ | 90/200 [05:46<07:58, 4.35s/it]\n 46%|████▌ | 91/200 [05:52<08:49, 4.86s/it]\n 46%|████▌ | 92/200 [05:53<06:26, 3.58s/it]\n 46%|████▋ | 93/200 [05:54<04:46, 2.68s/it]\n 47%|████▋ | 94/200 [05:54<03:36, 2.04s/it]\n 48%|████▊ | 95/200 [06:00<05:45, 3.29s/it]\n 48%|████▊ | 96/200 [06:01<04:16, 2.47s/it]\n 48%|████▊ | 97/200 [06:07<06:08, 3.58s/it]\n 49%|████▉ | 98/200 [06:13<07:21, 4.33s/it]\n 50%|████▉ | 99/200 [06:19<08:16, 4.91s/it]\n 50%|█████ | 100/200 [06:26<08:52, 5.32s/it]\n 50%|█████ | 101/200 [06:32<09:12, 5.58s/it]\n 51%|█████ | 102/200 [06:32<06:38, 4.06s/it]\n 52%|█████▏ | 103/200 [06:33<04:51, 3.00s/it]\n 52%|█████▏ | 104/200 [06:39<06:21, 3.98s/it]\n 52%|█████▎ | 105/200 [06:45<07:23, 4.67s/it]\n 53%|█████▎ | 106/200 [06:46<05:21, 3.42s/it]\n 54%|█████▎ | 107/200 [06:52<06:35, 4.25s/it]\n 54%|█████▍ | 108/200 [06:53<04:47, 3.12s/it]\n 55%|█████▍ | 109/200 [06:59<06:10, 4.07s/it]\n 55%|█████▌ | 110/200 [06:59<04:27, 2.98s/it]\n 56%|█████▌ | 111/200 [07:06<05:50, 3.94s/it]\n 56%|█████▌ | 112/200 [07:12<06:46, 4.62s/it]\n 56%|█████▋ | 113/200 [07:12<04:54, 3.39s/it]\n 57%|█████▋ | 114/200 [07:13<03:38, 2.54s/it]\n 57%|█████▊ | 115/200 [07:19<05:07, 3.62s/it]\n 58%|█████▊ | 116/200 [07:25<06:06, 4.37s/it]\n 58%|█████▊ | 117/200 [07:31<06:46, 4.90s/it]\n 59%|█████▉ | 118/200 [07:37<07:14, 5.30s/it]\n 60%|█████▉ | 119/200 [07:44<07:28, 5.54s/it]\n 60%|██████ | 120/200 [07:50<07:37, 5.71s/it]\n 60%|██████ | 121/200 [07:56<07:42, 5.85s/it]\n 61%|██████ | 122/200 [07:56<05:30, 4.24s/it]\n 62%|██████▏ | 123/200 [08:03<06:12, 4.84s/it]\n 62%|██████▏ | 124/200 [08:09<06:38, 5.25s/it]\n 62%|██████▎ | 125/200 [08:15<06:52, 5.50s/it]\n 63%|██████▎ | 126/200 [08:15<04:56, 4.00s/it]\n 64%|██████▎ | 127/200 [08:16<03:35, 2.96s/it]\n 64%|██████▍ | 128/200 [08:16<02:42, 2.26s/it]\n 64%|██████▍ | 129/200 [08:17<02:03, 1.74s/it]\n 65%|██████▌ | 130/200 [08:18<01:36, 1.38s/it]\n 66%|██████▌ | 131/200 [08:24<03:16, 2.84s/it]\n 66%|██████▌ | 132/200 [08:30<04:19, 3.82s/it]\n 66%|██████▋ | 133/200 [08:36<05:01, 4.49s/it]\n 67%|██████▋ | 134/200 [08:37<03:38, 3.32s/it]\n 68%|██████▊ | 135/200 [08:43<04:30, 4.16s/it]\n 68%|██████▊ | 136/200 [08:43<03:17, 3.09s/it]\n 68%|██████▊ | 137/200 [08:49<04:12, 4.01s/it]\n 69%|██████▉ | 138/200 [08:56<04:47, 4.64s/it]\n 70%|██████▉ | 139/200 [09:02<05:11, 5.10s/it]\n 70%|███████ | 140/200 [09:08<05:23, 5.40s/it]\n 70%|███████ | 141/200 [09:14<05:32, 5.63s/it]\n 71%|███████ | 142/200 [09:20<05:34, 5.76s/it]\n 72%|███████▏ | 143/200 [09:26<05:35, 5.89s/it]\n 72%|███████▏ | 144/200 [09:32<05:33, 5.96s/it]\n 72%|███████▎ | 145/200 [09:33<03:57, 4.32s/it]\n 73%|███████▎ | 146/200 [09:39<04:23, 4.88s/it]\n 74%|███████▎ | 147/200 [09:45<04:39, 5.28s/it]\n 74%|███████▍ | 148/200 [09:46<03:20, 3.85s/it]\n 74%|███████▍ | 149/200 [09:52<03:51, 4.53s/it]\n 75%|███████▌ | 150/200 [09:58<04:09, 5.00s/it]\n 76%|███████▌ | 151/200 [10:04<04:21, 5.35s/it]\n 76%|███████▌ | 152/200 [10:05<03:06, 3.89s/it]\n 76%|███████▋ | 153/200 [10:05<02:16, 2.90s/it]\n 77%|███████▋ | 154/200 [10:11<02:57, 3.87s/it]\n 78%|███████▊ | 155/200 [10:18<03:25, 4.56s/it]\n 78%|███████▊ | 156/200 [10:18<02:27, 3.35s/it]\n 78%|███████▊ | 157/200 [10:24<02:59, 4.18s/it]\n 79%|███████▉ | 158/200 [10:30<03:20, 4.77s/it]\n 80%|███████▉ | 159/200 [10:31<02:23, 3.50s/it]\n 80%|████████ | 160/200 [10:37<02:51, 4.29s/it]\n 80%|████████ | 161/200 [10:43<03:09, 4.85s/it]\n 81%|████████ | 162/200 [10:49<03:18, 5.22s/it]\n 82%|████████▏ | 163/200 [10:50<02:20, 3.80s/it]\n 82%|████████▏ | 164/200 [10:56<02:43, 4.55s/it]\n 82%|████████▎ | 165/200 [10:56<01:56, 3.34s/it]\n 