Running pipeline stage MKMLizer
Starting job with name cycy233-llm3-0-v3-mkmlizer
Waiting for job on cycy233-llm3-0-v3-mkmlizer to finish
cycy233-llm3-0-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-llm3-0-v3-mkmlizer: ║ _____ __ __ ║
cycy233-llm3-0-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-llm3-0-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-llm3-0-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-llm3-0-v3-mkmlizer: ║ /___/ ║
cycy233-llm3-0-v3-mkmlizer: ║ ║
cycy233-llm3-0-v3-mkmlizer: ║ Version: 0.8.10 ║
cycy233-llm3-0-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-llm3-0-v3-mkmlizer: ║ ║
cycy233-llm3-0-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-llm3-0-v3-mkmlizer: ║ belonging to: ║
cycy233-llm3-0-v3-mkmlizer: ║ ║
cycy233-llm3-0-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-llm3-0-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-llm3-0-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-llm3-0-v3-mkmlizer: ║ ║
cycy233-llm3-0-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-llm3-0-v3-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-llm3-0-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-llm3-0-v3-mkmlizer: Downloaded to shared memory in 14.217s
cycy233-llm3-0-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-llm3-0-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-llm3-0-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 36%|███▋ | 106/291 [00:01<00:02, 77.37it/s]
Loading 0: 74%|███████▍ | 215/291 [00:02<00:00, 91.82it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 74.38it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-llm3-0-v3-mkmlizer: quantized model in 11.636s
cycy233-llm3-0-v3-mkmlizer: Processed model cycy233/llm3.0 in 26.875s
cycy233-llm3-0-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-llm3-0-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-llm3-0-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-llm3-0-v3
cycy233-llm3-0-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-llm3-0-v3/config.json
cycy233-llm3-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-llm3-0-v3/tokenizer_config.json
cycy233-llm3-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-llm3-0-v3/tokenizer.model
cycy233-llm3-0-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-llm3-0-v3/special_tokens_map.json
cycy233-llm3-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-llm3-0-v3/tokenizer.json
cycy233-llm3-0-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-llm3-0-v3/flywheel_model.0.safetensors
cycy233-llm3-0-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-llm3-0-v3-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-llm3-0-v3-mkmlizer: warnings.warn(
cycy233-llm3-0-v3-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-llm3-0-v3-mkmlizer: warnings.warn(
cycy233-llm3-0-v3-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-llm3-0-v3-mkmlizer: warnings.warn(
cycy233-llm3-0-v3-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-llm3-0-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-llm3-0-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-llm3-0-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-llm3-0-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-llm3-0-v3_reward
cycy233-llm3-0-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-llm3-0-v3_reward/special_tokens_map.json
cycy233-llm3-0-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-llm3-0-v3_reward/config.json
cycy233-llm3-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-llm3-0-v3_reward/tokenizer_config.json
cycy233-llm3-0-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-llm3-0-v3_reward/merges.txt
cycy233-llm3-0-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-llm3-0-v3_reward/vocab.json
cycy233-llm3-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-llm3-0-v3_reward/tokenizer.json
cycy233-llm3-0-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-llm3-0-v3_reward/reward.tensors
Job cycy233-llm3-0-v3-mkmlizer completed after 52.48s with status: succeeded
Stopping job with name cycy233-llm3-0-v3-mkmlizer
Pipeline stage MKMLizer completed in 56.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-llm3-0-v3
Waiting for inference service cycy233-llm3-0-v3 to be ready
Inference service cycy233-llm3-0-v3 ready after 30.18130350112915s
Pipeline stage ISVCDeployer completed in 37.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1725142002105713s
Received healthy response to inference request in 1.1666741371154785s
Received healthy response to inference request in 1.2022202014923096s
Received healthy response to inference request in 1.2546470165252686s
Received healthy response to inference request in 1.2360622882843018s
5 requests
0 failed requests
5th percentile: 1.1737833499908448
10th percentile: 1.180892562866211
20th percentile: 1.1951109886169433
30th percentile: 1.208988618850708
40th percentile: 1.222525453567505
50th percentile: 1.2360622882843018
60th percentile: 1.2434961795806885
70th percentile: 1.2509300708770752
80th percentile: 1.4382204532623293
90th percentile: 1.8053673267364503
95th percentile: 1.9889407634735106
99th percentile: 2.135799512863159
mean time: 1.406423568725586
Pipeline stage StressChecker completed in 7.65s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-llm3-0_v3 status is now deployed due to DeploymentManager action
cycy233-llm3-0_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-llm3-0_v3
Running pipeline stage ISVCDeleter
Checking if service cycy233-llm3-0-v3 is running
Tearing down inference service cycy233-llm3-0-v3
Toredown service cycy233-llm3-0-v3
Pipeline stage ISVCDeleter completed in 6.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-llm3-0-v3/config.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-llm3-0-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-llm3-0-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-llm3-0-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.94s
cycy233-llm3-0_v3 status is now torndown due to DeploymentManager action