Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v8-1-2-5-v1-mkmlizer
Waiting for job on cycy233-misllm-v8-1-2-5-v1-mkmlizer to finish
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ║ ║
cycy233-misllm-v8-1-2-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v8-1-2-5-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-v8-1-2-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v8-1-2-5-v1-mkmlizer: Downloaded to shared memory in 29.581s
cycy233-misllm-v8-1-2-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v8-1-2-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v8-1-2-5-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 89.86it/s]
Loading 0: 70%|███████ | 204/291 [00:02<00:00, 102.15it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 82.07it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v8-1-2-5-v1-mkmlizer: quantized model in 15.851s
cycy233-misllm-v8-1-2-5-v1-mkmlizer: Processed model cycy233/misllm_v8.1.2.5 in 47.910s
cycy233-misllm-v8-1-2-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v8-1-2-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v8-1-2-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v8-1-2-5-v1
cycy233-misllm-v8-1-2-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v8-1-2-5-v1/config.json
cycy233-misllm-v8-1-2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v8-1-2-5-v1/tokenizer_config.json
cycy233-misllm-v8-1-2-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v8-1-2-5-v1/special_tokens_map.json
cycy233-misllm-v8-1-2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v8-1-2-5-v1/tokenizer.model
cycy233-misllm-v8-1-2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v8-1-2-5-v1/tokenizer.json
cycy233-misllm-v8-1-2-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v8-1-2-5-v1/flywheel_model.0.safetensors
cycy233-misllm-v8-1-2-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v8-1-2-5-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-v8-1-2-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-1-2-5-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-v8-1-2-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-1-2-5-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-v8-1-2-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-1-2-5-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-v8-1-2-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v8-1-2-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v8-1-2-5-v1-mkmlizer: Saving duration: 0.418s
cycy233-misllm-v8-1-2-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.264s
cycy233-misllm-v8-1-2-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v8-1-2-5-v1_reward/reward.tensors
Job cycy233-misllm-v8-1-2-5-v1-mkmlizer completed after 82.72s with status: succeeded
Stopping job with name cycy233-misllm-v8-1-2-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v8-1-2-5-v1
Waiting for inference service cycy233-misllm-v8-1-2-5-v1 to be ready
Tearing down inference service cycy233-misllm-v8-1-2-5-v1
%s, retrying in %s seconds...
Creating inference service cycy233-misllm-v8-1-2-5-v1
Waiting for inference service cycy233-misllm-v8-1-2-5-v1 to be ready
Inference service cycy233-misllm-v8-1-2-5-v1 ready after 513.0303275585175s
Pipeline stage ISVCDeployer completed in 1128.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4159486293792725s
Received healthy response to inference request in 1.169903039932251s
Received healthy response to inference request in 1.183445930480957s
Received healthy response to inference request in 3.881375551223755s
Received healthy response to inference request in 1.174351692199707s
5 requests
0 failed requests
5th percentile: 1.1707927703857421
10th percentile: 1.1716825008392333
20th percentile: 1.1734619617462159
30th percentile: 1.176170539855957
40th percentile: 1.1798082351684571
50th percentile: 1.183445930480957
60th percentile: 1.676447010040283
70th percentile: 2.169448089599609
80th percentile: 2.709034013748169
90th percentile: 3.2952047824859623
95th percentile: 3.588290166854858
99th percentile: 3.8227584743499756
mean time: 1.9650049686431885
Pipeline stage StressChecker completed in 10.39s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v8-1-2-5_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v8-1-2-5_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v8-1-2-5_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v8-1-2-5-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v8-1-2-5-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-1-2-5-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-1-2-5-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-1-2-5-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-1-2-5-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-1-2-5-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v8-1-2-5-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-1-2-5-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-1-2-5-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-1-2-5-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-1-2-5-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-1-2-5-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-1-2-5-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.45s
cycy233-misllm-v8-1-2-5_v1 status is now torndown due to DeploymentManager action