Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v9-0-1-v10-mkmlizer
Waiting for job on cycy233-misllm-v9-0-1-v10-mkmlizer to finish
cycy233-misllm-v9-0-1-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ /___/ ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ belonging to: ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ║ ║
cycy233-misllm-v9-0-1-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v9-0-1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
cycy233-misllm-v9-0-1-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v9-0-1-v10-mkmlizer: Downloaded to shared memory in 17.105s
cycy233-misllm-v9-0-1-v10-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v9-0-1-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v9-0-1-v10-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 96.15it/s]
Loading 0: 70%|███████ | 204/291 [00:01<00:00, 108.13it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 86.33it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v9-0-1-v10-mkmlizer: quantized model in 14.865s
cycy233-misllm-v9-0-1-v10-mkmlizer: Processed model cycy233/misllm_v9.0.1 in 34.259s
cycy233-misllm-v9-0-1-v10-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v9-0-1-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v9-0-1-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v9-0-1-v10
cycy233-misllm-v9-0-1-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-1-v10/config.json
cycy233-misllm-v9-0-1-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-1-v10/special_tokens_map.json
cycy233-misllm-v9-0-1-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-1-v10/tokenizer_config.json
cycy233-misllm-v9-0-1-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v9-0-1-v10/tokenizer.model
cycy233-misllm-v9-0-1-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-1-v10/tokenizer.json
cycy233-misllm-v9-0-1-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v9-0-1-v10/flywheel_model.0.safetensors
cycy233-misllm-v9-0-1-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v9-0-1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-misllm-v9-0-1-v10-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-misllm-v9-0-1-v10-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-misllm-v9-0-1-v10-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
cycy233-misllm-v9-0-1-v10-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v9-0-1-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v9-0-1-v10-mkmlizer: Saving duration: 0.399s
cycy233-misllm-v9-0-1-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.886s
cycy233-misllm-v9-0-1-v10-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v9-0-1-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v9-0-1-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v9-0-1-v10_reward
Job cycy233-misllm-v9-0-1-v10-mkmlizer completed after 62.53s with status: succeeded
Stopping job with name cycy233-misllm-v9-0-1-v10-mkmlizer
Pipeline stage MKMLizer completed in 67.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v9-0-1-v10
Waiting for inference service cycy233-misllm-v9-0-1-v10 to be ready
Inference service cycy233-misllm-v9-0-1-v10 ready after 40.255197048187256s
Pipeline stage ISVCDeployer completed in 48.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.92103910446167s
Received healthy response to inference request in 0.926084041595459s
Received healthy response to inference request in 0.7610657215118408s
Received healthy response to inference request in 0.9798488616943359s
Received healthy response to inference request in 0.9151220321655273s
5 requests
0 failed requests
5th percentile: 0.7918769836425781
10th percentile: 0.8226882457733155
20th percentile: 0.8843107700347901
30th percentile: 0.9173144340515137
40th percentile: 0.9216992378234863
50th percentile: 0.926084041595459
60th percentile: 0.9475899696350097
70th percentile: 0.9690958976745605
80th percentile: 1.1680869102478029
90th percentile: 1.5445630073547365
95th percentile: 1.732801055908203
99th percentile: 1.8833914947509764
mean time: 1.1006319522857666
Pipeline stage StressChecker completed in 6.11s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.02s
cycy233-misllm-v9-0-1_v10 status is now deployed due to DeploymentManager action
cycy233-misllm-v9-0-1_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v9-0-1_v10
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v9-0-1-v10 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.69s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v9-0-1-v10/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-1-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-1-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-1-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-1-v10/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-1-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v9-0-1-v10_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-1-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-1-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-1-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-1-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-1-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-1-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.99s
cycy233-misllm-v9-0-1_v10 status is now torndown due to DeploymentManager action