Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ Version: 0.9.9 ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: Downloaded to shared memory in 60.133s
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa4ss88de, device:0
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: quantized model in 29.287s
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.10_steps500 in 89.419s
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-1-2446-v1
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-1-2446-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-1-2446-v1/config.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-1-2446-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-1-2446-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-1-2446-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: Saving duration: 1.435s
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.441s
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-1-2446-v1_reward
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-1-2446-v1_reward/config.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-1-2446-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-1-2446-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-1-2446-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-1-2446-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-1-2446-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-1-2446-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer completed after 137.57s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-1-2446-v1-mkmlizer
Pipeline stage MKMLizer completed in 138.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-1-2446-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-1-2446-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service bbchicago-brt-8b-l3-v1-1-2446-v1 ready after 161.0440273284912s
Pipeline stage ISVCDeployer completed in 163.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.145770311355591s
Received healthy response to inference request in 1.3780426979064941s
Received healthy response to inference request in 1.363692283630371s
Received healthy response to inference request in 1.3973093032836914s
Received healthy response to inference request in 1.4015262126922607s
5 requests
0 failed requests
5th percentile: 1.3665623664855957
10th percentile: 1.3694324493408203
20th percentile: 1.3751726150512695
30th percentile: 1.3818960189819336
40th percentile: 1.3896026611328125
50th percentile: 1.3973093032836914
60th percentile: 1.398996067047119
70th percentile: 1.4006828308105468
80th percentile: 1.5503750324249268
90th percentile: 1.848072671890259
95th percentile: 1.9969214916229248
99th percentile: 2.1160005474090577
mean time: 1.5372681617736816
Pipeline stage StressChecker completed in 8.45s
bbchicago-brt-8b-l3-v1-1_2446_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-1_2446_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-1_2446_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-1-2446-v1 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-1-2446-v1
Service bbchicago-brt-8b-l3-v1-1-2446-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.75s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-1-2446-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 11.27s
bbchicago-brt-8b-l3-v1-1_2446_v1 status is now torndown due to DeploymentManager action