Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer to finish
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-7538-v4-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.
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: Downloaded to shared memory in 21.015s
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 82.76it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.13it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 138.54it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: quantized model in 18.849s
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e11.1 in 40.916s
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v4
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v4/config.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v4/special_tokens_map.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v4/tokenizer_config.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v4/tokenizer.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v4/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-7538-v4-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.
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7538-v4-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.
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7538-v4-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()
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: Saving duration: 0.294s
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.163s
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v4_reward
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v4_reward/config.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v4_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v4_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v4_reward/merges.txt
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v4_reward/vocab.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v4_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v4_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer completed after 300.1s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-7538-v4-mkmlizer
Pipeline stage MKMLizer completed in 300.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-7538-v4
Waiting for inference service cgato-l3-thespice-8b-dpo-7538-v4 to be ready
Inference service cgato-l3-thespice-8b-dpo-7538-v4 ready after 40.27853322029114s
Pipeline stage ISVCDeployer completed in 45.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0920016765594482s
Received healthy response to inference request in 1.2294580936431885s
Received healthy response to inference request in 1.260129690170288s
Received healthy response to inference request in 1.2233729362487793s
Received healthy response to inference request in 1.215383529663086s
5 requests
0 failed requests
5th percentile: 1.2169814109802246
10th percentile: 1.2185792922973633
20th percentile: 1.2217750549316406
30th percentile: 1.224589967727661
40th percentile: 1.2270240306854248
50th percentile: 1.2294580936431885
60th percentile: 1.2417267322540284
70th percentile: 1.2539953708648681
80th percentile: 1.4265040874481203
90th percentile: 1.7592528820037843
95th percentile: 1.925627279281616
99th percentile: 2.0587267971038816
mean time: 1.404069185256958
Pipeline stage StressChecker completed in 7.63s
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
cgato-l3-thespice-8b-dpo_7538_v4 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_7538_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dpo_7538_v4
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-7538-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-7538-v4/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-7538-v4_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-7538-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.70s
cgato-l3-thespice-8b-dpo_7538_v4 status is now torndown due to DeploymentManager action