run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rica40325-feedback-and-d-8178-v1-mkmlizer
Waiting for job on rica40325-feedback-and-d-8178-v1-mkmlizer to finish
Stopping job with name rica40325-feedback-and-d-8178-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name rica40325-feedback-and-d-8178-v1-mkmlizer
Waiting for job on rica40325-feedback-and-d-8178-v1-mkmlizer to finish
rica40325-feedback-and-d-8178-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ _____ __ __ ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ /___/ ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ Version: 0.10.1 ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ https://mk1.ai ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ belonging to: ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ Chai Research Corp. ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ║ ║
rica40325-feedback-and-d-8178-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-feedback-and-d-8178-v1-mkmlizer: quantized model in 25.460s
rica40325-feedback-and-d-8178-v1-mkmlizer: Processed model rica40325/feedback-and-dpo3kstep in 62.043s
rica40325-feedback-and-d-8178-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedback-and-d-8178-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedback-and-d-8178-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedback-and-d-8178-v1
rica40325-feedback-and-d-8178-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedback-and-d-8178-v1/config.json
rica40325-feedback-and-d-8178-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedback-and-d-8178-v1/special_tokens_map.json
rica40325-feedback-and-d-8178-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedback-and-d-8178-v1/tokenizer_config.json
rica40325-feedback-and-d-8178-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedback-and-d-8178-v1/tokenizer.json
rica40325-feedback-and-d-8178-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-feedback-and-d-8178-v1/flywheel_model.0.safetensors
rica40325-feedback-and-d-8178-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 6/291 [00:00<00:04, 59.92it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:04, 66.29it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:02, 88.14it/s]
Loading 0: 15%|█▍ | 43/291 [00:00<00:02, 90.11it/s]
Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 99.46it/s]
Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 95.55it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:07, 28.95it/s]
Loading 0: 31%|███ | 90/291 [00:01<00:06, 32.54it/s]
Loading 0: 34%|███▍ | 99/291 [00:02<00:04, 39.41it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 49.22it/s]
Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 55.16it/s]
Loading 0: 47%|████▋ | 137/291 [00:02<00:02, 68.23it/s]
Loading 0: 51%|█████ | 148/291 [00:02<00:01, 72.21it/s]
Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 77.58it/s]
Loading 0: 60%|██████ | 175/291 [00:02<00:01, 87.12it/s]
Loading 0: 64%|██████▍ | 187/291 [00:03<00:03, 28.21it/s]
Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 37.59it/s]
Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 44.79it/s]
Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 55.75it/s]
Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 60.09it/s]
Loading 0: 86%|████████▌ | 250/291 [00:04<00:00, 64.04it/s]
Loading 0: 91%|█████████ | 265/291 [00:04<00:00, 75.37it/s]
Loading 0: 95%|█████████▌| 277/291 [00:04<00:00, 78.86it/s]
Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 49.38it/s]
Job rica40325-feedback-and-d-8178-v1-mkmlizer completed after 84.87s with status: succeeded
Stopping job with name rica40325-feedback-and-d-8178-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedback-and-d-8178-v1
Waiting for inference service rica40325-feedback-and-d-8178-v1 to be ready
Inference service rica40325-feedback-and-d-8178-v1 ready after 311.1399586200714s
Pipeline stage MKMLDeployer completed in 311.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9478678703308105s
Received healthy response to inference request in 1.5536153316497803s
Received healthy response to inference request in 1.4685263633728027s
Received healthy response to inference request in 1.3209412097930908s
Received healthy response to inference request in 1.1753628253936768s
5 requests
0 failed requests
5th percentile: 1.2044785022735596
10th percentile: 1.2335941791534424
20th percentile: 1.291825532913208
30th percentile: 1.3504582405090333
40th percentile: 1.409492301940918
50th percentile: 1.4685263633728027
60th percentile: 1.5025619506835937
70th percentile: 1.5365975379943848
80th percentile: 1.6324658393859863
90th percentile: 1.7901668548583984
95th percentile: 1.8690173625946045
99th percentile: 1.9320977687835694
mean time: 1.4932627201080322
Pipeline stage StressChecker completed in 8.46s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.26s
rica40325-feedback-and-d_8178_v1 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-feedback-and-d-8178-v1-profiler
Waiting for inference service rica40325-feedback-and-d-8178-v1-profiler to be ready
Inference service rica40325-feedback-and-d-8178-v1-profiler ready after 200.45958185195923s
Pipeline stage MKMLProfilerDeployer completed in 200.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.34s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-feedback-and-d-8178-v1-profiler is running
Tearing down inference service rica40325-feedback-and-d-8178-v1-profiler
Service rica40325-feedback-and-d-8178-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.81s
rica40325-feedback-and-d_8178_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-feedback-and-d_8178_v1 status is now torndown due to DeploymentManager action