83%|████████▎ | 166/200 [10:57<01:24, 2.50s/it]\n 84%|████████▎ | 167/200 [10:58<01:02, 1.91s/it]\n 84%|████████▍ | 168/200 [10:58<00:48, 1.52s/it]\n 84%|████████▍ | 169/200 [11:04<01:29, 2.90s/it]\n 85%|████████▌ | 170/200 [11:05<01:05, 2.17s/it]\n 86%|████████▌ | 171/200 [11:05<00:49, 1.71s/it]\n 86%|████████▌ | 172/200 [11:12<01:24, 3.03s/it]\n 86%|████████▋ | 173/200 [11:18<01:47, 3.99s/it]\n 87%|████████▋ | 174/200 [11:24<01:59, 4.61s/it]\n 88%|████████▊ | 175/200 [11:24<01:25, 3.40s/it]\n 88%|████████▊ | 176/200 [11:25<01:01, 2.55s/it]\n 88%|████████▊ | 177/200 [11:31<01:23, 3.63s/it]\n 89%|████████▉ | 178/200 [11:37<01:35, 4.36s/it]\n 90%|████████▉ | 179/200 [11:43<01:42, 4.89s/it]\n 90%|█████████ | 180/200 [11:44<01:11, 3.57s/it]\n 90%|█████████ | 181/200 [11:44<00:50, 2.66s/it]\n 91%|█████████ | 182/200 [11:50<01:06, 3.71s/it]\n 92%|█████████▏| 183/200 [11:57<01:15, 4.45s/it]\n 92%|█████████▏| 184/200 [11:57<00:52, 3.27s/it]\n 92%|█████████▎| 185/200 [12:03<01:01, 4.12s/it]\n 93%|█████████▎| 186/200 [12:04<00:42, 3.03s/it]\n 94%|█████████▎| 187/200 [12:04<00:29, 2.28s/it]\n 94%|█████████▍| 188/200 [12:11<00:41, 3.46s/it]\n 94%|█████████▍| 189/200 [12:17<00:47, 4.36s/it]\n 95%|█████████▌| 190/200 [12:17<00:32, 3.21s/it]\n 96%|█████████▌| 191/200 [12:18<00:21, 2.41s/it]\n 96%|█████████▌| 192/200 [12:24<00:28, 3.56s/it]\n 96%|█████████▋| 193/200 [12:30<00:30, 4.35s/it]\n 97%|█████████▋| 194/200 [12:31<00:19, 3.24s/it]\n 98%|█████████▊| 195/200 [12:32<00:12, 2.43s/it]\n 98%|█████████▊| 196/200 [12:32<00:07, 1.88s/it]\n 98%|█████████▊| 197/200 [12:33<00:04, 1.48s/it]\n 99%|█████████▉| 198/200 [12:39<00:05, 2.94s/it]\n100%|█████████▉| 199/200 [12:40<00:02, 2.21s/it]\n100%|██████████| 200/200 [12:46<00:00, 3.43s/it]\n100%|██████████| 200/200 [12:46<00:00, 3.83s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1763433296/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_1763433296/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_1763433296/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_1763433296/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 : 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 : 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 (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 : 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 : 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 : 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 (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 : 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 : 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 : 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 (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 : 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 (0,)"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 766.4407689571381\nerrors 83\nmean length: 1.755\n\nthroughput (request / second): 0.26094645287741036\nthroughput (character / second): 0.45796102479985523\naverage request duration (s) 3.832102744579315\n50%ile request duration (s) 6.0920127630233765\n75%ile request duration (s) 6.177869439125061\n90%ile request duration (s) 6.240601396560669\n95%ile request duration (s) 6.27530038356781\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-prm-v1-pair-def-16871-v10-profiler is running
Tearing down inference service chaiml-prm-v1-pair-def-16871-v10-profiler
Service chaiml-prm-v1-pair-def-16871-v10-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.75s
Shutdown handler de-registered
chaiml-prm-v1-pair-def_16871_v10 status is now torndown due to DeploymentManager action