Running pipeline stage MKMLizer
Starting job with name shuttleai-shuttle-2-5-1-5730-v5-mkmlizer
Waiting for job on shuttleai-shuttle-2-5-1-5730-v5-mkmlizer to finish
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ _____ __ __ ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ /___/ ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ Version: 0.9.7 ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ https://mk1.ai ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ The license key for the current software has been verified as ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ belonging to: ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ Chai Research Corp. ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ║ ║
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: Downloaded to shared memory in 28.383s
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcq35j8co, device:0
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: quantized model in 36.082s
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: Processed model shuttleai/shuttle-2.5.1-mini-beta in 64.465s
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: creating bucket guanaco-mkml-models
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v5
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v5/config.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v5/special_tokens_map.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v5/tokenizer_config.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v5/tokenizer.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v5/flywheel_model.0.safetensors
shuttleai-shuttle-2-5-1-5730-v5-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.
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-1-5730-v5-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.
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: Saving duration: 0.321s
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.524s
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: creating bucket guanaco-reward-models
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v5_reward
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v5_reward/config.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v5_reward/special_tokens_map.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v5_reward/tokenizer_config.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v5_reward/merges.txt
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v5_reward/vocab.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v5_reward/tokenizer.json
shuttleai-shuttle-2-5-1-5730-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v5_reward/reward.tensors
Job shuttleai-shuttle-2-5-1-5730-v5-mkmlizer completed after 107.12s with status: succeeded
Stopping job with name shuttleai-shuttle-2-5-1-5730-v5-mkmlizer
Pipeline stage MKMLizer completed in 108.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service shuttleai-shuttle-2-5-1-5730-v5
Waiting for inference service shuttleai-shuttle-2-5-1-5730-v5 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service shuttleai-shuttle-2-5-1-5730-v5 ready after 90.79041242599487s
Pipeline stage ISVCDeployer completed in 92.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6664016246795654s
Received healthy response to inference request in 1.6366381645202637s
Received healthy response to inference request in 1.6070506572723389s
Received healthy response to inference request in 1.6128296852111816s
Received healthy response to inference request in 1.561903953552246s
5 requests
0 failed requests
5th percentile: 1.5709332942962646
10th percentile: 1.5799626350402831
20th percentile: 1.5980213165283204
30th percentile: 1.6082064628601074
40th percentile: 1.6105180740356446
50th percentile: 1.6128296852111816
60th percentile: 1.6223530769348145
70th percentile: 1.6318764686584473
80th percentile: 1.8425908565521243
90th percentile: 2.2544962406158446
95th percentile: 2.460448932647705
99th percentile: 2.625211086273193
mean time: 1.816964817047119
Pipeline stage StressChecker completed in 9.74s
shuttleai-shuttle-2-5-1-_5730_v5 status is now deployed due to DeploymentManager action
shuttleai-shuttle-2-5-1-_5730_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of shuttleai-shuttle-2-5-1-_5730_v5
Running pipeline stage ISVCDeleter
Checking if service shuttleai-shuttle-2-5-1-5730-v5 is running
Tearing down inference service shuttleai-shuttle-2-5-1-5730-v5
Service shuttleai-shuttle-2-5-1-5730-v5 has been torndown
Pipeline stage ISVCDeleter completed in 4.88s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key shuttleai-shuttle-2-5-1-5730-v5/config.json from bucket guanaco-mkml-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key shuttleai-shuttle-2-5-1-5730-v5_reward/config.json from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.06s
shuttleai-shuttle-2-5-1-_5730_v5 status is now torndown due to DeploymentManager action