Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v8-2-2-v1-mkmlizer
Waiting for job on cycy233-misllm-v8-2-2-v1-mkmlizer to finish
cycy233-misllm-v8-2-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ║ ║
cycy233-misllm-v8-2-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v8-2-2-v1-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-v8-2-2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v8-2-2-v1-mkmlizer: Downloaded to shared memory in 27.766s
cycy233-misllm-v8-2-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v8-2-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v8-2-2-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 93.26it/s]
Loading 0: 70%|███████ | 204/291 [00:02<00:00, 101.32it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 79.74it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v8-2-2-v1-mkmlizer: quantized model in 15.286s
cycy233-misllm-v8-2-2-v1-mkmlizer: Processed model cycy233/misllm_v8.2.2 in 45.383s
cycy233-misllm-v8-2-2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v8-2-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v8-2-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v8-2-2-v1
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v8-2-2-v1/config.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v8-2-2-v1/special_tokens_map.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v8-2-2-v1/tokenizer.model
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v8-2-2-v1/tokenizer_config.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v8-2-2-v1/tokenizer.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v8-2-2-v1/flywheel_model.0.safetensors
cycy233-misllm-v8-2-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v8-2-2-v1-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-v8-2-2-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-2-2-v1-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-v8-2-2-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-2-2-v1-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-v8-2-2-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-2-2-v1-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-v8-2-2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v8-2-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v8-2-2-v1-mkmlizer: Saving duration: 0.420s
cycy233-misllm-v8-2-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.557s
cycy233-misllm-v8-2-2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v8-2-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v8-2-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v8-2-2-v1_reward
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v8-2-2-v1_reward/config.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v8-2-2-v1_reward/tokenizer_config.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v8-2-2-v1_reward/special_tokens_map.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v8-2-2-v1_reward/merges.txt
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v8-2-2-v1_reward/vocab.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v8-2-2-v1_reward/tokenizer.json
cycy233-misllm-v8-2-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v8-2-2-v1_reward/reward.tensors
Job cycy233-misllm-v8-2-2-v1-mkmlizer completed after 72.89s with status: succeeded
Stopping job with name cycy233-misllm-v8-2-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v8-2-2-v1
Waiting for inference service cycy233-misllm-v8-2-2-v1 to be ready
Inference service cycy233-misllm-v8-2-2-v1 ready after 40.32629656791687s
Pipeline stage ISVCDeployer completed in 47.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.087702989578247s
Received healthy response to inference request in 1.1746671199798584s
Received healthy response to inference request in 8.476391315460205s
Received healthy response to inference request in 1.192213773727417s
Received healthy response to inference request in 1.189478874206543s
5 requests
0 failed requests
5th percentile: 1.1776294708251953
10th percentile: 1.1805918216705322
20th percentile: 1.186516523361206
30th percentile: 1.1900258541107178
40th percentile: 1.1911198139190673
50th percentile: 1.192213773727417
60th percentile: 1.550409460067749
70th percentile: 1.9086051464080809
80th percentile: 3.36544065475464
90th percentile: 5.920915985107422
95th percentile: 7.198653650283813
99th percentile: 8.220843782424927
mean time: 2.824090814590454
Pipeline stage StressChecker completed in 14.74s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cycy233-misllm-v8-2-2_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v8-2-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v8-2-2_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v8-2-2-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.23s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v8-2-2-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-2-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v8-2-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.63s
cycy233-misllm-v8-2-2_v1 status is now torndown due to DeploymentManager action