Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v9-0-2-v2-mkmlizer
Waiting for job on cycy233-misllm-v9-0-2-v2-mkmlizer to finish
cycy233-misllm-v9-0-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ /___/ ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ belonging to: ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ║ ║
cycy233-misllm-v9-0-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v9-0-2-v2-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-v9-0-2-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v9-0-2-v2-mkmlizer: Downloaded to shared memory in 37.376s
cycy233-misllm-v9-0-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v9-0-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v9-0-2-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:00<00:01, 98.38it/s]
Loading 0: 70%|███████ | 204/291 [00:01<00:00, 106.58it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 83.89it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v9-0-2-v2-mkmlizer: quantized model in 14.633s
cycy233-misllm-v9-0-2-v2-mkmlizer: Processed model cycy233/misllm_v9.0.2 in 54.247s
cycy233-misllm-v9-0-2-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v9-0-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v9-0-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v9-0-2-v2
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-2-v2/special_tokens_map.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-2-v2/config.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-2-v2/tokenizer.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v9-0-2-v2/tokenizer.model
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-2-v2/tokenizer_config.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v9-0-2-v2/flywheel_model.0.safetensors
cycy233-misllm-v9-0-2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v9-0-2-v2-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-v9-0-2-v2-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-2-v2-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-v9-0-2-v2-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-2-v2-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-v9-0-2-v2-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-2-v2-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-v9-0-2-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v9-0-2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v9-0-2-v2-mkmlizer: Saving duration: 0.422s
cycy233-misllm-v9-0-2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.206s
cycy233-misllm-v9-0-2-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v9-0-2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v9-0-2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v9-0-2-v2_reward
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v9-0-2-v2_reward/config.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v9-0-2-v2_reward/vocab.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v9-0-2-v2_reward/tokenizer_config.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v9-0-2-v2_reward/special_tokens_map.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v9-0-2-v2_reward/merges.txt
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v9-0-2-v2_reward/tokenizer.json
cycy233-misllm-v9-0-2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v9-0-2-v2_reward/reward.tensors
Job cycy233-misllm-v9-0-2-v2-mkmlizer completed after 83.46s with status: succeeded
Stopping job with name cycy233-misllm-v9-0-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 87.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v9-0-2-v2
Waiting for inference service cycy233-misllm-v9-0-2-v2 to be ready
Inference service cycy233-misllm-v9-0-2-v2 ready after 361.87335538864136s
Pipeline stage ISVCDeployer completed in 369.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9649183750152588s
Received healthy response to inference request in 10.69776177406311s
Received healthy response to inference request in 1.7771122455596924s
Received healthy response to inference request in 1.1776354312896729s
Received healthy response to inference request in 1.1766071319580078s
5 requests
0 failed requests
5th percentile: 1.1768127918243407
10th percentile: 1.1770184516906739
20th percentile: 1.17742977142334
30th percentile: 1.2975307941436767
40th percentile: 1.5373215198516847
50th percentile: 1.7771122455596924
60th percentile: 1.852234697341919
70th percentile: 1.9273571491241455
80th percentile: 3.711487054824831
90th percentile: 7.204624414443971
95th percentile: 8.951193094253538
99th percentile: 10.348448038101196
mean time: 3.3588069915771483
Pipeline stage StressChecker completed in 17.57s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-misllm-v9-0-2_v2 status is now deployed due to DeploymentManager action
admin requested tearing down of cycy233-misllm-v9-0-2_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v9-0-2-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v9-0-2-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-2-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-0-2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v9-0-2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-0-2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.47s
cycy233-misllm-v9-0-2_v2 status is now torndown due to DeploymentManager action