Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v2-4-v1-mkmlizer
Waiting for job on cycy233-misllm-v2-4-v1-mkmlizer to finish
cycy233-misllm-v2-4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v2-4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ Version: 0.8.10 ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v2-4-v1-mkmlizer: ║ ║
cycy233-misllm-v2-4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v2-4-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-v2-4-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v2-4-v1-mkmlizer: Downloaded to shared memory in 49.111s
cycy233-misllm-v2-4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v2-4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v2-4-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 70%|███████ | 204/291 [00:01<00:00, 120.79it/s]
Loading 0: 100%|██████████| 291/291 [00:02<00:00, 97.75it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v2-4-v1-mkmlizer: quantized model in 10.012s
cycy233-misllm-v2-4-v1-mkmlizer: Processed model cycy233/misllm_v2.4 in 59.956s
cycy233-misllm-v2-4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v2-4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v2-4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v2-4-v1
cycy233-misllm-v2-4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v2-4-v1/config.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v2-4-v1/special_tokens_map.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v2-4-v1/tokenizer_config.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v2-4-v1/tokenizer.model
cycy233-misllm-v2-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v2-4-v1/tokenizer.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v2-4-v1/flywheel_model.0.safetensors
cycy233-misllm-v2-4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v2-4-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-v2-4-v1-mkmlizer: warnings.warn(
cycy233-misllm-v2-4-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-v2-4-v1-mkmlizer: warnings.warn(
cycy233-misllm-v2-4-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-v2-4-v1-mkmlizer: warnings.warn(
cycy233-misllm-v2-4-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-v2-4-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v2-4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v2-4-v1-mkmlizer: Saving duration: 0.216s
cycy233-misllm-v2-4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.268s
cycy233-misllm-v2-4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v2-4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v2-4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v2-4-v1_reward
cycy233-misllm-v2-4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v2-4-v1_reward/config.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v2-4-v1_reward/special_tokens_map.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v2-4-v1_reward/tokenizer_config.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v2-4-v1_reward/vocab.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v2-4-v1_reward/merges.txt
cycy233-misllm-v2-4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v2-4-v1_reward/tokenizer.json
cycy233-misllm-v2-4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v2-4-v1_reward/reward.tensors
Job cycy233-misllm-v2-4-v1-mkmlizer completed after 124.99s with status: succeeded
Stopping job with name cycy233-misllm-v2-4-v1-mkmlizer
Pipeline stage MKMLizer completed in 130.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v2-4-v1
Waiting for inference service cycy233-misllm-v2-4-v1 to be ready
Tearing down inference service cycy233-misllm-v2-4-v1
%s, retrying in %s seconds...
Creating inference service cycy233-misllm-v2-4-v1
Waiting for inference service cycy233-misllm-v2-4-v1 to be ready
Inference service cycy233-misllm-v2-4-v1 ready after 40.23141288757324s
Pipeline stage ISVCDeployer completed in 63.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8828983306884766s
Received healthy response to inference request in 1.150214433670044s
Received healthy response to inference request in 1.1704857349395752s
Received healthy response to inference request in 0.9599483013153076s
Received healthy response to inference request in 1.177889347076416s
5 requests
0 failed requests
5th percentile: 0.9980015277862548
10th percentile: 1.036054754257202
20th percentile: 1.1121612071990967
30th percentile: 1.1542686939239502
40th percentile: 1.1623772144317628
50th percentile: 1.1704857349395752
60th percentile: 1.1734471797943116
70th percentile: 1.176408624649048
80th percentile: 1.3188911437988282
90th percentile: 1.6008947372436524
95th percentile: 1.7418965339660644
99th percentile: 1.8546979713439942
mean time: 1.268287229537964
Pipeline stage StressChecker completed in 7.01s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v2-4_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v2-4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v2-4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v2-4-v1 is running
Tearing down inference service cycy233-misllm-v2-4-v1
Toredown service cycy233-misllm-v2-4-v1
Pipeline stage ISVCDeleter completed in 4.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v2-4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v2-4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v2-4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v2-4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v2-4-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v2-4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v2-4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v2-4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v2-4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v2-4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v2-4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v2-4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v2-4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.04s
cycy233-misllm-v2-4_v1 status is now torndown due to DeploymentManager action